{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "ckbbj5diaHkg" }, "source": [ "# Fine-tuning Embeddings for RAG on Specific Data\n", "\n", "As we start our \"fine-tuning\" week, we'll start with the lowest hanging improvement one can do for RAG - which is:\n", "\n", "Fine-tuning embeddings!\n", "\n", "- 🀝 Breakout Room #1:\n", " - Task 1: Dependencies and Boilerplate\n", " - Task 2: Loading Data\n", " - Task 3: Constructing a Fine-tuning Dataset\n", " - Task 4: Fine-tuning `snowflake-arctic-embed-m`\n", " - Task 5: Evaluating our Retriever\n", "\n", "- 🀝 Breakout Room #2:\n", " - Task 1: Vibe Checking Our LCEL RAG Chain\n", " - Task 2: Ragas Evaluation\n", "\n" ] }, { "cell_type": "markdown", "metadata": { "id": "2xwor_3X6ODX" }, "source": [ "#### Basic Overview of Fine-tuning Embeddings\n", "\n", "In essence, what we want to do when we fine-tune our embedding models is very simple:\n", "\n", "```\n", "Move the embeddings for questions relating to a document\n", "closer together with that document\n", "```\n", "\n", "We can think of fine-tuning our embedding models as follows:\n", "\n", "1) We have some pair of text items that *should* be closer together\n", " - `Question`, `Document` pairs\n", " - EX: `Who drives the bus?`, `The bus was driven by Kyle, the Bus Driver`.\n", "\n", "2) We use these pairs as labeled data to fine-tune our embedding model.\n", "\n", "The process of training helps the model more accurately associate our questions with the correct documents." ] }, { "cell_type": "markdown", "metadata": { "id": "DX5R3HVz6FOQ" }, "source": [ "#####❓ Question #1:\n", "\n", "Describe the nuance between using Q&D pairs to train the embedding model vs. inter-document pairs/related sentences.\n", "\n", "What caveats does this approach have? Are there any special considerations for what kind of Q's we should use?\n", "\n", "---\n", "\n", "**ANSWER:**\n", "\n", "We are specifically relating *the questions* to *the documents*. This means that we are making our embedding model at the very specific task of relating potential questions to specific documents.\n", "\n", "There are many caveats, but the main ones are:\n", "\n", "- Your Q's should reflect the Q's of your users\n", "- This kind of fine-tuning will (purposefully) \"overfit\" on your data; this is the desired result in this case." ] }, { "cell_type": "markdown", "metadata": { "id": "-NkSaurzbpyS" }, "source": [ "## Task 1: Dependencies and Boilerplate\n", "\n", "We'll set up our `nest_asyncio` so we can leverage async loops in our Notebook.\n", "\n", "We'll also install the required libraries we'll be using today, and set up our OpenAI API key!" ] }, { "cell_type": "markdown", "metadata": { "id": "9c_EUibmcDU3" }, "source": [ "### Nest Asyncio" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "id": "zq-6s7LbPnKH" }, "outputs": [], "source": [ "import nest_asyncio\n", "\n", "nest_asyncio.apply()" ] }, { "cell_type": "markdown", "metadata": { "id": "R8uFz8RVcFFu" }, "source": [ "### Install Dependencies" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "ulZIBA1ZoSsV", "outputId": "fe410622-df5e-4093-99ef-34cb82e4f4ce" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m50.4/50.4 kB\u001b[0m \u001b[31m4.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m396.4/396.4 kB\u001b[0m \u001b[31m12.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m207.2/207.2 kB\u001b[0m \u001b[31m17.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m52.0/52.0 kB\u001b[0m \u001b[31m4.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.0/1.0 MB\u001b[0m \u001b[31m40.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.3/2.3 MB\u001b[0m \u001b[31m82.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m436.4/436.4 kB\u001b[0m \u001b[31m28.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m294.6/294.6 kB\u001b[0m \u001b[31m21.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m383.5/383.5 kB\u001b[0m \u001b[31m27.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m245.3/245.3 kB\u001b[0m \u001b[31m20.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.1/1.1 MB\u001b[0m \u001b[31m61.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m76.4/76.4 kB\u001b[0m \u001b[31m6.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m78.0/78.0 kB\u001b[0m \u001b[31m6.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m318.9/318.9 kB\u001b[0m \u001b[31m27.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.3/49.3 kB\u001b[0m \u001b[31m4.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m141.9/141.9 kB\u001b[0m \u001b[31m15.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m54.5/54.5 kB\u001b[0m \u001b[31m4.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m4.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25h" ] } ], "source": [ "!pip install -qU langchain_experimental langchain_openai langchain_huggingface langchain_core==0.2.38 langchain langchain_community langchain-text-splitters huggingface_hub" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "3GFD7B-tOCrx", "outputId": "9cff078c-a8b7-4cde-dae1-d5bf2985c270" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/981.5 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[91m━━\u001b[0m\u001b[91mβ•Έ\u001b[0m\u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m61.4/981.5 kB\u001b[0m \u001b[31m1.6 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K \u001b[91m━━━━━━━\u001b[0m\u001b[90mβ•Ί\u001b[0m\u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m174.1/981.5 kB\u001b[0m \u001b[31m3.0 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K \u001b[91m━━━━━━━━━━━━━━━━━\u001b[0m\u001b[91mβ•Έ\u001b[0m\u001b[90m━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m430.1/981.5 kB\u001b[0m \u001b[31m4.5 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K \u001b[91m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[91mβ•Έ\u001b[0m\u001b[90m━━\u001b[0m \u001b[32m931.8/981.5 kB\u001b[0m \u001b[31m7.0 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m981.5/981.5 kB\u001b[0m \u001b[31m6.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.1/2.1 MB\u001b[0m \u001b[31m31.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m472.8/472.8 kB\u001b[0m \u001b[31m33.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.5/1.5 MB\u001b[0m \u001b[31m60.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m27.0/27.0 MB\u001b[0m \u001b[31m52.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.5/3.5 MB\u001b[0m \u001b[31m95.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m15.9/15.9 MB\u001b[0m \u001b[31m51.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m159.9/159.9 kB\u001b[0m \u001b[31m15.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m553.2/553.2 kB\u001b[0m \u001b[31m36.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m274.7/274.7 kB\u001b[0m \u001b[31m20.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.1/3.1 MB\u001b[0m \u001b[31m89.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m45.3/45.3 kB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m82.7/82.7 kB\u001b[0m \u001b[31m8.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m294.5/294.5 kB\u001b[0m \u001b[31m23.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25h Building wheel for langdetect (setup.py) ... \u001b[?25l\u001b[?25hdone\n" ] } ], "source": [ "!pip install -qU faiss-cpu unstructured==0.15.7 python-pptx==1.0.2 nltk==3.9.1 pymupdf" ] }, { "cell_type": "markdown", "metadata": { "id": "0FM-eUlrcI8a" }, "source": [ "### Provide OpenAI API Key" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "wA_mlurVqtrp", "outputId": "b1953e14-c4ac-43b8-fcf2-7dfa3103a7a3" }, "outputs": [], "source": [ "import os\n", "import getpass\n", "\n", "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"Enter Your OpenAI API Key: \")\n", "#os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"Enter Your LangChain API Key: \")\n", "#os.environ[\"QDRANT_API_KEY\"] = getpass.getpass(\"Enter Your Qdrant API Key: \")\n", "\n", "os.environ[\"LANGCHAIN_TRACING_V2\"] = 'false'\n", "os.environ[\"QDRANT_URL\"] = 'https://6db11fca-6840-43a7-9aa0-96fa9b3c0320.europe-west3-0.gcp.cloud.qdrant.io'" ] }, { "cell_type": "markdown", "metadata": { "id": "TFZ217gCDVTr" }, "source": [ "## Task 2: Loading Data\n", "\n", "We'll be using a recent document released by the EU 'laying down harmonised rules on artificial intelligence and amending Regulations'.\n", "\n", "The data can be found [here](https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=CELEX%3A32024R1689), though we will be using a HTML version which was collected into the AIM DataRepository." ] }, { "cell_type": "markdown", "metadata": { "id": "3g0mawyG0T4c" }, "source": [ "First, we'll clone and then `cd` into the DataRepository." ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "K9z9tZVAedkk", "outputId": "914eb4d7-053a-4ac0-ab13-d75b97d3d7dd" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Cloning into 'policy-rag'...\n", "remote: Enumerating objects: 46, done.\u001b[K\n", "remote: Counting objects: 100% (46/46), done.\u001b[K\n", "remote: Compressing objects: 100% (34/34), done.\u001b[K\n", "remote: Total 46 (delta 10), reused 43 (delta 9), pack-reused 0 (from 0)\u001b[K\n", "Receiving objects: 100% (46/46), 12.22 MiB | 36.06 MiB/s, done.\n", "Resolving deltas: 100% (10/10), done.\n" ] } ], "source": [ "!git clone https://github.com/ledgerW/policy-rag.git" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "sz9gfy4FO81w", "outputId": "6dc775e9-231c-47ad-dec0-5d09a1319f47" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "/content/policy-rag\n" ] } ], "source": [ "%cd policy-rag" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "OOyMrgSuPAWQ", "outputId": "eeee8f0b-754c-4c50-caff-7f344ec90fb0" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "README.md environment.yml golden_dataset.yml sdg.py\n", "chunk_experiment.py \u001b[34mexperiments\u001b[m\u001b[m \u001b[34mpolicy_rag\u001b[m\u001b[m \u001b[34mtests\u001b[m\u001b[m\n", "\u001b[34mdata\u001b[m\u001b[m fine_tuning.ipynb scratch.ipynb\n" ] } ], "source": [ "!ls" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "id": "ZKN8PYNLNyQ9" }, "outputs": [], "source": [ "data_dir = 'data'" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "id": "jZLgb5xqNyQ9" }, "outputs": [], "source": [ "from policy_rag.text_utils import DocLoader" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "0cVu0jUuNyQ-", "outputId": "a5b81496-03c2-47b1-9915-960225386693" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "137\n" ] } ], "source": [ "loader = DocLoader()\n", "docs = loader.load_dir(data_dir)\n", "print(len(docs))" ] }, { "cell_type": "markdown", "metadata": { "id": "-UbKa6-V0nvp" }, "source": [ "Next, we'll set up a classic naive chunking strategy as we only care that the documents get parsed into chunks that we can generate synthetic questions about." ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "id": "NsPrOOqXOsNX" }, "outputs": [], "source": [ "from policy_rag.text_utils import get_recursive_token_chunks, get_semantic_chunks" ] }, { "cell_type": "markdown", "metadata": { "id": "lf_PoX7l09Rg" }, "source": [ "Next we can load/split these documents as follows." ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "id": "OMYPX6N6Os8M" }, "outputs": [], "source": [ "training_documents = get_recursive_token_chunks(\n", " docs=docs,\n", " model_name='gpt-4',\n", " chunk_size=100,\n", " chunk_overlap=25\n", ")" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "PAozuMoNOvnp", "outputId": "b10674d0-ea30-4ecf-b22e-b92cdac01ef0" }, "outputs": [ { "data": { "text/plain": [ "1222" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "len(training_documents)" ] }, { "cell_type": "markdown", "metadata": { "id": "0yE2TFIq1BuJ" }, "source": [ "Next, we're going to associate each of our chunks with a unique identifier." ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "id": "AwyIForybIpo" }, "outputs": [], "source": [ "import uuid\n", "\n", "id_set = set()\n", "\n", "for document in training_documents:\n", " id = str(uuid.uuid4())\n", " while id in id_set:\n", " id = uuid.uuid4()\n", " id_set.add(id)\n", " document.metadata[\"id\"] = id" ] }, { "cell_type": "markdown", "metadata": { "id": "PJnL4oNg341U" }, "source": [ "Next, we'll simply use naive Python slicing to create a training, test, and validation set to prepare our data for the next step." ] }, { "cell_type": "code", "execution_count": 71, "metadata": { "id": "MTS4GTSEcnG4" }, "outputs": [], "source": [ "training_split_documents = training_documents[:700]\n", "val_split_documents = training_documents[700:775]\n", "test_split_documents = training_documents[775:850]" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "9h20eexuC9Ad", "outputId": "e9fa8840-bb9d-444d-c59f-b4bd4adad603" }, "outputs": [ { "data": { "text/plain": [ "Document(metadata={'source': 'data/Blueprint-for-an-AI-Bill-of-Rights.pdf', 'file_path': 'data/Blueprint-for-an-AI-Bill-of-Rights.pdf', 'page': 0, 'total_pages': 73, 'format': 'PDF 1.6', 'title': 'Blueprint for an AI Bill of Rights', 'author': '', 'subject': '', 'keywords': '', 'creator': 'Adobe Illustrator 26.3 (Macintosh)', 'producer': 'iLovePDF', 'creationDate': \"D:20220920133035-04'00'\", 'modDate': \"D:20221003104118-04'00'\", 'trapped': '', 'id': 'ecbd3a8c-01c7-47ce-89f6-f426d9d15848'}, page_content='BLUEPRINT FOR AN \\nAI BILL OF \\nRIGHTS \\nMAKING AUTOMATED \\nSYSTEMS WORK FOR \\nTHE AMERICAN PEOPLE \\nOCTOBER 2022')" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "training_split_documents[0]" ] }, { "cell_type": "markdown", "metadata": { "id": "tzlvKbONDWvQ" }, "source": [ "## Task 3: Constructing a Fine-tuning Dataset\n", "\n", "Using the nodes we created above, we can finally start constructing a fine-tuning dataset utilizing OpenAI's `gpt-4o-mini` (released [July 18th](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/)).\n", "\n", "The basic idea here is straightforward enough:\n", "\n", "1. We look at a document\n", "2. We generate questions that could be answered by that node\n", "\n", "This gives us a number of question/context pairs that we can use to fine-tune our Embeddings model." ] }, { "cell_type": "code", "execution_count": 40, "metadata": { "id": "_EWfmIscMrvg" }, "outputs": [], "source": [ "from langchain_openai import ChatOpenAI\n", "\n", "qa_chat_model = ChatOpenAI(\n", " model=\"gpt-4o-mini\",\n", " temperature=0\n", ")" ] }, { "cell_type": "markdown", "metadata": { "id": "8-hLnsSB6Y-S" }, "source": [ "We'll create a simple Question Generation prompt to query `gpt-4o-mini` to generate Questions for each retrieved context." ] }, { "cell_type": "code", "execution_count": 39, "metadata": { "id": "diEWcw00NMSj" }, "outputs": [], "source": [ "from langchain_core.prompts import ChatPromptTemplate\n", "\n", "qa_prompt = \"\"\"\\\n", "Given the following context, you must generate 1 question based only on the provided context.