Add files

.pre-commit-config.yaml

@@ -0,0 +1,51 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: check-executables-have-shebangs
+      - id: check-json
+      - id: check-merge-conflict
+      - id: check-shebang-scripts-are-executable
+      - id: check-toml
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: mixed-line-ending
+        args: ["--fix=lf"]
+      - id: requirements-txt-fixer
+      - id: trailing-whitespace
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.8.4
+    hooks:
+      - id: ruff
+        args: ["--fix"]
+      - id: ruff-format
+        args: ["--line-length", "119"]
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.14.0
+    hooks:
+      - id: mypy
+        args: ["--ignore-missing-imports"]
+        additional_dependencies:
+          [
+            "types-python-slugify",
+            "types-requests",
+            "types-PyYAML",
+            "types-pytz",
+          ]
+  - repo: https://github.com/kynan/nbstripout
+    rev: 0.8.1
+    hooks:
+      - id: nbstripout
+        args:
+          [
+            "--extra-keys",
+            "metadata.interpreter metadata.kernelspec cell.metadata.pycharm",
+          ]
+  - repo: https://github.com/nbQA-dev/nbQA
+    rev: 1.9.1
+    hooks:
+      - id: nbqa-black
+      - id: nbqa-pyupgrade
+        args: ["--py37-plus"]
+      - id: nbqa-isort
+        args: ["--float-to-top"]

.python-version

@@ -0,0 +1 @@
+3.10

.vscode/extensions.json

@@ -0,0 +1,8 @@
+{
+    "recommendations": [
+        "ms-python.python",
+        "charliermarsh.ruff",
+        "streetsidesoftware.code-spell-checker",
+        "tamasfe.even-better-toml"
+    ]
+}

.vscode/settings.json

@@ -0,0 +1,21 @@
+{
+    "editor.formatOnSave": true,
+    "files.insertFinalNewline": false,
+    "[python]": {
+        "editor.defaultFormatter": "charliermarsh.ruff",
+        "editor.formatOnType": true,
+        "editor.codeActionsOnSave": {
+            "source.fixAll.ruff": "explicit",
+            "source.organizeImports": "explicit"
+        }
+    },
+    "[jupyter]": {
+        "files.insertFinalNewline": false
+    },
+    "notebook.output.scrolling": true,
+    "notebook.formatOnCellExecution": true,
+    "notebook.formatOnSave.enabled": true,
+    "notebook.codeActionsOnSave": {
+        "source.organizeImports": "explicit"
+    }
+}

README.md

@@ -1,8 +1,8 @@
 ---
 title: Llama 3.1 Swallow 8B Instruct V0.3
-emoji: 🌍
-colorFrom: blue
-colorTo: red
+emoji: ⚡
+colorFrom: red
+colorTo: purple
 sdk: gradio
 sdk_version: 5.9.1
 app_file: app.py

app.py

@@ -0,0 +1,128 @@
+#!/usr/bin/env python
+
+import os
+from collections.abc import Iterator
+from threading import Thread
+
+import gradio as gr
+import spaces
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
+
+DESCRIPTION = "# Llama 3.1 Swallow 8B Instruct V0.3"
+
+if not torch.cuda.is_available():
+    DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
+
+MAX_MAX_NEW_TOKENS = 2048
+DEFAULT_MAX_NEW_TOKENS = 1024
+MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
+
+if torch.cuda.is_available():
+    model_id = "tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.3"
+    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
+    model.eval()
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+
+@spaces.GPU
+@torch.inference_mode()
+def generate(
+    message: str,
+    chat_history: list[dict],
+    system_prompt: str = "",
+    max_new_tokens: int = 1024,
+    temperature: float = 0.6,
+    top_p: float = 0.9,
+    top_k: int = 50,
+    repetition_penalty: float = 1.0,
+) -> Iterator[str]:
+    conversation = []
+    if system_prompt:
+        conversation.append({"role": "system", "content": system_prompt})
+    conversation += chat_history
+    conversation.append({"role": "user", "content": message})
+
+    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
+    if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
+        input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
+        gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
+    input_ids = input_ids.to(model.device)
+
+    streamer = TextIteratorStreamer(tokenizer, timeout=20.0, skip_prompt=True, skip_special_tokens=True)
+    generate_kwargs = dict(
+        {"input_ids": input_ids},
+        streamer=streamer,
+        max_new_tokens=max_new_tokens,
+        do_sample=True,
+        top_p=top_p,
+        top_k=top_k,
+        temperature=temperature,
+        num_beams=1,
+        repetition_penalty=repetition_penalty,
+        pad_token_id=tokenizer.eos_token_id,
+    )
+    t = Thread(target=model.generate, kwargs=generate_kwargs)
+    t.start()
+
+    outputs = []
+    for text in streamer:
+        outputs.append(text)
+        yield "".join(outputs)
+
+
+demo = gr.ChatInterface(
+    fn=generate,
+    additional_inputs_accordion=gr.Accordion(label="詳細設定", open=False),
+    additional_inputs=[
+        gr.Textbox(label="System prompt", value="あなたは誠実で優秀な日本人のアシスタントです。"),
+        gr.Slider(
+            label="Max new tokens",
+            minimum=1,
+            maximum=MAX_MAX_NEW_TOKENS,
+            step=1,
+            value=DEFAULT_MAX_NEW_TOKENS,
+        ),
+        gr.Slider(
+            label="Temperature",
+            minimum=0.1,
+            maximum=2.0,
+            step=0.1,
+            value=0.6,
+        ),
+        gr.Slider(
+            label="Top-p (nucleus sampling)",
+            minimum=0.05,
+            maximum=1.0,
+            step=0.05,
+            value=0.9,
+        ),
+        gr.Slider(
+            label="Top-k",
+            minimum=1,
+            maximum=1000,
+            step=1,
+            value=50,
+        ),
+        gr.Slider(
+            label="Repetition penalty",
+            minimum=1.0,
+            maximum=2.0,
+            step=0.05,
+            value=1.0,
+        ),
+    ],
+    stop_btn=None,
+    examples=[
+        [
+            "東京の紅葉した公園で、東京タワーと高層ビルを背景に、空を舞うツバメと草地に佇むラマが出会う温かな物語を書いてください。"
+        ],
+    ],
+    type="messages",
+    description=DESCRIPTION,
+    css_paths="style.css",
+    fill_height=True,
+)
+
+if __name__ == "__main__":
+    demo.launch()

