{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "id": "Hyg4prvKsTfC"
      },
      "outputs": [],
      "source": [
        "#!pip install bitsandbytes\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#pip install accelerate"
      ],
      "metadata": {
        "id": "MVqLMtMt0Uhc"
      },
      "execution_count": 15,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#!pip install accelerate\n",
        "#!pip install bitsandbytes -i https://pypi.org/simple/\n"
      ],
      "metadata": {
        "id": "BeHjgLP_0laH"
      },
      "execution_count": 16,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Load model directly\n",
        "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
        "\n",
        "#tokenizer = AutoTokenizer.from_pretrained(\"harry85/tokenizer-finetuned-TinyLLAMA\")\n",
        "#model = AutoModelForCausalLM.from_pretrained(\"unsloth/tinyllama-bnb-4bit\")\n",
        "# Load model directly\n",
        "#from transformers import AutoTokenizer, AutoModelForCausalLM\n",
        "# Load model directly\n",
        "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
        "\n",
        "tokenizer = AutoTokenizer.from_pretrained(\"harry85/finetuned-TinyLLAMA-own-data-07\")\n",
        "model = AutoModelForCausalLM.from_pretrained(\"harry85/finetuned-TinyLLAMA-own-data-07\")\n",
        "\n",
        "\n",
        "# Enable native 2x faster inference if supported\n",
        "# This feature depends on the specific model and framework used; modify as needed.\n",
        "# For example, in the case of some models, you can use model.half() to convert to FP16 for faster inference.\n",
        "\n",
        "# Define the Alpaca prompt\n",
        "alpaca_prompt = \"\"\"\\\n",
        "### Instruction:\n",
        "{0}\n",
        "\n",
        "### Input:\n",
        "\n",
        "{1}\n",
        "\n",
        "### Response:\n",
        "{2}\"\"\"\n",
        "\n",
        "# Prepare the input\n",
        "inputs = tokenizer(\n",
        "    [\n",
        "        alpaca_prompt.format(\n",
        "            \"Continue the Fibonacci sequence.\",  # instruction\n",
        "            \"1, 1, 2, 3, 5, 8\",  # input\n",
        "            \"\"  # output - leave this blank for generation!\n",
        "        )\n",
        "    ],\n",
        "    return_tensors=\"pt\"\n",
        ").to(\"cuda\")\n",
        "\n",
        "# Generate the output\n",
        "outputs = model.generate(**inputs, max_new_tokens=64, use_cache=True)\n",
        "\n",
        "# Decode and print the output\n",
        "response = tokenizer.batch_decode(outputs, skip_special_tokens=True)\n",
        "print(response)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "RxlJ3o75sUrN",
        "outputId": "1c767815-7def-42a3-f250-69c7bbe802b7"
      },
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Unused kwargs: ['quant_method']. These kwargs are not used in <class 'transformers.utils.quantization_config.BitsAndBytesConfig'>.\n",
            "`low_cpu_mem_usage` was None, now set to True since model is quantized.\n",
            "Some weights of the model checkpoint at harry85/finetuned-TinyLLAMA-own-data-07 were not used when initializing LlamaForCausalLM: ['base_model.model.model.layers.0.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.0.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.0.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.0.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.0.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.0.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.0.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.0.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.0.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.0.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.0.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.0.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.0.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.0.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.1.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.1.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.1.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.1.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.1.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.1.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.1.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.1.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.1.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.1.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.1.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.1.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.1.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.1.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.10.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.10.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.10.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.10.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.10.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.10.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.10.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.10.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.10.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.10.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.10.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.10.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.10.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.10.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.11.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.11.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.11.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.11.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.11.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.11.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.11.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.11.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.11.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.11.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.11.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.11.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.11.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.11.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.12.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.12.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.12.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.12.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.12.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.12.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.12.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.12.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.12.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.12.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.12.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.12.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.12.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.12.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.13.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.13.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.13.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.13.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.13.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.13.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.13.