\n", "\n", "Context:\n", "{context}\n", "\n", "Question:\n", "\"\"\"\n", "\n", "qa_prompt_template = ChatPromptTemplate.from_template(qa_prompt)" ] }, { "cell_type": "markdown", "metadata": { "id": "u87Izpgm6_fk" }, "source": [ "We'll create a simple chain to query the LLM!" ] }, { "cell_type": "code", "execution_count": 41, "metadata": { "id": "ggl9SSjiNbpG" }, "outputs": [], "source": [ "question_generation_chain = qa_prompt_template | qa_chat_model" ] }, { "cell_type": "code", "execution_count": 42, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "VgbH2Vw9C9Af", "outputId": "539f9663-a8a9-4c83-bc21-954877880cbe" }, "outputs": [ { "data": { "text/plain": [ "AIMessage(content='What are some examples of accessible formats that can be provided for individuals with disabilities?', additional_kwargs={'refusal': None}, response_metadata={'token_usage': {'completion_tokens': 16, 'prompt_tokens': 41, 'total_tokens': 57, 'completion_tokens_details': {'reasoning_tokens': 0}, 'prompt_tokens_details': {'cached_tokens': 0}}, 'model_name': 'gpt-4o-mini-2024-07-18', 'system_fingerprint': 'fp_f85bea6784', 'finish_reason': 'stop', 'logprobs': None}, id='run-226cc984-fef8-45e7-b314-71a7ac9a3872-0', usage_metadata={'input_tokens': 41, 'output_tokens': 16, 'total_tokens': 57})" ] }, "execution_count": 42, "metadata": {}, "output_type": "execute_result" } ], "source": [ "question_generation_chain.invoke({'context': 'What types of accessible formats are available for persons with disabilities?'})" ] }, { "cell_type": "markdown", "metadata": { "id": "4duvHirh7DQv" }, "source": [ "There's a lot going on in this function - let's take a deeper look:\n", "\n", "1. First, we provide a list of documents and a number of questions\n", "2. We, for each document in our list, generate `n_questions` of questions.\n", "3. We then associate those questions and contexts via a `UUID`.\n", "\n", "> NOTE: The reason we're doing this `UUID` association is for ease of use later in the notebook." ] }, { "cell_type": "markdown", "metadata": { "id": "1Lm2JvgC9X37" }, "source": [ "##### πŸ—οΈ Activity #1:\n", "\n", "We have:\n", "\n", "- Lists of `Documents` with the `metadata` field `id`.\n", "\n", "We need:\n", "\n", "- An object with key `id`, which have values `str` questions.\n", "- An object with key `question_id`, which have values `List(str)` which will be a list of associated `context_id`.\n", "\n", "An Example:\n", "\n", "question_object:\n", "```python\n", "{\n", "'b4b95fb6-f827-4454-aa5b-20e62733f172': 'What types of accessible formats are available for persons with disabilities?',\n", "'df58ee4f-714c-419e-8324-94e5870574e2': 'How do accessible formats benefit persons with disabilities?',\n", "'505fce8b-0e56-48de-a251-61027e396918': 'What are some of the risks associated with the increasing capabilities of AI systems that generate synthetic content?',\n", "'8ff0ab33-60dc-4fee-8958-91bfb686aca8': 'Why is it important for providers of AI systems to embed technical solutions for marking and detecting synthetic content?'\n", "}\n", " ```\n", "\n", " context_object:\n", " ```python\n", "{\n", "'b4b95fb6-f827-4454-aa5b-20e62733f172': ['dd75bf94-75f3-4603-8e4b-5522f6925638'],\n", "'df58ee4f-714c-419e-8324-94e5870574e2': ['dd75bf94-75f3-4603-8e4b-5522f6925638'],\n", "'505fce8b-0e56-48de-a251-61027e396918': ['ffe3893f-688c-48e8-90bd-7a9feb953d90'],\n", "'8ff0ab33-60dc-4fee-8958-91bfb686aca8': ['ffe3893f-688c-48e8-90bd-7a9feb953d90'],\n", "}\n", " ```\n", "\n", " As you can see, a piece of context can be associated with more than 1 question.\n", "\n", " The task is to write the Python function(s) to accomplish this task.\n", "\n", " Your function signature is provided below, along with the desired return values.\n", "\n", " > NOTE: You can make any modifications that you desire - assuming that you have the correct input and outputs." ] }, { "cell_type": "code", "execution_count": 22, "metadata": { "id": "-e9LrbQ3C9Af" }, "outputs": [], "source": [ "question_data = {\n", "'b4b95fb6-f827-4454-aa5b-20e62733f172': 'What types of accessible formats are available for persons with disabilities?',\n", "'df58ee4f-714c-419e-8324-94e5870574e2': 'How do accessible formats benefit persons with disabilities?',\n", "'505fce8b-0e56-48de-a251-61027e396918': 'What are some of the risks associated with the increasing capabilities of AI systems that generate synthetic content?',\n", "'8ff0ab33-60dc-4fee-8958-91bfb686aca8': 'Why is it important for providers of AI systems to embed technical solutions for marking and detecting synthetic content?'\n", "}\n", "\n", "context_data = {\n", "'b4b95fb6-f827-4454-aa5b-20e62733f172': ['dd75bf94-75f3-4603-8e4b-5522f6925638'],\n", "'df58ee4f-714c-419e-8324-94e5870574e2': ['dd75bf94-75f3-4603-8e4b-5522f6925638'],\n", "'505fce8b-0e56-48de-a251-61027e396918': ['ffe3893f-688c-48e8-90bd-7a9feb953d90'],\n", "'8ff0ab33-60dc-4fee-8958-91bfb686aca8': ['ffe3893f-688c-48e8-90bd-7a9feb953d90'],\n", "}" ] }, { "cell_type": "code", "execution_count": 17, "metadata": { "id": "a5Z59xQWC9Ag" }, "outputs": [], "source": [ "from pydantic import BaseModel, RootModel, field_validator\n", "from typing import List, Dict\n", "from uuid import UUID\n", "\n", "class QuestionObject(RootModel[Dict[str, str]]):\n", " model_config = {'validate_assignment': True}\n", "\n", " @field_validator('root')\n", " def validate_key_is_uuid(cls, value):\n", " for key in value.keys():\n", " try:\n", " u = UUID(key)\n", " if u.version != 4:\n", " raise ValueError(f\"{key} is not UUID v4\")\n", " except ValueError as e:\n", " raise ValueError(f\"{key} is not UUID v4\")\n", " return value\n", "\n", "\n", "class ContextObject(RootModel[Dict[str, List[str]]]):\n", " model_config = {'validate_assignment': True}\n", "\n", " @field_validator('root')\n", " def validate_key_is_uuid(cls, value):\n", " for key in value.keys():\n", " try:\n", " u = UUID(key)\n", " if u.version != 4:\n", " raise ValueError(f\"{key} is not UUID v4\")\n", " except ValueError as e:\n", " raise ValueError(f\"{key} is not UUID v4\")\n", " return value\n", "\n", " @field_validator('root')\n", " def validate_values_are_uuid(cls, value):\n", " for key, val in value.items():\n", " for v in val:\n", " try:\n", " u = UUID(v)\n", " if u.version != 4:\n", " raise ValueError(f\"{key} is not UUID v4\")\n", " except:\n", " raise ValueError(f\"{key} is not UUID v4\")\n", " return value" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Prep Data" ] }, { "cell_type": "code", "execution_count": 57, "metadata": {}, "outputs": [], "source": [ "def create_question_context_pairs(\n", " documents: List[Document]\n", " ) -> Tuple[List[str], List[str]]:\n", " questions: List[str] = []\n", " contexts: List[str] = []\n", "\n", " for doc in documents:\n", " question = question_generation_chain.invoke({'context': doc.page_content})\n", " questions.append(question.content)\n", " contexts.append(doc.page_content)\n", "\n", " return questions, contexts" ] }, { "cell_type": "markdown", "metadata": { "id": "_FSTG0bb7w73" }, "source": [ "We'll use the function to generate training, validation, and test data with `n_questions=2` for each." ] }, { "cell_type": "code", "execution_count": 72, "metadata": { "id": "85Dq6KRqEs0F" }, "outputs": [], "source": [ "questions, contexts = create_question_context_pairs(training_split_documents)\n", "val_questions, val_contexts = create_question_context_pairs(val_split_documents)\n", "test_questions, test_contexts = create_question_context_pairs(test_split_documents)" ] }, { "cell_type": "code", "execution_count": 73, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "\n", "pd.DataFrame({'id': range(0, len(questions)), 'anchor': questions, 'positive': contexts}).to_json('training.jsonl', orient='records')\n", "\n", "train_val_len = len(questions)+len(val_questions)\n", "pd.DataFrame({'id': range(len(questions), train_val_len), 'anchor': val_questions, 'positive': val_contexts}).to_json('validation.jsonl', orient='records')\n", "\n", "train_val_test_len = train_val_len + len(test_questions)\n", "pd.DataFrame({'id': range(train_val_len, train_val_test_len), 'anchor': test_questions, 'positive': test_contexts}).to_json('test.jsonl', orient='records')" ] }, { "cell_type": "code", "execution_count": 64, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Generating train split: 500 examples [00:00, 30169.64 examples/s]\n", "Generating train split: 75 examples [00:00, 14845.34 examples/s]\n", "Generating train split: 75 examples [00:00, 13127.99 examples/s]\n" ] } ], "source": [ "from sentence_transformers import SentenceTransformer\n", "from sentence_transformers.evaluation import (\n", " InformationRetrievalEvaluator,\n", " SequentialEvaluator,\n", ")\n", "from sentence_transformers.util import cos_sim\n", "from datasets import load_dataset, concatenate_datasets\n", "\n", "\n", "#train_dataset = load_dataset(\"json\", data_files=\"training.jsonl\", split=\"train\")\n", "val_dataset = load_dataset(\"json\", data_files=\"validation.jsonl\", split=\"train\")\n", " \n", "# Convert the datasets to dictionaries\n", "corpus = dict(\n", " zip(corpus_dataset[\"id\"], corpus_dataset[\"positive\"])\n", ") # Our corpus (cid => document)\n", "queries = dict(\n", " zip(val_dataset[\"id\"], val_dataset[\"anchor\"])\n", ") # Our queries (qid => question)\n", " \n", "# Create a mapping of relevant document (1 in our case) for each query\n", "relevant_docs = {} # Query ID to relevant documents (qid => set([relevant_cids])\n", "for q_id in queries:\n", " relevant_docs[q_id] = [q_id]\n", " \n", " \n", "evaluator = InformationRetrievalEvaluator(\n", " queries=queries,\n", " corpus=corpus,\n", " relevant_docs=relevant_docs\n", ")" ] }, { "cell_type": "markdown", "metadata": { "id": "K_jYOnAI43zK" }, "source": [ "### Reformating and Saving Datasets\n", "\n", "Now, we can save our datasets for later use!\n", "\n", "> NOTE: If you ran into issues creating the data - you can use the data from the DataRespository. It's simply called: `train_dataset.jsonl`, etc." ] }, { "cell_type": "markdown", "metadata": { "id": "vAwklqQCgVi-" }, "source": [ "## Task 4: Fine-tuning `gte-large-en-v1.5`\n", "\n", "Now that we have a dataset, let's grab a `sentence-transformers` Embeddings model!\n", "\n", "We'll be using Snowflake's [`snowflake-arctic-embed-m`](https://huggingface.co./Snowflake/snowflake-arctic-embed-m) as a base embeddings model.\n", "\n", "It is a well performing embeddings model by itself, but there's a lot of very specific domain terms and vocabulary in our courpus - so lets fine-tune it and see what that can do for us!" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "id": "AXzVHP3v1Cno" }, "outputs": [], "source": [ "!pip install -qU sentence_transformers datasets pyarrow optimum[exporters]" ] }, { "cell_type": "code", "execution_count": 38, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 664, "referenced_widgets": [ "941cb11c2b954930b10b1428e8e0cf40", "e1f63d4e2df04970b188702a562d71bf", "69b02e117be749c2b9f0a5f4c13522f2", "d6ea1f88af9240db884e42c7616cde14", "71a669f899c541d0a6cf18f4e139de34", "fad62cb1a0ff4760b17a5247de518e3d", "d8d57da8d0654b958b466195306ae28a", "c15620b939914d9e8e3034a40e73d357", "f4f1696bef9b40a0a05d55c56fb23eff", "be5e375ca07844c6b734d998d0794702", "7f4e537ea54248158014536ac62468fb", "260bd64f8e0947858046bc0950a185af", "e9a0fb52fe9c45f4a58c940bf1f3dfb3", "c79aeb6cfafd42f88f43d630e300a016", "885fbec012514fb189f61c4777180dcf", "e0e656f937bc4b1d85d0f0fc6b906725", "cc23412bc12b49af9f06030961039646", "f2113ec0bf764ac7af3a9fd9d4ab9e54", "eb690c7a5d294e359acf44113dcdedc9", "e59d85704f264a249d3172609cc3ea93", "9fc8aea93c474b8db505e8fe35f86e4d", "bf307298c0b54e76bd27ee55c2c8e33e", "ba48250c8d1a4b869b3984e89e609a65", "601a68c9f95f4e7294ebe191b1d3bcc9", "b24fefe04ec449c3bf3e059fc31d3655", "a71c56f4215c4b0e9affc34dca348b54", "71a3e7d00bf2468a918d8790e3eedef0", "904196c265f34f82bbd25826e95d6518", "b2a1e2b745ce4f82aa86d1913c44a987", "95e4c9dc822f4641822d259ecd5b2684", "17bc37a2d8824104baf8b1fcd3c85e30", "f278940553124e56ad857ddb00d00141", "1dcf6074f5f14229b2f118fdb05f35a7", "3cb8803558334bca804dd7c0c05b677c", "9dbf3c514d434d4aa631ac0644a395b4", "65bb1340dd1d43d98cffae5ee0172d48", "39419bb1e79541668d4d86dcd74e6269", "5ddf4b48bbfd4eb8af1c695e0e4e8f65", "100700603e854bbe937b39b4fc693a87", "684b55e94d934156b9a99d4108fa3849", "4df120a3fc6d4be881bab6e28dbb4547", "d08cb75923e34eb88f917b8e43caee0a", "d22ea87f82654ce282d68ff2330498c7", "ff5dee654f9c41ef9d5635e1b0663d1d", "661684f9eb8c4860a21221e9afba881e", "26579f3154e04f0fa160b0d36b86eaeb", "830c9aea80514ec9977f7bb606e58214", "2cf2ca752e564482ade99507b8bcf29c", "41a35948e9454835925bf0e2586b526e", "7a32eaea10544afba8d7e9c47b02eb25", "63ffc3294c214b1d814ae0d6fe34b4fc", "e5e014a04d0c4778a586064cdd09526a", "728babf8f44742c8bb1b007b073d80f7", "b9c1ba7a50b34789bd1fbb3693cd42f0", "487a0a31e6ac4737b108106bf78b73e5", "5c789a4dfdaa4ee5b6ff6210b1e4113e", "79a2bb833709472c9ff79deeb913b242", "a4842dc8f7304d21b1a1723aa3ae3205", "b1481983d01640f892a08dc3f579a5fb", "c6a290fae64e452fbe27a519b6956689", "be5ac4aa543347558de0ea730909eda7", "9391ed4727d5470a8636b010089b4c23", "5f37bf8a87dd449b9ba203cfec1f1911", "dc19251b2af74e5ca87b47b7e37d5b3a", "a512356c0de140f8a24d46c7b69ad195", "1243d94a1c704d54be128aa1d22acebf", "416d61b5a3cd45dcb2bf77f5a1336eb1", "b6f53899d1004c03971e13cf236d83a6", "e4f37d7070b949daa4937bc1c001450f", "0799a78c0cd54522b14f4994bb62074a", "e25a28e09e134048a29cc22a4ae000f1", "3a85a2eeb44840a5a3abcf1c1363eadc", "72913a91036e4e3281b37c7445f3598d", "1322f0a12b034f648afdfa287ddff45b", "b4385f11ff514010b85ebf46e36f0658", "6b36c6d1ac1d43528a02e71ccb1faabc", "8409651d319b408f95d59f01812c6a4e", "4d1b875c0c4a4c22b40345183f5eda80", "fe2a723aed954391919647ea7ee6960e", "ed8b7c70eee348688191dd011c03b70a", "e2e26c47dfd74119ae1f151ef314cf43", "b12fd85e3fbf4270972fee2ce3cbf84d", "e7668e7cf5a2441fa48bcb81f6e8feb6", "4e1199157bba49f7a5c10189d8a88b75", "46d53760dc9043c7b591156c552cac80", "3ae2098a41f2420f9ce6152536db2fc9", "84b25a8cbe7846119f679c0ffa0e67c0", "003008aa233e465f8186acb391e54edf", "e9243eceb4344a3595be76f0605c2c15", "cf9f0b0058f4432bafe3a74e5205658f", "a1fab3040d814d7e88368dd9aa6a07c7", "563c82052ab44f6cba2a607f35b8e116", "4f4236c3772b4ffd9e867db8a5f3f9e3", "d3abfb110a434c9cac3a54ea17f932ab", "bfb6a086089a482db26fc8364712dbcf", "bf5646c479c1426698378f2ed5fb81b4", "423380483ff7450eb844fcd930bd060a", "1e39343a616c41ff8d123a39d832d99e", "87f1c7d9a56d43e59f227c6d51a50d7a", "c44c462147e0495f83fb43cb21f8ec30", "ca449ed7f3364b25a8f76a6e1e6cbdbf", "996e1dbb6de84fe0a837eb02e5dabbfe", "f4cbfa45eff24264b712f5a6b0b48ec4", "b90b699209484938968ef673f153b8cb", "cfa45c6a7d544deda41944d787e87d3a", "706082a2c72a4cd68b9e893ec61de34c", "76831eb40b72418ab1c41b47846a3c47", "64ea657034be4d918ea331a7f97ac983", "49d3cafbcf8d4adf9f1582f5febfd8ca", "3140fcad984d4bf88ba95d2e88fab13e", "995803924a5a49c2bde5f586777911f3", "8c5a14700b7545339a177204eeedcc3b", "59f81e00efad4857a37e61b22c22d851", "7a576273d59747efbcd96fe90d112374", "461cc391ec6d4e52b27a61343aca6872", "69116ab4892047c2b2cd71310707c61e", "bbf2f6fd042346a389b4ccb978c064f9", "db3463ec0fe44b0aa3a33028f74a667f", "457b2a6bfdf941f9b96df25138f073df", "584c596ee11f45d7bfad02dbbc8e52e1", "7e4351d85d684185a8ac704a3043b9a2", "e5ef0d550e2c4f829caf3c47a72a1bf2", "b25bf487739a4deeaf700a3f1b4cb9da", "d94c120ebdf54241adc4dfdda9f716f2", "f489742ec1104e0f8638a1de8f8f9ef6", "ee1ea5e939d740c38fe9daebb83fd2c2", "612dd8f9ef0047d8b97b1ad2480a59b2", "48df4a674b7248ca830508fe50860f3f", "d578c47644c447ab922c3cb4b3404c43", "a988e2eba727484f94f3441b1310364c", "a5368801499e473cb117329c3dfa955b", "164aede9d80a45b3aa90ce83995af89d" ] }, "id": "G-PGsQB7Xo6V", "outputId": "9aa74716-e1fa-4a90-d0da-bef5cdf9932c" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/usr/local/lib/python3.10/dist-packages/sentence_transformers/cross_encoder/CrossEncoder.py:13: TqdmExperimentalWarning: Using `tqdm.autonotebook.tqdm` in notebook mode. Use `tqdm.tqdm` instead to force console mode (e.g. in jupyter console)\n", " from tqdm.autonotebook import tqdm, trange\n", "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:90: UserWarning: \n", "The secret `HF_TOKEN` does not exist in your Colab secrets.\n", "To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co./settings/tokens), set it as secret in your Google Colab and restart your session.\n", "You will be able to reuse this secret in all of your notebooks.\n", "Please note that authentication is recommended but still optional to access public models or datasets.\n", " warnings.warn(\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "941cb11c2b954930b10b1428e8e0cf40", "version_major": 2, "version_minor": 0 }, "text/plain": [ "modules.json: 0%| | 0.00/229 [00:00 NOTE: PyTorch (`torch`) is a popular machine learning library - while we don't go very deep into PyTorch it's an incredibly powerful and interesting library! Please read more about it [here](https://pytorch.org/tutorials/beginner/basics/intro.html)!" ] }, { "cell_type": "code", "execution_count": 39, "metadata": { "id": "B-WbpuUWYFJr" }, "outputs": [], "source": [ "from torch.utils.data import DataLoader\n", "from torch.utils.data import Dataset\n", "from sentence_transformers import InputExample" ] }, { "cell_type": "markdown", "metadata": { "id": "AJtPPlck8HBE" }, "source": [ "We're using a toy batch size here to reflect the limited number of examples we have.\n", "\n", "> NOTE: It is typical to use a much larger batch size (~64+), hardware permitting." ] }, { "cell_type": "code", "execution_count": 40, "metadata": { "id": "8Lokhy6KYHAv" }, "outputs": [], "source": [ "BATCH_SIZE = 20" ] }, { "cell_type": "markdown", "metadata": { "id": "b-6DT8hc8PmT" }, "source": [ "Let's move our dataset into the expected format for training." ] }, { "cell_type": "code", "execution_count": 43, "metadata": { "id": "tiizmeIqZ_-w" }, "outputs": [], "source": [ "from sentence_transformers import SentenceTransformer\n", "from sentence_transformers.evaluation import (\n", " InformationRetrievalEvaluator,\n", " SequentialEvaluator,\n", ")\n", "from sentence_transformers.util import cos_sim\n", "from datasets import load_dataset, concatenate_datasets\n", "\n", "\n", "train_dataset = load_dataset(\"json\", data_files=\"training.jsonl\", split=\"train\")\n", "val_dataset = load_dataset(\"json\", data_files=\"validation.jsonl\", split=\"train\")\n", "test_dataset = load_dataset(\"json\", data_files=\"test.jsonl\", split=\"train\")\n", "corpus_dataset = concatenate_datasets([train_dataset, val_dataset, test_dataset])\n", " \n", "# Convert the datasets to dictionaries\n", "corpus = dict(\n", " zip(corpus_dataset[\"id\"], corpus_dataset[\"positive\"])\n", ") # Our corpus (cid => document)\n", "queries = dict(\n", " zip(val_dataset[\"id\"], val_dataset[\"anchor\"])\n", ") # Our queries (qid => question)\n", " \n", "# Create a mapping of relevant document (1 in our case) for each query\n", "relevant_docs = {} # Query ID to relevant documents (qid => set([relevant_cids])\n", "for q_id in queries:\n", " relevant_docs[q_id] = [q_id]\n", " \n", " \n", "evaluator = InformationRetrievalEvaluator(\n", " queries=queries,\n", " corpus=corpus,\n", " relevant_docs=relevant_docs\n", ")" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "from datasets import load_dataset\n", "\n", "train_dataset = load_dataset(\"json\", data_files=\"training.jsonl\", split=\"train\")" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'id': 50,\n", " 'anchor': 'What steps should be taken to ensure that individuals impacted by a system are notified of significant use case or key functionality changes?',\n", " 'positive': 'system functioning and the role automation plays, notice that such systems are in use, the individual or organiza\\xad\\ntion responsible for the system, and explanations of outcomes that are clear, timely, and accessible. Such notice \\nshould be kept up-to-date and people impacted by the system should be notified of significant use case or key \\nfunctionality changes. You should know how and why an outcome impacting you was determined by an'}" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "train_dataset[50]" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "{'queries': 'Discuss the implications of biased automated sentiment analyzers as highlighted in the context. How can such biases affect online discourse and the representation of marginalized groups?',\n", " 'corpus': None,\n", " 'relevant_docs': ['5c3c3c94-f47d-4e85-bc8a-61f5d9e9014b'],\n", " 'mode': 'text'}" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "train_dataset[50]" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": { "id": "_vA8rzlX8XbT" }, "source": [ "Next up, we'll prepare our loss function!\n", "\n", "Loss is an important part of training, fine-tuning, and more. If you want a deep dive on loss - you can check out our [event on loss!](https://www.youtube.com/watch?v=iB8FWR9aD5Q&t=8s).\n", "\n", "The core loss we're using today is called `MultipleNegativesRankingLoss` - you can find more information [here](https://github.com/UKPLab/sentence-transformers/blob/master/sentence_transformers/losses/MultipleNegativesRankingLoss.py).\n", "\n", "This is \"wrapped\" in `MatryoshkaLoss`, which you can read the implementation of [here](https://github.com/UKPLab/sentence-transformers/blob/master/sentence_transformers/losses/MatryoshkaLoss.py)." ] }, { "cell_type": "code", "execution_count": 44, "metadata": { "id": "Uga4nnBqlVeh" }, "outputs": [], "source": [ "from sentence_transformers.losses import MatryoshkaLoss, MultipleNegativesRankingLoss\n", "\n", "matryoshka_dimensions = [1024, 512, 256, 128, 64]\n", "inner_train_loss = MultipleNegativesRankingLoss(model)\n", "train_loss = MatryoshkaLoss(\n", " model, inner_train_loss, matryoshka_dims=matryoshka_dimensions\n", ")" ] }, { "cell_type": "markdown", "metadata": { "id": "aJG4fOm66PHI" }, "source": [ "##### πŸ—οΈ Activity #2:\n", "\n", "Both of these losses sound \"cool\", but what are they - exactly - under the hood?\n", "\n", "Why are these losses specifically doing? Please write a short summary of each loss. \n", "\n", "LW:\n", "**Multiple Negatives Ranking Loss** is a more efficient variation of the standard Triplet Loss commonly used in contrastive learning models. A training batch contains an Anchor-Positive pair along with multiple Anchor-Negative pairs, computes the loss (or similarity really) of each embedding pair with a cosine similarity, and then uses a variation of a Softmax over the similarities of all the pairs such that the Anchor-Positive pair similarity is maximized, while the Anchor-Negative pairs are minimized.\n", "\n", "**Matryoshka Loss** works by aggregating losses across multiple output embedding sizes, such that the larger embeddings represent finer and finer detail.\n", "\n", "> NOTE: This is a course focused on AI Engineering and the application of AI - looking for a hint? Try pasting the code (linked above) into ChatGPT/Claude to write the summary!" ] }, { "cell_type": "markdown", "metadata": { "id": "QKxRuXfH844c" }, "source": [ "Now we can set-up our evaluator.\n", "\n", "> NOTE: Due to the formatting of our dataset - this is all we have to do!" ] }, { "cell_type": "markdown", "metadata": { "id": "MYfap_ct8-bU" }, "source": [ "We'll train this model for 5 epochs, though you could increase this number if we had a significant amount more data." ] }, { "cell_type": "code", "execution_count": 46, "metadata": { "id": "svZG0pBHiQr6" }, "outputs": [], "source": [ "EPOCHS = 5" ] }, { "cell_type": "markdown", "metadata": { "id": "wxitWoNX9DwW" }, "source": [ "It's training time!\n", "\n", "> NOTE: We're manually defining a warm-up period here - this is just to provide a smooth ramp into our training!" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from sentence_transformers import SentenceTransformerTrainingArguments\n", "from sentence_transformers.training_args import BatchSamplers\n", " \n", "finetuned_model_name = 'policy_gte_large_6'\n", "\n", "# load train dataset again\n", "train_dataset = load_dataset(\"json\", data_files=\"training.jsonl\", split=\"train\")\n", " \n", "# define training arguments\n", "args = SentenceTransformerTrainingArguments(\n", " output_dir=finetuned_model_name, # output directory and hugging face model ID\n", " num_train_epochs=EPOCHS, # number of epochs\n", " per_device_train_batch_size=32, # train batch size\n", " gradient_accumulation_steps=16, # for a global batch size of 512\n", " per_device_eval_batch_size=16, # evaluation batch size\n", " warmup_ratio=0.1, # warmup ratio\n", " learning_rate=2e-5, # learning rate, 2e-5 is a good value\n", " lr_scheduler_type=\"cosine\", # use constant learning rate scheduler\n", " optim=\"adamw_torch_fused\", # use fused adamw optimizer\n", " tf32=True, # use tf32 precision\n", " bf16=True, # use bf16 precision\n", " batch_sampler=BatchSamplers.NO_DUPLICATES, # MultipleNegativesRankingLoss benefits from no duplicate samples in a batch\n", " eval_strategy=\"epoch\", # evaluate after each epoch\n", " save_strategy=\"epoch\", # save after each epoch\n", " logging_steps=10, # log every 10 steps\n", " save_total_limit=3, # save only the last 3 models\n", " load_best_model_at_end=True, # load the best model when training ends\n", ")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "from sentence_transformers import SentenceTransformerTrainer\n", " \n", "trainer = SentenceTransformerTrainer(\n", " model=model,\n", " args=args,\n", " train_dataset=train_dataset.select_columns([\"positive\", \"anchor\"]),\n", " loss=train_loss,\n", " evaluator=evaluator,\n", ")" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "trainer.train()\n", "trainer.save_model()" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 145, "referenced_widgets": [ "aff3a571f355474690e7b5b8094a827f", "cca5686952a8422e828fe06a5b26fe31", "3f412df4ae384216bc2ff05b45976695", "230a83c8d6f740498fd24928b83eef25", "de32a0436b0a48379652638ee573be35", "5ab69cb33f6e4993a18f2f4819f3cd4a", "06181760a7bb47d0af60fb4080fd2586", "90790a4bd48242bdb659803f02604774", "6b53e0c6f1cb449c8ee93cf12e5f192b", "4be1ca35c785486fb8c11c3439412a9c", "ea161e1670be478f8a3adc44b819ad48", "5a480538a2434170b49536ad596bf4f4", "7a42be9991564d7b89aa090600eb0f06", "6b8362dd21ad4db9a3398d826d292b39", "99912b9fe62e4b35b63abd219380a26d", "28a422c882a345359315f73606cce5cc", "6d60c7b6d6d24aaba618ad031b2eb1cd", "bdcfe5ad999142408db010ddb62e8fde", "ca0586788cd24803acb7052d70f9f091", "bdfaef138a7340a1b45e5b257fdfea4d", "c2e9e7085b2f42a7b8fa3b4fc2ec0b10", "207c134337c844d19862b7056bd5de73", "5d122374044e4f87a8a98b79205db43e", "dcda6daa8c2e49fb9703e9e883c4f995", "62833db6c2f6488e9838b794e829f0db", "03f3a4d9071f446c9c900f545c43bca7", "550d13efadd3447ba09bf08e8fddfee5", "7a1c259949b64822b14efe96efa5a1c6", "969e34faa7894fed97bb94bfd574d2c7", "2f8f03280cb34d5d9b7bf032a20cbdc5", "e3cc1e352d134667ba3e78a5a37a49a6", "c362cace867045c3964721c8954ce29e" ] }, "id": "mJeIaeJxNyRH", "outputId": "1f1d353c-aef1-4430-b35e-f75e571d2719" }, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "aff3a571f355474690e7b5b8094a827f", "version_major": 2, "version_minor": 0 }, "text/plain": [ "VBox(children=(HTML(value='