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.13.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.13.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.13.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.13.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.13.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.13.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.13.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.14.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.14.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.14.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.14.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.14.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.14.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.14.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.14.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.14.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.14.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.14.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.14.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.14.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.14.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.15.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.15.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.15.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.15.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.15.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.15.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.15.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.15.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.15.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.15.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.15.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.15.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.15.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.15.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.16.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.16.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.16.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.16.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.16.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.16.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.16.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.16.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.16.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.16.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.16.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.16.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.16.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.16.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.17.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.17.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.17.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.17.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.17.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.17.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.17.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.17.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.17.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.17.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.17.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.17.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.17.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.17.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.18.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.18.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.18.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.18.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.18.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.18.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.18.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.18.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.18.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.18.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.18.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.18.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.18.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.18.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.19.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.19.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.19.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.19.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.19.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.19.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.19.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.19.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.19.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.19.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.19.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.19.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.19.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.19.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.2.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.2.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.2.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.2.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.2.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.2.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.2.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.2.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.2.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.2.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.2.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.2.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.2.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.2.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.20.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.20.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.20.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.20.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.20.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.20.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.20.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.20.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.20.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.20.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.20.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.20.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.20.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.20.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.21.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.21.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.21.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.21.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.21.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.21.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.21.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.21.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.21.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.21.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.21.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.21.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.21.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.21.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.3.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.3.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.3.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.3.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.3.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.3.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.3.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.3.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.3.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.3.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.3.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.3.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.3.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.3.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.4.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.4.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.4.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.4.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.4.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.4.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.4.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.4.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.4.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.4.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.4.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.4.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.4.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.4.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.5.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.5.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.5.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.5.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.5.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.5.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.5.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.5.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.5.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.5.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.5.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.5.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.5.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.5.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.6.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.6.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.6.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.6.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.6.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.6.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.6.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.6.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.6.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.6.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.6.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.6.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.6.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.6.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.7.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.7.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.7.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.7.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.7.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.7.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.7.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.7.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.7.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.7.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.7.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.7.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.7.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.7.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.8.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.8.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.8.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.8.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.8.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.8.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.8.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.8.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.8.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.8.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.8.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.8.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.8.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.8.self_attn.v_proj.lora_B.weight', 'base_model.model.model.layers.9.mlp.down_proj.lora_A.weight', 'base_model.model.model.layers.9.mlp.down_proj.lora_B.weight', 'base_model.model.model.layers.9.mlp.gate_proj.lora_A.weight', 'base_model.model.model.layers.9.mlp.gate_proj.lora_B.weight', 'base_model.model.model.layers.9.mlp.up_proj.lora_A.weight', 'base_model.model.model.layers.9.mlp.up_proj.lora_B.weight', 'base_model.model.model.layers.9.self_attn.k_proj.lora_A.weight', 'base_model.model.model.layers.9.self_attn.k_proj.lora_B.weight', 'base_model.model.model.layers.9.self_attn.o_proj.lora_A.weight', 'base_model.model.model.layers.9.self_attn.o_proj.lora_B.weight', 'base_model.model.model.layers.9.self_attn.q_proj.lora_A.weight', 'base_model.model.model.layers.9.self_attn.q_proj.lora_B.weight', 'base_model.model.model.layers.9.self_attn.v_proj.lora_A.weight', 'base_model.model.model.layers.9.self_attn.v_proj.lora_B.weight']\n",
            "- This IS expected if you are initializing LlamaForCausalLM from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
            "- This IS NOT expected if you are initializing LlamaForCausalLM from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
            "Some weights of LlamaForCausalLM were not initialized from the model checkpoint at harry85/finetuned-TinyLLAMA-own-data-07 and are newly initialized: ['embed_tokens.weight', 'layers.0.input_layernorm.weight', 'layers.0.mlp.down_proj.weight', 'layers.0.mlp.gate_proj.weight', 'layers.0.mlp.up_proj.weight', 'layers.0.post_attention_layernorm.weight', 'layers.0.self_attn.k_proj.weight', 'layers.0.self_attn.o_proj.weight', 'layers.0.self_attn.q_proj.weight', 'layers.0.self_attn.v_proj.weight', 'layers.1.input_layernorm.weight', 'layers.1.mlp.down_proj.weight', 'layers.1.mlp.gate_proj.weight', 'layers.1.mlp.up_proj.weight', 'layers.1.post_attention_layernorm.weight', 'layers.1.self_attn.k_proj.weight', 'layers.1.self_attn.o_proj.weight', 'layers.1.self_attn.q_proj.weight', 'layers.1.self_attn.v_proj.weight', 'layers.10.input_layernorm.weight', 'layers.10.mlp.down_proj.weight', 'layers.10.mlp.gate_proj.weight', 'layers.10.mlp.up_proj.weight', 'layers.10.post_attention_layernorm.weight', 'layers.10.self_attn.k_proj.weight', 'layers.10.self_attn.o_proj.weight', 'layers.10.self_attn.q_proj.weight', 'layers.10.self_attn.v_proj.weight', 'layers.11.input_layernorm.weight', 'layers.11.mlp.down_proj.weight', 'layers.11.mlp.gate_proj.weight', 'layers.11.mlp.up_proj.weight', 'layers.11.post_attention_layernorm.weight', 'layers.11.self_attn.k_proj.weight', 'layers.11.self_attn.o_proj.weight', 'layers.11.self_attn.q_proj.weight', 'layers.11.self_attn.v_proj.weight', 'layers.12.input_layernorm.weight', 'layers.12.mlp.down_proj.weight', 'layers.12.mlp.gate_proj.weight', 'layers.12.mlp.up_proj.weight', 'layers.12.post_attention_layernorm.weight', 'layers.12.self_attn.k_proj.weight', 