self.position_ids.size(0):\n", "/root/.cache/huggingface/modules/transformers_modules/Alibaba-NLP/new-impl/40ced75c3017eb27626c9d4ea981bde21a2662f4/modeling.py:210: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!\n", " if seq_len > self.max_seq_len_cached:\n", "Post-processing the exported models...\n", "Deduplicating shared (tied) weights...\n", "\n", "Validating ONNX model onnx/model.onnx...\n", "\t-[βœ“] ONNX model output names match reference model (sentence_embedding, token_embeddings)\n", "\t- Validating ONNX Model output \"token_embeddings\":\n", "\t\t-[βœ“] (2, 16, 1024) matches (2, 16, 1024)\n", "\t\t-[x] values not close enough, max diff: 0.00023162364959716797 (atol: 1e-05)\n", "\t- Validating ONNX Model output \"sentence_embedding\":\n", "\t\t-[βœ“] (2, 1024) matches (2, 1024)\n", "\t\t-[x] values not close enough, max diff: 2.574920654296875e-05 (atol: 1e-05)\n", "The ONNX export succeeded with the warning: The maximum absolute difference between the output of the reference model and the ONNX exported model is not within the set tolerance 1e-05:\n", "- token_embeddings: max diff = 0.00023162364959716797\n", "- sentence_embedding: max diff = 2.574920654296875e-05.\n", " The exported model was saved at: onnx\n" ] } ], "source": [ "!optimum-cli export onnx --model lw2134/policy_gte_large onnx/ --task feature-extraction --trust-remote-code --framework pt" ] }, { "cell_type": "code", "execution_count": 49, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 67, "referenced_widgets": [ "d278995977384c8fb7fa80a0723d5202", "d5b521e25b0b4abd8cf283a6f7b5bdf4", "9f0200c7b60f4fda824c0e7b3d2baf34", "73cf998fe0ca4df89ddc2e99ad5ac36a", "3e3ef21a3a6a41de85c3878e3c132f87", "0c21593bcc9b4b05be727f958b5acc98", "4456fc5bf5084c699ea1eded61e835b4", "c79604c83838496fb750facfb63925b3", "c5f20f64248341f082a70bb7831ef24b", "a9cac96674f24aa1a62bc9823cd3b192", "322b28569a964b90abf2973cfe583a9d" ] }, "id": "AEWIIiFrNyRH", "outputId": "7defdea1-ce83-4d33-9a5a-6045fcccffc0" }, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "d278995977384c8fb7fa80a0723d5202", "version_major": 2, "version_minor": 0 }, "text/plain": [ "model.safetensors: 0%| | 0.00/1.74G [00:00 NOTE: We're assuming 1 correct document in a \"hit\"." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "0713_3cowX4q" }, "outputs": [], "source": [ "def evaluate_openai(\n", " dataset,\n", " embed_model,\n", " top_k=5,\n", " verbose=False,\n", "):\n", " corpus = dataset['corpus']\n", " questions = dataset['questions']\n", " relevant_docs = dataset['relevant_contexts']\n", " documents = [Document(page_content=content, metadata={\"id\": doc_id}) for doc_id, content in corpus.items()]\n", " vectorstore = FAISS.from_documents(documents, embed_model)\n", "\n", " retriever = vectorstore.as_retriever(search_kwargs={\"k\": top_k})\n", "\n", " eval_results = []\n", " for id, question in tqdm.tqdm(questions.items()):\n", " retrieved_nodes = retriever.invoke(question)\n", " retrieved_ids = [node.metadata[\"id\"] for node in retrieved_nodes]\n", " expected_id = relevant_docs[id][0]\n", " is_hit = expected_id in retrieved_ids\n", " eval_results.append({\"id\": id, \"question\": question, \"expected_id\": expected_id, \"is_hit\": is_hit})\n", "\n", " return eval_results" ] }, { "cell_type": "markdown", "metadata": { "id": "hOr49m4O9lxY" }, "source": [ "All that's left to do is evaluate, we'll evaluate our model against:\n", "\n", "1. OpenAI's closed source `text-embedding-3-small`\n", "2. The base non-fine-tuned version of `Snowflake/snowflake-arctic-embed-m`.\n", "\n", "Let's see how it stacks up!" ] }, { "cell_type": "markdown", "metadata": { "id": "ijaeYpf593IW" }, "source": [ "### `text-embedding-3-small`" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "kyY3PztaxnU3", "outputId": "870feec7-fc79-4ca1-f365-803b478e3272" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 50/50 [00:07<00:00, 7.14it/s]\n" ] } ], "source": [ "te3_openai = OpenAIEmbeddings(model=\"text-embedding-3-small\")\n", "te3_results = evaluate_openai(test_dataset, te3_openai)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "kkyW90TCxx_i" }, "outputs": [], "source": [ "te3_results_df = pd.DataFrame(te3_results)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "MscVRdNCylJ-", "outputId": "d9a7174d-371c-43f8-9318-1497c4c47bde" }, "outputs": [ { "data": { "text/plain": [ "1.0" ] }, "execution_count": 33, "metadata": {}, "output_type": "execute_result" } ], "source": [ "te3_hit_rate = te3_results_df[\"is_hit\"].mean()\n", "te3_hit_rate" ] }, { "cell_type": "markdown", "metadata": { "id": "4Ra-mh0L96dQ" }, "source": [ "### `Snowflake/snowflake-arctic-embed-m` (base)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "OEskxwvFypHe", "outputId": "12d946a2-3079-43c5-99f2-5acdabff1dab" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 50/50 [00:00<00:00, 55.86it/s]\n" ] } ], "source": [ "from langchain_huggingface import HuggingFaceEmbeddings\n", "\n", "huggingface_embeddings = HuggingFaceEmbeddings(model_name=\"Snowflake/snowflake-arctic-embed-m\")\n", "arctic_embed_m_results = evaluate_openai(test_dataset, huggingface_embeddings)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "KlKgiXTWzMTg" }, "outputs": [], "source": [ "arctic_embed_m_results_df = pd.DataFrame(arctic_embed_m_results)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "zV5vJWrJzOhc", "outputId": "9ebb5064-f281-4d0b-d9d9-6c0882bda62f" }, "outputs": [ { "data": { "text/plain": [ "0.86" ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" } ], "source": [ "arctic_embed_m_hit_rate = arctic_embed_m_results_df[\"is_hit\"].mean()\n", "arctic_embed_m_hit_rate" ] }, { "cell_type": "markdown", "metadata": { "id": "lcR3-0s19_lu" }, "source": [ "### `Snowflake/snowflake-arctic-embed-m` (fine-tuned)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "Ilse1LduzP1i", "outputId": "80a75a78-2943-4f65-849a-66649443e0aa" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Some weights of BertModel were not initialized from the model checkpoint at finetuned_arctic and are newly initialized: ['pooler.dense.bias', 'pooler.dense.weight']\n", "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n", "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 50/50 [00:00<00:00, 83.70it/s]\n" ] } ], "source": [ "finetune_embeddings = HuggingFaceEmbeddings(model_name=\"finetuned_arctic\")\n", "finetune_results = evaluate_openai(test_dataset, finetune_embeddings)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "xxhZPqkNzZlh" }, "outputs": [], "source": [ "finetune_results_df = pd.DataFrame(finetune_results)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "4thAK2BXzaj6", "outputId": "32d0145a-8f5e-4c8d-bf8f-435ca4b25ae1" }, "outputs": [ { "data": { "text/plain": [ "1.0" ] }, "execution_count": 39, "metadata": {}, "output_type": "execute_result" } ], "source": [ "finetune_hit_rate = finetune_results_df[\"is_hit\"].mean()\n", "finetune_hit_rate" ] }, { "cell_type": "markdown", "metadata": { "id": "5pR0Ug9C9odh" }, "source": [ "# 🀝 Breakout Room #2" ] }, { "cell_type": "markdown", "metadata": { "id": "iegFM209mBk3" }, "source": [ "## Task 1: Vibe Checking the RAG Pipeline\n", "\n", "We're going to use our RAG pipeline to vibe check on some common phrases now that we've modified it!" ] }, { "cell_type": "markdown", "metadata": { "id": "Xzg0AA5krgR4" }, "source": [ "### Creating New Chunks\n", "\n", "In order to try and evaluate our system more fairly, let's create new chunks that we will use to create our Vector Store." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "KwQ2_LqNr0Tw" }, "outputs": [], "source": [ "text_splitter = RecursiveCharacterTextSplitter(\n", " chunk_size = 600,\n", " chunk_overlap = 50,\n", " length_function = len\n", ")\n", "\n", "training_documents = text_splitter.split_documents(training_documents_loaded.load())" ] }, { "cell_type": "markdown", "metadata": { "id": "gIdxahHXpP-c" }, "source": [ "### Base Chain\n", "\n", "We'll start by constructing our base chain, which will use the untrained retrieval model." ] }, { "cell_type": "markdown", "metadata": { "id": "bOsxIXpNpWC2" }, "source": [ "#### R - Retrieval" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "azIGIKYfmNCT" }, "outputs": [], "source": [ "from langchain_community.vectorstores import FAISS\n", "\n", "base_vectorstore = FAISS.from_documents(training_documents, huggingface_embeddings)\n", "base_retriever = base_vectorstore.as_retriever(search_kwargs={\"k\": 6})" ] }, { "cell_type": "markdown", "metadata": { "id": "l-1nVZ0KpX5N" }, "source": [ "#### A - Augmented" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "G10Fr-aKojeA" }, "outputs": [], "source": [ "from langchain_core.prompts import ChatPromptTemplate\n", "\n", "RAG_PROMPT = \"\"\"\\\n", "Given a provided context and a question, you must answer the question. If you do not know the answer, you must state that you do not know.\n", "\n", "Context:\n", "{context}\n", "\n", "Question:\n", "{question}\n", "\n", "Answer:\n", "\"\"\"\n", "\n", "rag_prompt_template = ChatPromptTemplate.from_template(RAG_PROMPT)" ] }, { "cell_type": "markdown", "metadata": { "id": "Euq6RQEopZvD" }, "source": [ "#### G - Generation" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "5-mfbbrypMHG" }, "outputs": [], "source": [ "rag_llm = ChatOpenAI(\n", " model=\"gpt-4o-mini\",\n", " temperature=0\n", ")" ] }, { "cell_type": "markdown", "metadata": { "id": "wQ2p4mnUpbYY" }, "source": [ "#### RAG - LCEL RAG Pipeline" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "ssuR-LaboyGq" }, "outputs": [], "source": [ "from operator import itemgetter\n", "from langchain_core.output_parsers import StrOutputParser\n", "from langchain_core.runnables import RunnablePassthrough, RunnableParallel\n", "\n", "base_rag_chain = (\n", " {\"context\": itemgetter(\"question\") | base_retriever, \"question\": itemgetter(\"question\")}\n", " | RunnablePassthrough.assign(context=itemgetter(\"context\"))\n", " | {\"response\": rag_prompt_template | rag_llm | StrOutputParser(), \"context\": itemgetter(\"context\")}\n", ")" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 69 }, "id": "emm6WbB9pfKt", "outputId": "87362d44-f332-4db7-8c62-76ff0d6a3985" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "type": "string" }, "text/plain": [ "'The EU wants to regulate AI to promote a human-centric approach to AI, ensure the development of secure, trustworthy, and ethical AI, protect ethical principles, and facilitate the protection of natural persons, democracy, the rule of law, and environmental protection. Additionally, the regulation aims to boost innovation and employment, making the Union a leader in the uptake of trustworthy AI.'" ] }, "execution_count": 45, "metadata": {}, "output_type": "execute_result" } ], "source": [ "base_rag_chain.invoke({\"question\" : \"Why does the EU want to regulate AI?\"})[\"response\"]" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 35 }, "id": "mUOrd0OBprAq", "outputId": "efc938ba-98d4-4eae-b2f8-4a030d15264c" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "type": "string" }, "text/plain": [ "'I do not know.'" ] }, "execution_count": 46, "metadata": {}, "output_type": "execute_result" } ], "source": [ "base_rag_chain.invoke({\"question\" : \"What are the codes of practice?\"})[\"response\"]" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 69 }, "id": "OnfuFl59py7I", "outputId": "dacc11e0-5f99-444b-c20a-497099b85bea" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "type": "string" }, "text/plain": [ "'The context suggests that models with at least a billion parameters are considered to display significant generality and competence in performing a wide range of tasks. Therefore, it can be inferred that having a billion parameters is a threshold for being considered a model with \"too many\" parameters in this context.'" ] }, "execution_count": 47, "metadata": {}, "output_type": "execute_result" } ], "source": [ "base_rag_chain.invoke({\"question\" : \"How many parameters is too many parameters?\"})[\"response\"]" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 122 }, "id": "-NmqwHBDqTZ8", "outputId": "78089a88-552f-4767-949d-01d052d28373" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "type": "string" }, "text/plain": [ "'An emotion recognition system is a type of artificial intelligence (AI) technology designed to identify and interpret human emotions based on various inputs, such as facial expressions, voice tone, body language, or biometric data. These systems analyze patterns in the data to infer the emotional state of an individual.\\n\\nThe importance of emotion recognition systems lies in their potential applications across various fields, including mental health, customer service, security, and human-computer interaction. They can enhance user experiences, improve communication, and provide insights into emotional well-being. However, there are significant concerns regarding their reliability, specificity, and potential for discriminatory outcomes, particularly given the variability of emotional expression across different cultures and individuals.'" ] }, "execution_count": 48, "metadata": {}, "output_type": "execute_result" } ], "source": [ "base_rag_chain.invoke({\"question\" : \"What is an emotion recognition system and why is it important?\"})[\"response\"]" ] }, { "cell_type": "markdown", "metadata": { "id": "SqNS0UJAp3lC" }, "source": [ "### Fine-tuned Embedding Model\n", "\n", "Now let's rebuild our RAG chain with the Fine-tuned model - the only component we need to change is our `FAISS` vectorstore!" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "ihO7tP6mqATy" }, "outputs": [], "source": [ "finetune_vectorstore = FAISS.from_documents(training_documents, finetune_embeddings)\n", "finetune_retriever = finetune_vectorstore.as_retriever(search_kwargs={\"k\": 6})" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "1_cIFvWzqKGY" }, "outputs": [], "source": [ "finetune_rag_chain = (\n", " {\"context\": itemgetter(\"question\") | finetune_retriever, \"question\": itemgetter(\"question\")}\n", " | RunnablePassthrough.assign(context=itemgetter(\"context\"))\n", " | {\"response\": rag_prompt_template | rag_llm | StrOutputParser(), \"context\": itemgetter(\"context\")}\n", ")" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 69 }, "id": "OJmRHJF2qNgj", "outputId": "48a724c6-886d-4774-f6a6-d0444a43f10b" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "type": "string" }, "text/plain": [ "'The EU wants to regulate AI to establish harmonized rules on artificial intelligence, ensuring safety, accountability, and ethical standards in the deployment of AI systems. This regulation aims to address the risks associated with high-risk AI systems and to protect the rights and interests of individuals and society as a whole.'" ] }, "execution_count": 51, "metadata": {}, "output_type": "execute_result" } ], "source": [ "finetune_rag_chain.invoke({\"question\" : \"Why does the EU want to regulate AI?\"})[\"response\"]" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 35 }, "id": "EnK-c2ugqPPh", "outputId": "2de4664b-14a6-4ec3-eb82-092b99daf10b" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "type": "string" }, "text/plain": [ "'I do not know.'" ] }, "execution_count": 52, "metadata": {}, "output_type": "execute_result" } ], "source": [ "finetune_rag_chain.invoke({\"question\" : \"What are the codes of practice?\"})[\"response\"]" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 35 }, "id": "83hssg1AWozc", "outputId": "4796adaa-b229-42fc-f054-23b338a598bc" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "type": "string" }, "text/plain": [ "'I do not know.'" ] }, "execution_count": 53, "metadata": {}, "output_type": "execute_result" } ], "source": [ "finetune_rag_chain.invoke({\"question\" : \"How many parameters is too many parameters?\"})[\"response\"]" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 122 }, "id": "rsHmGeFbqRET", "outputId": "289b27f0-2055-4e54-fc98-fde99f627d91" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "type": "string" }, "text/plain": [ "'An emotion recognition system is an AI system designed to identify or infer the emotions or intentions of natural persons based on their biometric data. This includes recognizing emotions such as happiness, sadness, anger, surprise, disgust, embarrassment, excitement, shame, contempt, satisfaction, and amusement. It does not encompass physical states like pain or fatigue.\\n\\nThe importance of emotion recognition systems lies in their potential applications across various fields, such as mental health, customer service, security, and human-computer interaction. By accurately identifying emotions, these systems can enhance user experiences, improve communication, and provide insights into human behavior, which can be crucial for developing responsive and empathetic AI technologies.'" ] }, "execution_count": 54, "metadata": {}, "output_type": "execute_result" } ], "source": [ "finetune_rag_chain.invoke({\"question\" : \"What is an emotion recognition system and why is it important?\"})[\"response\"]" ] }, { "cell_type": "markdown", "metadata": { "id": "jDgD8seY_I3W" }, "source": [ "#####❓Question #2:\n", "\n", "Which LCEL RAG Chain do you think answered the questions better, and why? \n", "\n", "LW: So, it actually looks like the base model answered better, which is weird. The fine-tuned model answered \"I don't know\" 2 of 4 times opposed to only 1 of 4 with the base model. Otherwise the answers are about the same with the base model maybe even marginally better according to an anecdotal glance at the answers." ] }, { "cell_type": "markdown", "metadata": { "id": "WCbq1sZArIx4" }, "source": [ "## Task 2: RAGAS Evaluation\n", "\n", "It's great to have some idea of how our system is doing based on vibe-checks, but let's use RAGAS to provide more insight info. on how things are improving!" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "_FNscBsPdm3p", "outputId": "ded473b3-4610-41de-b892-9c7087fba542" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/185.7 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[91m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[91mβ•Έ\u001b[0m \u001b[32m184.3/185.7 kB\u001b[0m \u001b[31m7.5 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m185.7/185.7 kB\u001b[0m \u001b[31m4.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25h\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/71.1 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m71.1/71.1 kB\u001b[0m \u001b[31m6.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25h" ] } ], "source": [ "!pip install -qU ragas" ] }, { "cell_type": "markdown", "metadata": { "id": "1wZzCz2mszM5" }, "source": [ "### RAGAS Synthetic Testset Generation\n", "\n", "First things first, we need to generate some data to test our model on.\n", "\n", "Let's use our test data that we created before as a base!" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "wKdQYQqps97f" }, "outputs": [], "source": [ "from ragas.testset.generator import TestsetGenerator\n", "from ragas.testset.evolutions import simple, reasoning, multi_context\n", "from langchain_openai import OpenAIEmbeddings\n", "\n", "generator_llm = ChatOpenAI(model=\"gpt-3.5-turbo\")\n", "critic_llm = ChatOpenAI(model=\"gpt-4o-mini\")\n", "embeddings = OpenAIEmbeddings()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "4tHo-ZcDtGSK" }, "outputs": [], "source": [ "generator = TestsetGenerator.from_langchain(\n", " generator_llm,\n", " critic_llm,\n", " embeddings\n", ")" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "YNjJsBOktLPT" }, "outputs": [], "source": [ "testset = generator.generate_with_langchain_docs(\n", " test_split_documents,\n", " test_size=20,\n", " distributions={simple: 0.5, reasoning: 0.25, multi_context: 0.25},\n", " raise_exceptions=False\n", ")" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 293 }, "id": "u7z2qoDJvz_2", "outputId": "bdd56f58-18c4-4b61-9f91-398613f0d1f6" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "summary": "{\n \"name\": \"testset\",\n \"rows\": 5,\n \"fields\": [\n {\n \"column\": \"question\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 5,\n \"samples\": [\n \"How can natural or legal persons lodge a complaint regarding the infringement of regulations related to AI systems?\",\n \"How are Member States' experts involved in the preparation of delegated acts in the European Parliament and the Council?\",\n \"How can the Commission and market surveillance authorities collaborate to promote compliance and identify non-compliance with respect to high-risk AI systems?\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"contexts\",\n \"properties\": {\n \"dtype\": \"object\",\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"ground_truth\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 5,\n \"samples\": [\n \"Natural or legal persons can lodge a complaint regarding the infringement of regulations related to AI systems by submitting a complaint to the relevant market surveillance authority. Union and national law already provide effective remedies for individuals and entities whose rights are affected by AI systems.\",\n \"Member States' experts are involved in the preparation of delegated acts in the European Parliament and the Council by receiving all documents at the same time as the Parliament and Council, and by having systematic access to meetings of Commission expert groups dealing with the preparation of delegated acts.\",\n \"The Commission and market surveillance authorities can collaborate by proposing joint activities, including joint investigations, to promote compliance, identify non-compliance, raise awareness, and provide guidance in relation to high-risk AI systems that present a serious risk across two or more Member States. These joint activities should be carried out in accordance with Article 9 of Regulation (EU) 2019/1020, with coordination support provided by the AI Office for joint investigations.\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"evolution_type\",\n \"properties\": {\n \"dtype\": \"category\",\n \"num_unique_values\": 1,\n \"samples\": [\n \"simple\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"metadata\",\n \"properties\": {\n \"dtype\": \"object\",\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"episode_done\",\n \"properties\": {\n \"dtype\": \"boolean\",\n \"num_unique_values\": 1,\n \"samples\": [\n true\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}", "type": "dataframe" }, "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
questioncontextsground_truthevolution_typemetadataepisode_done
0What role do competent authorities play in sup...[( 50 ) and (EU) 2016/97 ( 51 ) of the Europea...Competent authorities play a crucial role in s...simple[{'source': 'eu_ai_act.html', 'id': '51ea4d92-...True
1How can natural or legal persons lodge a compl...[(170) Union and national law already provide ...Natural or legal persons can lodge a complaint...simple[{'source': 'eu_ai_act.html', 'id': '9f53f575-...True
2How can the Commission and market surveillance...[(160) The market surveillance authorities and...The Commission and market surveillance authori...simple[{'source': 'eu_ai_act.html', 'id': 'f360da98-...True
3What requirements are established for internal...[undertakings and insurance holding companies ...Requirements regarding internal governance, ar...simple[{'source': 'eu_ai_act.html', 'id': '95e97d50-...True
4How are Member States' experts involved in the...[the preparation of delegated acts, the Europe...Member States' experts are involved in the pre...simple[{'source': 'eu_ai_act.html', 'id': '14147088-...True
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "text/plain": [ " question \\\n", "0 What role do competent authorities play in sup... \n", "1 How can natural or legal persons lodge a compl... \n", "2 How can the Commission and market surveillance... \n", "3 What requirements are established for internal... \n", "4 How are Member States' experts involved in the... \n", "\n", " contexts \\\n", "0 [( 50 ) and (EU) 2016/97 ( 51 ) of the Europea... \n", "1 [(170) Union and national law already provide ... \n", "2 [(160) The market surveillance authorities and... \n", "3 [undertakings and insurance holding companies ... \n", "4 [the preparation of delegated acts, the Europe... \n", "\n", " ground_truth evolution_type \\\n", "0 Competent authorities play a crucial role in s... simple \n", "1 Natural or legal persons can lodge a complaint... simple \n", "2 The Commission and market surveillance authori... simple \n", "3 Requirements regarding internal governance, ar... simple \n", "4 Member States' experts are involved in the pre... simple \n", "\n", " metadata episode_done \n", "0 [{'source': 'eu_ai_act.html', 'id': '51ea4d92-... True \n", "1 [{'source': 'eu_ai_act.html', 'id': '9f53f575-... True \n", "2 [{'source': 'eu_ai_act.html', 'id': 'f360da98-... True \n", "3 [{'source': 'eu_ai_act.html', 'id': '95e97d50-... True \n", "4 [{'source': 'eu_ai_act.html', 'id': '14147088-... True " ] }, "execution_count": 59, "metadata": {}, "output_type": "execute_result" } ], "source": [ "testset.to_pandas().head()" ] }, { "cell_type": "markdown", "metadata": { "id": "SUBS7yLmwHo8" }, "source": [ "### Generating Answer Datasets\n", "\n", "For each of our pipelines, let's generate answers to these questions!\n", "\n", "Once we have our: Questions, Answers, Contexts, Ground Truths we can move on to evaluating our datasets!" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "qDxhIdZFwnyK" }, "outputs": [], "source": [ "from datasets import Dataset\n", "\n", "def generate_answers(chain, testset):\n", " answers = []\n", " contexts = []\n", " questions = testset.to_pandas()[\"question\"].values.tolist()\n", " ground_truths = testset.to_pandas()[\"ground_truth\"].values.tolist()\n", "\n", " for question in tqdm.tqdm(questions):\n", " answer = chain.invoke({\"question\" : question})\n", " answers.append(answer[\"response\"])\n", " contexts.append([context.page_content for context in answer[\"context\"]])\n", "\n", " return Dataset.from_dict({\n", " \"question\" : questions,\n", " \"answer\" : answers,\n", " \"contexts\" : contexts,\n", " \"ground_truth\" : ground_truths\n", " })" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "K64AC_PFyuM9", "outputId": "cb439210-c3f2-47b0-c2f7-0827205fa83c" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 19/19 [00:15<00:00, 1.20it/s]\n" ] } ], "source": [ "base_dataset = generate_answers(base_rag_chain, testset)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "ABwQzmJuzB5J", "outputId": "ef9d2298-4b7a-4533-aa51-70f471182635" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 19/19 [00:18<00:00, 1.03it/s]\n" ] } ], "source": [ "finetune_dataset = generate_answers(finetune_rag_chain, testset)" ] }, { "cell_type": "markdown", "metadata": { "id": "yn2rN2lmvHeq" }, "source": [ "### Evaluating Using the Test Set\n", "\n", "Now that we have a test set - it's time to evaluate our pipelines with it!" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "qv1XatkXvOaL" }, "outputs": [], "source": [ "from ragas.metrics import (\n", " context_recall,\n", " context_precision,\n", ")" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "eKrPx5Hsz2Vp" }, "outputs": [], "source": [ "from ragas import evaluate\n", "\n", "result = evaluate(\n", " base_dataset,\n", " metrics=[\n", " context_precision,\n", " context_recall,\n", " ],\n", ")" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "EhkCw25F1V_l", "outputId": "f4da4c8f-4375-4977-a989-acaabc86ec62" }, "outputs": [ { "data": { "text/plain": [ "{'context_precision': 0.7086, 'context_recall': 0.6898}" ] }, "execution_count": 65, "metadata": {}, "output_type": "execute_result" } ], "source": [ "result" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 293 }, "id": "YhkPzbz60_Rq", "outputId": "77aba5ae-d906-4f74-b7e6-89fc6ff202a1" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "summary": "{\n \"name\": \"result\",\n \"rows\": 5,\n \"fields\": [\n {\n \"column\": \"question\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 5,\n \"samples\": [\n \"How can natural or legal persons lodge a complaint regarding the infringement of regulations related to AI systems?\",\n \"How are Member States' experts involved in the preparation of delegated acts in the European Parliament and the Council?\",\n \"How can the Commission and market surveillance authorities collaborate to promote compliance and identify non-compliance with respect to high-risk AI systems?\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"contexts\",\n \"properties\": {\n \"dtype\": \"object\",\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"answer\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 5,\n \"samples\": [\n \"Natural or legal persons can lodge a complaint regarding the infringement of regulations related to AI systems by utilizing the provisions set out for downstream providers to report possible infringements of the rules on providers of general-purpose AI models and systems. This process is supported by the AI Office, which facilitates effective monitoring of compliance with the regulations.\",\n \"Member States' experts are involved in the preparation of delegated acts by receiving all documents at the same time as the European Parliament and the Council. Additionally, their experts systematically have access to meetings of Commission expert groups, ensuring equal participation in the process.\",\n \"The Commission and market surveillance authorities can collaborate to promote compliance and identify non-compliance with respect to high-risk AI systems by working together on evaluations of compliance. Market surveillance authorities should cooperate with the AI Office to carry out these evaluations and inform the Board and other market surveillance authorities about their findings. Additionally, market surveillance authorities can request assistance from the AI Office when they are unable to conclude an investigation on a high-risk AI system. This collaborative approach ensures that both entities can effectively monitor and enforce compliance with the mandatory requirements laid down in the regulation for high-risk AI systems.\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"ground_truth\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 5,\n \"samples\": [\n \"Natural or legal persons can lodge a complaint regarding the infringement of regulations related to AI systems by submitting a complaint to the relevant market surveillance authority. Union and national law already provide effective remedies for individuals and entities whose rights are affected by AI systems.\",\n \"Member States' experts are involved in the preparation of delegated acts in the European Parliament and the Council by receiving all documents at the same time as the Parliament and Council, and by having systematic access to meetings of Commission expert groups dealing with the preparation of delegated acts.\",\n \"The Commission and market surveillance authorities can collaborate by proposing joint activities, including joint investigations, to promote compliance, identify non-compliance, raise awareness, and provide guidance in relation to high-risk AI systems that present a serious risk across two or more Member States. These joint activities should be carried out in accordance with Article 9 of Regulation (EU) 2019/1020, with coordination support provided by the AI Office for joint investigations.\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"context_precision\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.3247648721978082,\n \"min\": 0.249999999975,\n \"max\": 0.99999999995,\n \"num_unique_values\": 4,\n \"samples\": [\n 0.249999999975,\n 0.99999999995,\n 0.691666666649375\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"context_recall\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.27386127875258304,\n \"min\": 0.5,\n \"max\": 1.0,\n \"num_unique_values\": 2,\n \"samples\": [\n 0.5,\n 1.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}", "type": "dataframe" }, "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