'layers.12.self_attn.o_proj.weight', 'layers.12.self_attn.q_proj.weight', 'layers.12.self_attn.v_proj.weight', 'layers.13.input_layernorm.weight', 'layers.13.mlp.down_proj.weight', 'layers.13.mlp.gate_proj.weight', 'layers.13.mlp.up_proj.weight', 'layers.13.post_attention_layernorm.weight', 'layers.13.self_attn.k_proj.weight', 'layers.13.self_attn.o_proj.weight', 'layers.13.self_attn.q_proj.weight', 'layers.13.self_attn.v_proj.weight', 'layers.14.input_layernorm.weight', 'layers.14.mlp.down_proj.weight', 'layers.14.mlp.gate_proj.weight', 'layers.14.mlp.up_proj.weight', 'layers.14.post_attention_layernorm.weight', 'layers.14.self_attn.k_proj.weight', 'layers.14.self_attn.o_proj.weight', 'layers.14.self_attn.q_proj.weight', 'layers.14.self_attn.v_proj.weight', 'layers.15.input_layernorm.weight', 'layers.15.mlp.down_proj.weight', 'layers.15.mlp.gate_proj.weight', 'layers.15.mlp.up_proj.weight', 'layers.15.post_attention_layernorm.weight', 'layers.15.self_attn.k_proj.weight', 'layers.15.self_attn.o_proj.weight', 'layers.15.self_attn.q_proj.weight', 'layers.15.self_attn.v_proj.weight', 'layers.16.input_layernorm.weight', 'layers.16.mlp.down_proj.weight', 'layers.16.mlp.gate_proj.weight', 'layers.16.mlp.up_proj.weight', 'layers.16.post_attention_layernorm.weight', 'layers.16.self_attn.k_proj.weight', 'layers.16.self_attn.o_proj.weight', 'layers.16.self_attn.q_proj.weight', 'layers.16.self_attn.v_proj.weight', 'layers.17.input_layernorm.weight', 'layers.17.mlp.down_proj.weight', 'layers.17.mlp.gate_proj.weight', 'layers.17.mlp.up_proj.weight', 'layers.17.post_attention_layernorm.weight', 'layers.17.self_attn.k_proj.weight', 'layers.17.self_attn.o_proj.weight', 'layers.17.self_attn.q_proj.weight', 'layers.17.self_attn.v_proj.weight', 'layers.18.input_layernorm.weight', 'layers.18.mlp.down_proj.weight', 'layers.18.mlp.gate_proj.weight', 'layers.18.mlp.up_proj.weight', 'layers.18.post_attention_layernorm.weight', 'layers.18.self_attn.k_proj.weight', 'layers.18.self_attn.o_proj.weight', 'layers.18.self_attn.q_proj.weight', 'layers.18.self_attn.v_proj.weight', 'layers.19.input_layernorm.weight', 'layers.19.mlp.down_proj.weight', 'layers.19.mlp.gate_proj.weight', 'layers.19.mlp.up_proj.weight', 'layers.19.post_attention_layernorm.weight', 'layers.19.self_attn.k_proj.weight', 'layers.19.self_attn.o_proj.weight', 'layers.19.self_attn.q_proj.weight', 'layers.19.self_attn.v_proj.weight', 'layers.2.input_layernorm.weight', 'layers.2.mlp.down_proj.weight', 'layers.2.mlp.gate_proj.weight', 'layers.2.mlp.up_proj.weight', 'layers.2.post_attention_layernorm.weight', 'layers.2.self_attn.k_proj.weight', 'layers.2.self_attn.o_proj.weight', 'layers.2.self_attn.q_proj.weight', 'layers.2.self_attn.v_proj.weight', 'layers.20.input_layernorm.weight', 'layers.20.mlp.down_proj.weight', 'layers.20.mlp.gate_proj.weight', 'layers.20.mlp.up_proj.weight', 'layers.20.post_attention_layernorm.weight', 'layers.20.self_attn.k_proj.weight', 'layers.20.self_attn.o_proj.weight', 'layers.20.self_attn.q_proj.weight', 'layers.20.self_attn.v_proj.weight', 'layers.21.input_layernorm.weight', 'layers.21.mlp.down_proj.weight', 'layers.21.mlp.gate_proj.weight', 'layers.21.mlp.up_proj.weight', 'layers.21.post_attention_layernorm.weight', 'layers.21.self_attn.k_proj.weight', 'layers.21.self_attn.o_proj.weight', 'layers.21.self_attn.q_proj.weight', 'layers.21.self_attn.v_proj.weight', 'layers.3.input_layernorm.weight', 'layers.3.mlp.down_proj.weight', 'layers.3.mlp.gate_proj.weight', 'layers.3.mlp.up_proj.weight', 'layers.3.post_attention_layernorm.weight', 'layers.3.self_attn.k_proj.weight', 'layers.3.self_attn.o_proj.weight', 'layers.3.self_attn.q_proj.weight', 'layers.3.self_attn.v_proj.weight', 'layers.4.input_layernorm.weight', 'layers.4.mlp.down_proj.weight', 'layers.4.mlp.gate_proj.weight', 'layers.4.mlp.up_proj.weight', 'layers.4.post_attention_layernorm.weight', 'layers.4.self_attn.k_proj.weight', 'layers.4.self_attn.o_proj.weight', 'layers.4.self_attn.q_proj.weight', 'layers.4.self_attn.v_proj.weight', 'layers.5.input_layernorm.weight', 'layers.5.mlp.down_proj.weight', 'layers.5.mlp.gate_proj.weight', 'layers.5.mlp.up_proj.weight', 'layers.5.post_attention_layernorm.weight', 'layers.5.self_attn.k_proj.weight', 'layers.5.self_attn.o_proj.weight', 'layers.5.self_attn.q_proj.weight', 'layers.5.self_attn.v_proj.weight', 'layers.6.input_layernorm.weight', 'layers.6.mlp.down_proj.weight', 'layers.6.mlp.gate_proj.weight', 'layers.6.mlp.up_proj.weight', 'layers.6.post_attention_layernorm.weight', 'layers.6.self_attn.k_proj.weight', 'layers.6.self_attn.o_proj.weight', 'layers.6.self_attn.q_proj.weight', 'layers.6.self_attn.v_proj.weight', 'layers.7.input_layernorm.weight', 'layers.7.mlp.down_proj.weight', 'layers.7.mlp.gate_proj.weight', 'layers.7.mlp.up_proj.weight', 'layers.7.post_attention_layernorm.weight', 'layers.7.self_attn.k_proj.weight', 'layers.7.self_attn.o_proj.weight', 'layers.7.self_attn.q_proj.weight', 'layers.7.self_attn.v_proj.weight', 'layers.8.input_layernorm.weight', 'layers.8.mlp.down_proj.weight', 'layers.8.mlp.gate_proj.weight', 'layers.8.mlp.up_proj.weight', 'layers.8.post_attention_layernorm.weight', 'layers.8.self_attn.k_proj.weight', 'layers.8.self_attn.o_proj.weight', 'layers.8.self_attn.q_proj.weight', 'layers.8.self_attn.v_proj.weight', 'layers.9.input_layernorm.weight', 'layers.9.mlp.down_proj.weight', 'layers.9.mlp.gate_proj.weight', 'layers.9.mlp.up_proj.weight', 'layers.9.post_attention_layernorm.weight', 'layers.9.self_attn.k_proj.weight', 'layers.9.self_attn.o_proj.weight', 'layers.9.self_attn.q_proj.weight', 'layers.9.self_attn.v_proj.weight', 'lm_head.weight', 'norm.weight']\n",
            "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "['### Instruction:\\nContinue the Fibonacci sequence.\\n\\n### Input:\\n\\n1, 1, 2, 3, 5, 8\\n\\n### Response:\\n']\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "if False:\n",
        "    from unsloth import FastLanguageModel\n",
        "    model, tokenizer = FastLanguageModel.from_pretrained(\n",
        "        model_name = \"lora_model\", # YOUR MODEL YOU USED FOR TRAINING\n",
        "        max_seq_length = max_seq_length,\n",
        "        dtype = dtype,\n",
        "        load_in_4bit = load_in_4bit,\n",
        "    )\n",
        "    FastLanguageModel.for_inference(model) # Enable native 2x faster inference\n",
        "\n",
        "# alpaca_prompt = You MUST copy from above!\n",
        "\n",
        "inputs = tokenizer(\n",
        "[\n",
        "    alpaca_prompt.format(\n",
        "        \"which country  Haris Hota live\", # instruction\n",
        "        \"Haris Hota\", # input\n",
        "        \"\", # output - leave this blank for generation!\n",
        "    )\n",
        "], return_tensors = \"pt\").to(\"cuda\")\n",
        "\n",
        "from transformers import TextStreamer\n",
        "text_streamer = TextStreamer(tokenizer)\n",
        "_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 64)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "IuUufGQz5BBR",
        "outputId": "07f59e9c-a09e-484c-df1f-406f6e75e36b"
      },
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<s> ### Instruction:\n",
            "which country  Haris Hota live\n",
            "\n",
            "### Input:\n",
            "\n",
            "Haris Hota\n",
            "\n",
            "### Response:\n",
            "<unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk><unk>\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "aTqhZ5y1533Y"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}