questioncontextsanswerground_truthcontext_precisioncontext_recall
0What role do competent authorities play in sup...[of the high-risk AI system with the requireme...I do not know.Competent authorities play a crucial role in s...0.6916671.0
1How can natural or legal persons lodge a compl...[of protection or the need for compliance with...Natural or legal persons can lodge a complaint...Natural or legal persons can lodge a complaint...0.2500000.5
2How can the Commission and market surveillance...[of protection or the need for compliance with...The Commission and market surveillance authori...The Commission and market surveillance authori...0.5000000.5
3What requirements are established for internal...[For deployers that are financial institutions...The requirements established for internal gove...Requirements regarding internal governance, ar...1.0000000.5
4How are Member States' experts involved in the...[access to meetings of Commission expert group...Member States' experts are involved in the pre...Member States' experts are involved in the pre...1.0000001.0
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "text/plain": [ " question \\\n", "0 What role do competent authorities play in sup... \n", "1 How can natural or legal persons lodge a compl... \n", "2 How can the Commission and market surveillance... \n", "3 What requirements are established for internal... \n", "4 How are Member States' experts involved in the... \n", "\n", " contexts \\\n", "0 [of the high-risk AI system with the requireme... \n", "1 [of protection or the need for compliance with... \n", "2 [of protection or the need for compliance with... \n", "3 [For deployers that are financial institutions... \n", "4 [access to meetings of Commission expert group... \n", "\n", " answer \\\n", "0 I do not know. \n", "1 Natural or legal persons can lodge a complaint... \n", "2 The Commission and market surveillance authori... \n", "3 The requirements established for internal gove... \n", "4 Member States' experts are involved in the pre... \n", "\n", " ground_truth context_precision \\\n", "0 Competent authorities play a crucial role in s... 0.691667 \n", "1 Natural or legal persons can lodge a complaint... 0.250000 \n", "2 The Commission and market surveillance authori... 0.500000 \n", "3 Requirements regarding internal governance, ar... 1.000000 \n", "4 Member States' experts are involved in the pre... 1.000000 \n", "\n", " context_recall \n", "0 1.0 \n", "1 0.5 \n", "2 0.5 \n", "3 0.5 \n", "4 1.0 " ] }, "execution_count": 66, "metadata": {}, "output_type": "execute_result" } ], "source": [ "result.to_pandas().head()" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "pG3Cdbg11aP6" }, "outputs": [], "source": [ "result = evaluate(\n", " finetune_dataset,\n", " metrics=[\n", " context_precision,\n", " context_recall,\n", " ],\n", ")" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "weKKUo1n1lva", "outputId": "35a46dbb-4548-4309-a60a-afc00d95bc43" }, "outputs": [ { "data": { "text/plain": [ "{'context_precision': 0.7467, 'context_recall': 0.8947}" ] }, "execution_count": 68, "metadata": {}, "output_type": "execute_result" } ], "source": [ "result" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 293 }, "id": "MRdqp-Jb2KI3", "outputId": "34c28479-da34-4c16-e9ba-b676018a448a" }, "outputs": [ { "data": { "application/vnd.google.colaboratory.intrinsic+json": { "summary": "{\n \"name\": \"result\",\n \"rows\": 5,\n \"fields\": [\n {\n \"column\": \"question\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 5,\n \"samples\": [\n \"How can natural or legal persons lodge a complaint regarding the infringement of regulations related to AI systems?\",\n \"How are Member States' experts involved in the preparation of delegated acts in the European Parliament and the Council?\",\n \"How can the Commission and market surveillance authorities collaborate to promote compliance and identify non-compliance with respect to high-risk AI systems?\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"contexts\",\n \"properties\": {\n \"dtype\": \"object\",\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"answer\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 5,\n \"samples\": [\n \"Natural or legal persons can lodge a complaint regarding the infringement of regulations related to AI systems by submitting a duly reasoned complaint to the relevant market surveillance authority. The complaint should indicate at least the point of contact of the provider of the general-purpose AI model concerned, a description of the relevant facts, the provisions of the regulation that are believed to be infringed, and the reasons for considering that an infringement has occurred.\",\n \"Member States' experts are involved in the preparation of delegated acts by being consulted by the Commission before the adoption of such acts. The Commission is required to consult experts designated by each Member State in accordance with the principles laid down in the Interinstitutional Agreement of 13 April 2016 on Better Law-Making. Additionally, the European Parliament and the Council receive all documents at the same time as the Member States' experts, and their experts have systematic access to meetings of the Commission expert groups.\",\n \"The Commission and market surveillance authorities can collaborate to promote compliance and identify non-compliance with respect to high-risk AI systems by proposing and conducting joint activities, including joint investigations. These activities aim to raise awareness, provide guidance, and ensure compliance with the regulations concerning specific categories of high-risk AI systems that present serious risks across two or more Member States. Additionally, market surveillance authorities can cooperate with the AI Office to evaluate compliance and inform relevant parties, including the Board and other market surveillance authorities, about their findings and any non-compliance issues.\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"ground_truth\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 5,\n \"samples\": [\n \"Natural or legal persons can lodge a complaint regarding the infringement of regulations related to AI systems by submitting a complaint to the relevant market surveillance authority. Union and national law already provide effective remedies for individuals and entities whose rights are affected by AI systems.\",\n \"Member States' experts are involved in the preparation of delegated acts in the European Parliament and the Council by receiving all documents at the same time as the Parliament and Council, and by having systematic access to meetings of Commission expert groups dealing with the preparation of delegated acts.\",\n \"The Commission and market surveillance authorities can collaborate by proposing joint activities, including joint investigations, to promote compliance, identify non-compliance, raise awareness, and provide guidance in relation to high-risk AI systems that present a serious risk across two or more Member States. These joint activities should be carried out in accordance with Article 9 of Regulation (EU) 2019/1020, with coordination support provided by the AI Office for joint investigations.\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"context_precision\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.07453559925309863,\n \"min\": 0.8333333333055556,\n \"max\": 0.9999999999833333,\n \"num_unique_values\": 3,\n \"samples\": [\n 0.9999999999833333,\n 0.8333333333055556,\n 0.9999999999666667\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"context_recall\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 0.22360679774997896,\n \"min\": 0.5,\n \"max\": 1.0,\n \"num_unique_values\": 2,\n \"samples\": [\n 0.5,\n 1.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}", "type": "dataframe" }, "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
questioncontextsanswerground_truthcontext_precisioncontext_recall
0What role do competent authorities play in sup...[as defined in Regulation (EU) NoΒ 575/2013 of ...Competent authorities are designated to superv...Competent authorities play a crucial role in s...1.0000001.0
1How can natural or legal persons lodge a compl...[(170) Union and national law already provide ...Natural or legal persons can lodge a complaint...Natural or legal persons can lodge a complaint...0.8333331.0
2How can the Commission and market surveillance...[(160) The market surveillance authorities and...The Commission and market surveillance authori...The Commission and market surveillance authori...1.0000001.0
3What requirements are established for internal...[(158) Union financial services law includes i...The requirements established for internal gove...Requirements regarding internal governance, ar...1.0000000.5
4How are Member States' experts involved in the...[access to meetings of Commission expert group...Member States' experts are involved in the pre...Member States' experts are involved in the pre...1.0000001.0
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "text/plain": [ " question \\\n", "0 What role do competent authorities play in sup... \n", "1 How can natural or legal persons lodge a compl... \n", "2 How can the Commission and market surveillance... \n", "3 What requirements are established for internal... \n", "4 How are Member States' experts involved in the... \n", "\n", " contexts \\\n", "0 [as defined in Regulation (EU) NoΒ 575/2013 of ... \n", "1 [(170) Union and national law already provide ... \n", "2 [(160) The market surveillance authorities and... \n", "3 [(158) Union financial services law includes i... \n", "4 [access to meetings of Commission expert group... \n", "\n", " answer \\\n", "0 Competent authorities are designated to superv... \n", "1 Natural or legal persons can lodge a complaint... \n", "2 The Commission and market surveillance authori... \n", "3 The requirements established for internal gove... \n", "4 Member States' experts are involved in the pre... \n", "\n", " ground_truth context_precision \\\n", "0 Competent authorities play a crucial role in s... 1.000000 \n", "1 Natural or legal persons can lodge a complaint... 0.833333 \n", "2 The Commission and market surveillance authori... 1.000000 \n", "3 Requirements regarding internal governance, ar... 1.000000 \n", "4 Member States' experts are involved in the pre... 1.000000 \n", "\n", " context_recall \n", "0 1.0 \n", "1 1.0 \n", "2 1.0 \n", "3 0.5 \n", "4 1.0 " ] }, "execution_count": 69, "metadata": {}, "output_type": "execute_result" } ], "source": [ "result.to_pandas().head()" ] }, { "cell_type": "markdown", "metadata": { "id": "Y-aKOB1m-Bi8" }, "source": [ "#### πŸ—οΈ Activity #3:\n", "\n", "Discuss changes that you'd make to this pipeline based on the performance improvements that you see with RAGAS and the fine-tuning.\n", "\n", "Come up with 3 changes, and then we'll discuss these options as a group!" ] }, { "cell_type": "markdown", "metadata": { "id": "IwCgzuZd-TTs" }, "source": [ "1. We could implement some retrieval techniques, like Contextual Compression and MultiQueryRetriever to address precision and recall, like we did in the past. With Langchain, these cost very little to implement.\n", "2. We could attempt to improve the quality of the fine-tune by, for example, increasing the value of `n_questions` in the question generator chain, and/or by simply increasing the number of training examples. On a related note, I'm curious about the comparative performance of a fine-tune vs. non-fine-tune approach (i.e. option 1 vs. option 2 above), especially from a cost-benefit perspective.\n", "3. We could take another look at the actual fine-tuning traninig process, to include the base model and embedding size - and basically go bigger." ] }, { "cell_type": "markdown", "metadata": { "id": "VbyRqemZNyRV" }, "source": [] } ], "metadata": { "accelerator": "GPU", "colab": { "gpuType": "A100", "provenance": [] }, "kernelspec": { "display_name": "Python 3", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.11.10" }, "widgets": { "application/vnd.jupyter.widget-state+json": { "003008aa233e465f8186acb391e54edf": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "03f3a4d9071f446c9c900f545c43bca7": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "06181760a7bb47d0af60fb4080fd2586": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": "center", "align_self": null, "border": null, "bottom": null, "display": "flex", "flex": null, "flex_flow": "column", "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": "50%" } }, "0799a78c0cd54522b14f4994bb62074a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_6b36c6d1ac1d43528a02e71ccb1faabc", "placeholder": "​", "style": "IPY_MODEL_8409651d319b408f95d59f01812c6a4e", "value": " 1.74G/1.74G [00:07<00:00, 228MB/s]" } }, "0c21593bcc9b4b05be727f958b5acc98": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "100700603e854bbe937b39b4fc693a87": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "1243d94a1c704d54be128aa1d22acebf": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "1322f0a12b034f648afdfa287ddff45b": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "164aede9d80a45b3aa90ce83995af89d": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "17bc37a2d8824104baf8b1fcd3c85e30": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "1dcf6074f5f14229b2f118fdb05f35a7": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "1e39343a616c41ff8d123a39d832d99e": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "207c134337c844d19862b7056bd5de73": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "LabelModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "LabelModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "LabelView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_550d13efadd3447ba09bf08e8fddfee5", "placeholder": "​", "style": "IPY_MODEL_7a1c259949b64822b14efe96efa5a1c6", "value": "Your token has been saved in your configured git credential helpers (store)." } }, "230a83c8d6f740498fd24928b83eef25": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "CheckboxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "CheckboxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "CheckboxView", "description": "Add token as git credential?", "description_tooltip": null, "disabled": false, "indent": true, "layout": "IPY_MODEL_5a480538a2434170b49536ad596bf4f4", "style": "IPY_MODEL_7a42be9991564d7b89aa090600eb0f06", "value": true } }, "260bd64f8e0947858046bc0950a185af": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_e9a0fb52fe9c45f4a58c940bf1f3dfb3", "IPY_MODEL_c79aeb6cfafd42f88f43d630e300a016", "IPY_MODEL_885fbec012514fb189f61c4777180dcf" ], "layout": "IPY_MODEL_e0e656f937bc4b1d85d0f0fc6b906725" } }, "261999802b634c68b0f0fc9c76fab918": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "26579f3154e04f0fa160b0d36b86eaeb": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_7a32eaea10544afba8d7e9c47b02eb25", "placeholder": "​", "style": "IPY_MODEL_63ffc3294c214b1d814ae0d6fe34b4fc", "value": "configuration.py: 100%" } }, "28a422c882a345359315f73606cce5cc": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "2cf2ca752e564482ade99507b8bcf29c": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_b9c1ba7a50b34789bd1fbb3693cd42f0", "placeholder": "​", "style": "IPY_MODEL_487a0a31e6ac4737b108106bf78b73e5", "value": " 7.13k/7.13k [00:00<00:00, 494kB/s]" } }, "2f8f03280cb34d5d9b7bf032a20cbdc5": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "3140fcad984d4bf88ba95d2e88fab13e": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "322b28569a964b90abf2973cfe583a9d": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "39419bb1e79541668d4d86dcd74e6269": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_d22ea87f82654ce282d68ff2330498c7", "placeholder": "​", "style": "IPY_MODEL_ff5dee654f9c41ef9d5635e1b0663d1d", "value": " 1.35k/1.35k [00:00<00:00, 111kB/s]" } }, "3a85a2eeb44840a5a3abcf1c1363eadc": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "3ae2098a41f2420f9ce6152536db2fc9": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "3cb5b7c4200e428797a80dfbdce76b4f": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_d08e6f53da37496596d54b8e10813d76", "placeholder": "​", "style": "IPY_MODEL_3f98b81574bd4777871d01bad70f68c2", "value": " 0/1 [00:00<?, ?example/s]" } }, "3cb8803558334bca804dd7c0c05b677c": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_9dbf3c514d434d4aa631ac0644a395b4", "IPY_MODEL_65bb1340dd1d43d98cffae5ee0172d48", "IPY_MODEL_39419bb1e79541668d4d86dcd74e6269" ], "layout": "IPY_MODEL_5ddf4b48bbfd4eb8af1c695e0e4e8f65" } }, "3e3ef21a3a6a41de85c3878e3c132f87": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "3f412df4ae384216bc2ff05b45976695": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "PasswordModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "PasswordModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "PasswordView", "continuous_update": true, "description": "Token:", "description_tooltip": null, "disabled": false, "layout": "IPY_MODEL_4be1ca35c785486fb8c11c3439412a9c", "placeholder": "​", "style": "IPY_MODEL_ea161e1670be478f8a3adc44b819ad48", "value": "" } }, "3f98b81574bd4777871d01bad70f68c2": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "416d61b5a3cd45dcb2bf77f5a1336eb1": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_b6f53899d1004c03971e13cf236d83a6", "IPY_MODEL_e4f37d7070b949daa4937bc1c001450f", "IPY_MODEL_0799a78c0cd54522b14f4994bb62074a" ], "layout": "IPY_MODEL_e25a28e09e134048a29cc22a4ae000f1" } }, "41a35948e9454835925bf0e2586b526e": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "423380483ff7450eb844fcd930bd060a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "4456fc5bf5084c699ea1eded61e835b4": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "457b2a6bfdf941f9b96df25138f073df": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "461cc391ec6d4e52b27a61343aca6872": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "46d53760dc9043c7b591156c552cac80": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "487a0a31e6ac4737b108106bf78b73e5": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "48df4a674b7248ca830508fe50860f3f": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "49d3cafbcf8d4adf9f1582f5febfd8ca": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "4be1ca35c785486fb8c11c3439412a9c": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "4d1b875c0c4a4c22b40345183f5eda80": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_fe2a723aed954391919647ea7ee6960e", "IPY_MODEL_ed8b7c70eee348688191dd011c03b70a", "IPY_MODEL_e2e26c47dfd74119ae1f151ef314cf43" ], "layout": "IPY_MODEL_b12fd85e3fbf4270972fee2ce3cbf84d" } }, "4df120a3fc6d4be881bab6e28dbb4547": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "4e1199157bba49f7a5c10189d8a88b75": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "4f4236c3772b4ffd9e867db8a5f3f9e3": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "550d13efadd3447ba09bf08e8fddfee5": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "563c82052ab44f6cba2a607f35b8e116": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_1e39343a616c41ff8d123a39d832d99e", "placeholder": "​", "style": "IPY_MODEL_87f1c7d9a56d43e59f227c6d51a50d7a", "value": " 232k/232k [00:00<00:00, 5.24MB/s]" } }, "584c596ee11f45d7bfad02dbbc8e52e1": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "59f81e00efad4857a37e61b22c22d851": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_db3463ec0fe44b0aa3a33028f74a667f", "max": 695, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_457b2a6bfdf941f9b96df25138f073df", "value": 695 } }, "5a480538a2434170b49536ad596bf4f4": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "5ab69cb33f6e4993a18f2f4819f3cd4a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_28a422c882a345359315f73606cce5cc", "placeholder": "​", "style": "IPY_MODEL_6d60c7b6d6d24aaba618ad031b2eb1cd", "value": "\nPro Tip: If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks.
" } }, "5c789a4dfdaa4ee5b6ff6210b1e4113e": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_79a2bb833709472c9ff79deeb913b242", "IPY_MODEL_a4842dc8f7304d21b1a1723aa3ae3205", "IPY_MODEL_b1481983d01640f892a08dc3f579a5fb" ], "layout": "IPY_MODEL_c6a290fae64e452fbe27a519b6956689" } }, "5d122374044e4f87a8a98b79205db43e": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "LabelModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "LabelModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "LabelView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_969e34faa7894fed97bb94bfd574d2c7", "placeholder": "​", "style": "IPY_MODEL_2f8f03280cb34d5d9b7bf032a20cbdc5", "value": "Your token has been saved to /root/.cache/huggingface/token" } }, "5ddf4b48bbfd4eb8af1c695e0e4e8f65": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "5f37bf8a87dd449b9ba203cfec1f1911": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "601a68c9f95f4e7294ebe191b1d3bcc9": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_904196c265f34f82bbd25826e95d6518", "placeholder": "​", "style": "IPY_MODEL_b2a1e2b745ce4f82aa86d1913c44a987", "value": "sentence_bert_config.json: 100%" } }, "612dd8f9ef0047d8b97b1ad2480a59b2": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "62833db6c2f6488e9838b794e829f0db": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "63ffc3294c214b1d814ae0d6fe34b4fc": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "64ea657034be4d918ea331a7f97ac983": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "65bb1340dd1d43d98cffae5ee0172d48": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_4df120a3fc6d4be881bab6e28dbb4547", "max": 1349, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_d08cb75923e34eb88f917b8e43caee0a", "value": 1349 } }, "661684f9eb8c4860a21221e9afba881e": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_26579f3154e04f0fa160b0d36b86eaeb", "IPY_MODEL_830c9aea80514ec9977f7bb606e58214", "IPY_MODEL_2cf2ca752e564482ade99507b8bcf29c" ], "layout": "IPY_MODEL_41a35948e9454835925bf0e2586b526e" } }, "684b55e94d934156b9a99d4108fa3849": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "69116ab4892047c2b2cd71310707c61e": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "69b02e117be749c2b9f0a5f4c13522f2": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_c15620b939914d9e8e3034a40e73d357", "max": 229, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_f4f1696bef9b40a0a05d55c56fb23eff", "value": 229 } }, "6b36c6d1ac1d43528a02e71ccb1faabc": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "6b53e0c6f1cb449c8ee93cf12e5f192b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "6b8362dd21ad4db9a3398d826d292b39": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "6d60c7b6d6d24aaba618ad031b2eb1cd": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "706082a2c72a4cd68b9e893ec61de34c": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "71a3e7d00bf2468a918d8790e3eedef0": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "71a669f899c541d0a6cf18f4e139de34": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "728babf8f44742c8bb1b007b073d80f7": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "72913a91036e4e3281b37c7445f3598d": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "73cf998fe0ca4df89ddc2e99ad5ac36a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_a9cac96674f24aa1a62bc9823cd3b192", "placeholder": "​", "style": "IPY_MODEL_322b28569a964b90abf2973cfe583a9d", "value": " 1.74G/1.74G [00:44<00:00, 38.3MB/s]" } }, "76831eb40b72418ab1c41b47846a3c47": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "79a2bb833709472c9ff79deeb913b242": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_be5ac4aa543347558de0ea730909eda7", "placeholder": "​", "style": "IPY_MODEL_9391ed4727d5470a8636b010089b4c23", "value": "modeling.py: 100%" } }, "7a1c259949b64822b14efe96efa5a1c6": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "7a32eaea10544afba8d7e9c47b02eb25": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "7a42be9991564d7b89aa090600eb0f06": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "7a576273d59747efbcd96fe90d112374": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_584c596ee11f45d7bfad02dbbc8e52e1", "placeholder": "​", "style": "IPY_MODEL_7e4351d85d684185a8ac704a3043b9a2", "value": " 695/695 [00:00<00:00, 56.1kB/s]" } }, "7e4351d85d684185a8ac704a3043b9a2": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "7f4e537ea54248158014536ac62468fb": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "830c9aea80514ec9977f7bb606e58214": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_e5e014a04d0c4778a586064cdd09526a", "max": 7127, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_728babf8f44742c8bb1b007b073d80f7", "value": 7127 } }, "8409651d319b408f95d59f01812c6a4e": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "84b25a8cbe7846119f679c0ffa0e67c0": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "8740362325a5465e98273083a7784478": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_8b279a4a7982443683fdcf99b1c48120", "max": 1, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_261999802b634c68b0f0fc9c76fab918", "value": 1 } }, "87f1c7d9a56d43e59f227c6d51a50d7a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "885fbec012514fb189f61c4777180dcf": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_9fc8aea93c474b8db505e8fe35f86e4d", "placeholder": "​", "style": "IPY_MODEL_bf307298c0b54e76bd27ee55c2c8e33e", "value": " 71.8k/71.8k [00:00<00:00, 3.30MB/s]" } }, "8b279a4a7982443683fdcf99b1c48120": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "8c5a14700b7545339a177204eeedcc3b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_69116ab4892047c2b2cd71310707c61e", "placeholder": "​", "style": "IPY_MODEL_bbf2f6fd042346a389b4ccb978c064f9", "value": "special_tokens_map.json: 100%" } }, "8dad48d002334b71b552bb4f01b40c9b": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": "hidden", "width": null } }, "904196c265f34f82bbd25826e95d6518": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "90790a4bd48242bdb659803f02604774": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "9391ed4727d5470a8636b010089b4c23": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "941cb11c2b954930b10b1428e8e0cf40": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_e1f63d4e2df04970b188702a562d71bf", "IPY_MODEL_69b02e117be749c2b9f0a5f4c13522f2", "IPY_MODEL_d6ea1f88af9240db884e42c7616cde14" ], "layout": "IPY_MODEL_71a669f899c541d0a6cf18f4e139de34" } }, "95e4c9dc822f4641822d259ecd5b2684": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "969e34faa7894fed97bb94bfd574d2c7": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "995803924a5a49c2bde5f586777911f3": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_8c5a14700b7545339a177204eeedcc3b", "IPY_MODEL_59f81e00efad4857a37e61b22c22d851", "IPY_MODEL_7a576273d59747efbcd96fe90d112374" ], "layout": "IPY_MODEL_461cc391ec6d4e52b27a61343aca6872" } }, "996e1dbb6de84fe0a837eb02e5dabbfe": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_76831eb40b72418ab1c41b47846a3c47", "max": 711661, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_64ea657034be4d918ea331a7f97ac983", "value": 711661 } }, "99912b9fe62e4b35b63abd219380a26d": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ButtonStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ButtonStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "button_color": null, "font_weight": "" } }, "9dbf3c514d434d4aa631ac0644a395b4": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_100700603e854bbe937b39b4fc693a87", "placeholder": "​", "style": "IPY_MODEL_684b55e94d934156b9a99d4108fa3849", "value": "config.json: 100%" } }, "9f0200c7b60f4fda824c0e7b3d2baf34": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_c79604c83838496fb750facfb63925b3", "max": 1736585680, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_c5f20f64248341f082a70bb7831ef24b", "value": 1736585680 } }, "9fc8aea93c474b8db505e8fe35f86e4d": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "a1fab3040d814d7e88368dd9aa6a07c7": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_bf5646c479c1426698378f2ed5fb81b4", "max": 231508, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_423380483ff7450eb844fcd930bd060a", "value": 231508 } }, "a4842dc8f7304d21b1a1723aa3ae3205": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_5f37bf8a87dd449b9ba203cfec1f1911", "max": 59023, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_dc19251b2af74e5ca87b47b7e37d5b3a", "value": 59023 } }, "a512356c0de140f8a24d46c7b69ad195": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "a5368801499e473cb117329c3dfa955b": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "a71c56f4215c4b0e9affc34dca348b54": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_f278940553124e56ad857ddb00d00141", "placeholder": "​", "style": "IPY_MODEL_1dcf6074f5f14229b2f118fdb05f35a7", "value": " 54.0/54.0 [00:00<00:00, 4.53kB/s]" } }, "a988e2eba727484f94f3441b1310364c": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "a9cac96674f24aa1a62bc9823cd3b192": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "aae66fffe3834923bd798e183740b3d6": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_d62e51d0c84d48f9b3bc2e2493f732f1", "IPY_MODEL_8740362325a5465e98273083a7784478", "IPY_MODEL_3cb5b7c4200e428797a80dfbdce76b4f" ], "layout": "IPY_MODEL_8dad48d002334b71b552bb4f01b40c9b" } }, "aff3a571f355474690e7b5b8094a827f": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "VBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "VBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "VBoxView", "box_style": "", "children": [ "IPY_MODEL_c2e9e7085b2f42a7b8fa3b4fc2ec0b10", "IPY_MODEL_207c134337c844d19862b7056bd5de73", "IPY_MODEL_5d122374044e4f87a8a98b79205db43e", "IPY_MODEL_dcda6daa8c2e49fb9703e9e883c4f995" ], "layout": "IPY_MODEL_06181760a7bb47d0af60fb4080fd2586" } }, "b12fd85e3fbf4270972fee2ce3cbf84d": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "b1481983d01640f892a08dc3f579a5fb": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_a512356c0de140f8a24d46c7b69ad195", "placeholder": "​", "style": "IPY_MODEL_1243d94a1c704d54be128aa1d22acebf", "value": " 59.0k/59.0k [00:00<00:00, 3.52MB/s]" } }, "b24fefe04ec449c3bf3e059fc31d3655": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_95e4c9dc822f4641822d259ecd5b2684", "max": 54, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_17bc37a2d8824104baf8b1fcd3c85e30", "value": 54 } }, "b25bf487739a4deeaf700a3f1b4cb9da": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_612dd8f9ef0047d8b97b1ad2480a59b2", "placeholder": "​", "style": "IPY_MODEL_48df4a674b7248ca830508fe50860f3f", "value": "1_Pooling/config.json: 100%" } }, "b2a1e2b745ce4f82aa86d1913c44a987": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "b4385f11ff514010b85ebf46e36f0658": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "b51e0ea5a82b446992d121bdbb11ffcd": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "b6f53899d1004c03971e13cf236d83a6": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_3a85a2eeb44840a5a3abcf1c1363eadc", "placeholder": "​", "style": "IPY_MODEL_72913a91036e4e3281b37c7445f3598d", "value": "model.safetensors: 100%" } }, "b90b699209484938968ef673f153b8cb": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "b9c1ba7a50b34789bd1fbb3693cd42f0": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "ba48250c8d1a4b869b3984e89e609a65": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_601a68c9f95f4e7294ebe191b1d3bcc9", "IPY_MODEL_b24fefe04ec449c3bf3e059fc31d3655", "IPY_MODEL_a71c56f4215c4b0e9affc34dca348b54" ], "layout": "IPY_MODEL_71a3e7d00bf2468a918d8790e3eedef0" } }, "bbf2f6fd042346a389b4ccb978c064f9": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "bdcfe5ad999142408db010ddb62e8fde": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "LabelModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "LabelModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "LabelView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_ca0586788cd24803acb7052d70f9f091", "placeholder": "​", "style": "IPY_MODEL_bdfaef138a7340a1b45e5b257fdfea4d", "value": "Connecting..." } }, "bdfaef138a7340a1b45e5b257fdfea4d": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "be5ac4aa543347558de0ea730909eda7": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "be5e375ca07844c6b734d998d0794702": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "bf307298c0b54e76bd27ee55c2c8e33e": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "bf5646c479c1426698378f2ed5fb81b4": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "bfb6a086089a482db26fc8364712dbcf": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "c15620b939914d9e8e3034a40e73d357": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "c2e9e7085b2f42a7b8fa3b4fc2ec0b10": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "LabelModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "LabelModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "LabelView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_62833db6c2f6488e9838b794e829f0db", "placeholder": "​", "style": "IPY_MODEL_03f3a4d9071f446c9c900f545c43bca7", "value": "Token is valid (permission: write)." } }, "c359508223504035ae45a5c35ab38e34": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "c362cace867045c3964721c8954ce29e": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "c44c462147e0495f83fb43cb21f8ec30": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_ca449ed7f3364b25a8f76a6e1e6cbdbf", "IPY_MODEL_996e1dbb6de84fe0a837eb02e5dabbfe", "IPY_MODEL_f4cbfa45eff24264b712f5a6b0b48ec4" ], "layout": "IPY_MODEL_b90b699209484938968ef673f153b8cb" } }, "c5f20f64248341f082a70bb7831ef24b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "c6a290fae64e452fbe27a519b6956689": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "c79604c83838496fb750facfb63925b3": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "c79aeb6cfafd42f88f43d630e300a016": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_eb690c7a5d294e359acf44113dcdedc9", "max": 71774, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_e59d85704f264a249d3172609cc3ea93", "value": 71774 } }, "ca0586788cd24803acb7052d70f9f091": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "ca449ed7f3364b25a8f76a6e1e6cbdbf": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_cfa45c6a7d544deda41944d787e87d3a", "placeholder": "​", "style": "IPY_MODEL_706082a2c72a4cd68b9e893ec61de34c", "value": "tokenizer.json: 100%" } }, "cc23412bc12b49af9f06030961039646": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "cca5686952a8422e828fe06a5b26fe31": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_90790a4bd48242bdb659803f02604774", "placeholder": "​", "style": "IPY_MODEL_6b53e0c6f1cb449c8ee93cf12e5f192b", "value": "

Copy a token from your Hugging Face\ntokens page and paste it below.
Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file.
" } }, "cf9f0b0058f4432bafe3a74e5205658f": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_d3abfb110a434c9cac3a54ea17f932ab", "placeholder": "​", "style": "IPY_MODEL_bfb6a086089a482db26fc8364712dbcf", "value": "vocab.txt: 100%" } }, "cfa45c6a7d544deda41944d787e87d3a": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d08cb75923e34eb88f917b8e43caee0a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "d08e6f53da37496596d54b8e10813d76": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d22ea87f82654ce282d68ff2330498c7": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d278995977384c8fb7fa80a0723d5202": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_d5b521e25b0b4abd8cf283a6f7b5bdf4", "IPY_MODEL_9f0200c7b60f4fda824c0e7b3d2baf34", "IPY_MODEL_73cf998fe0ca4df89ddc2e99ad5ac36a" ], "layout": "IPY_MODEL_3e3ef21a3a6a41de85c3878e3c132f87" } }, "d3abfb110a434c9cac3a54ea17f932ab": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d578c47644c447ab922c3cb4b3404c43": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d5b521e25b0b4abd8cf283a6f7b5bdf4": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_0c21593bcc9b4b05be727f958b5acc98", "placeholder": "​", "style": "IPY_MODEL_4456fc5bf5084c699ea1eded61e835b4", "value": "model.safetensors: 100%" } }, "d62e51d0c84d48f9b3bc2e2493f732f1": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_c359508223504035ae45a5c35ab38e34", "placeholder": "​", "style": "IPY_MODEL_b51e0ea5a82b446992d121bdbb11ffcd", "value": "Computing widget examples:   0%" } }, "d6ea1f88af9240db884e42c7616cde14": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_be5e375ca07844c6b734d998d0794702", "placeholder": "​", "style": "IPY_MODEL_7f4e537ea54248158014536ac62468fb", "value": " 229/229 [00:00<00:00, 18.5kB/s]" } }, "d8d57da8d0654b958b466195306ae28a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "d94c120ebdf54241adc4dfdda9f716f2": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_d578c47644c447ab922c3cb4b3404c43", "max": 297, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_a988e2eba727484f94f3441b1310364c", "value": 297 } }, "db3463ec0fe44b0aa3a33028f74a667f": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "dc19251b2af74e5ca87b47b7e37d5b3a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "dcda6daa8c2e49fb9703e9e883c4f995": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "LabelModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "LabelModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "LabelView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_e3cc1e352d134667ba3e78a5a37a49a6", "placeholder": "​", "style": "IPY_MODEL_c362cace867045c3964721c8954ce29e", "value": "Login successful" } }, "de32a0436b0a48379652638ee573be35": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ButtonModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ButtonModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ButtonView", "button_style": "", "description": "Login", "disabled": false, "icon": "", "layout": "IPY_MODEL_6b8362dd21ad4db9a3398d826d292b39", "style": "IPY_MODEL_99912b9fe62e4b35b63abd219380a26d", "tooltip": "" } }, "e0e656f937bc4b1d85d0f0fc6b906725": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "e1f63d4e2df04970b188702a562d71bf": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_fad62cb1a0ff4760b17a5247de518e3d", "placeholder": "​", "style": "IPY_MODEL_d8d57da8d0654b958b466195306ae28a", "value": "modules.json: 100%" } }, "e25a28e09e134048a29cc22a4ae000f1": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "e2e26c47dfd74119ae1f151ef314cf43": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_84b25a8cbe7846119f679c0ffa0e67c0", "placeholder": "​", "style": "IPY_MODEL_003008aa233e465f8186acb391e54edf", "value": " 1.38k/1.38k [00:00<00:00, 92.1kB/s]" } }, "e3cc1e352d134667ba3e78a5a37a49a6": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "e4f37d7070b949daa4937bc1c001450f": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_1322f0a12b034f648afdfa287ddff45b", "max": 1736585680, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_b4385f11ff514010b85ebf46e36f0658", "value": 1736585680 } }, "e59d85704f264a249d3172609cc3ea93": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "e5e014a04d0c4778a586064cdd09526a": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "e5ef0d550e2c4f829caf3c47a72a1bf2": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_b25bf487739a4deeaf700a3f1b4cb9da", "IPY_MODEL_d94c120ebdf54241adc4dfdda9f716f2", "IPY_MODEL_f489742ec1104e0f8638a1de8f8f9ef6" ], "layout": "IPY_MODEL_ee1ea5e939d740c38fe9daebb83fd2c2" } }, "e7668e7cf5a2441fa48bcb81f6e8feb6": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "e9243eceb4344a3595be76f0605c2c15": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_cf9f0b0058f4432bafe3a74e5205658f", "IPY_MODEL_a1fab3040d814d7e88368dd9aa6a07c7", "IPY_MODEL_563c82052ab44f6cba2a607f35b8e116" ], "layout": "IPY_MODEL_4f4236c3772b4ffd9e867db8a5f3f9e3" } }, "e9a0fb52fe9c45f4a58c940bf1f3dfb3": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_cc23412bc12b49af9f06030961039646", "placeholder": "​", "style": "IPY_MODEL_f2113ec0bf764ac7af3a9fd9d4ab9e54", "value": "README.md: 100%" } }, "ea161e1670be478f8a3adc44b819ad48": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "eb690c7a5d294e359acf44113dcdedc9": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "ed8b7c70eee348688191dd011c03b70a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_46d53760dc9043c7b591156c552cac80", "max": 1384, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_3ae2098a41f2420f9ce6152536db2fc9", "value": 1384 } }, "ee1ea5e939d740c38fe9daebb83fd2c2": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "f2113ec0bf764ac7af3a9fd9d4ab9e54": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "f278940553124e56ad857ddb00d00141": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "f489742ec1104e0f8638a1de8f8f9ef6": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_a5368801499e473cb117329c3dfa955b", "placeholder": "​", "style": "IPY_MODEL_164aede9d80a45b3aa90ce83995af89d", "value": " 297/297 [00:00<00:00, 21.3kB/s]" } }, "f4cbfa45eff24264b712f5a6b0b48ec4": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_49d3cafbcf8d4adf9f1582f5febfd8ca", "placeholder": "​", "style": "IPY_MODEL_3140fcad984d4bf88ba95d2e88fab13e", "value": " 712k/712k [00:00<00:00, 8.21MB/s]" } }, "f4f1696bef9b40a0a05d55c56fb23eff": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "fad62cb1a0ff4760b17a5247de518e3d": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "fe2a723aed954391919647ea7ee6960e": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_e7668e7cf5a2441fa48bcb81f6e8feb6", "placeholder": "​", "style": "IPY_MODEL_4e1199157bba49f7a5c10189d8a88b75", "value": "tokenizer_config.json: 100%" } }, "ff5dee654f9c41ef9d5635e1b0663d1d": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } } } } }, "nbformat": 4, "nbformat_minor": 0 }