pyproject.toml

@@ -0,0 +1,49 @@
+[project]
+name = "llama-3-1-swallow-8b-instruct-v0-3"
+version = "0.1.0"
+description = ""
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "accelerate>=1.2.1",
+    "gradio>=5.9.1",
+    "spaces>=0.31.1",
+    "torch==2.4.0",
+    "transformers>=4.47.1",
+]
+
+[tool.ruff]
+line-length = 119
+
+[tool.ruff.lint]
+select = ["ALL"]
+ignore = [
+    "COM812", # missing-trailing-comma
+    "D203",   # one-blank-line-before-class
+    "D213",   # multi-line-summary-second-line
+    "E501",   # line-too-long
+    "SIM117", # multiple-with-statements
+]
+extend-ignore = [
+    "D100",    # undocumented-public-module
+    "D101",    # undocumented-public-class
+    "D102",    # undocumented-public-method
+    "D103",    # undocumented-public-function
+    "D104",    # undocumented-public-package
+    "D105",    # undocumented-magic-method
+    "D107",    # undocumented-public-init
+    "EM101",   # raw-string-in-exception
+    "FBT001",  # boolean-type-hint-positional-argument
+    "FBT002",  # boolean-default-value-positional-argument
+    "PD901",   # pandas-df-variable-name
+    "PGH003",  # blanket-type-ignore
+    "PLR0913", # too-many-arguments
+    "PLR0915", # too-many-statements
+    "TRY003",  # raise-vanilla-args
+]
+unfixable = [
+    "F401", # unused-import
+]
+
+[tool.ruff.format]
+docstring-code-format = true

requirements.txt

@@ -0,0 +1,238 @@
+# This file was autogenerated by uv via the following command:
+#    uv pip compile pyproject.toml -o requirements.txt
+accelerate==1.2.1
+    # via llama-3-1-swallow-8b-instruct-v0-3 (pyproject.toml)
+aiofiles==23.2.1
+    # via gradio
+annotated-types==0.7.0
+    # via pydantic
+anyio==4.7.0
+    # via
+    #   gradio
+    #   httpx
+    #   starlette
+certifi==2024.12.14
+    # via
+    #   httpcore
+    #   httpx
+    #   requests
+charset-normalizer==3.4.1
+    # via requests
+click==8.1.8
+    # via
+    #   typer
+    #   uvicorn
+exceptiongroup==1.2.2
+    # via anyio
+fastapi==0.115.6
+    # via gradio
+ffmpy==0.5.0
+    # via gradio
+filelock==3.16.1
+    # via
+    #   huggingface-hub
+    #   torch
+    #   transformers
+    #   triton
+fsspec==2024.12.0
+    # via
+    #   gradio-client
+    #   huggingface-hub
+    #   torch
+gradio==5.9.1
+    # via
+    #   llama-3-1-swallow-8b-instruct-v0-3 (pyproject.toml)
+    #   spaces
+gradio-client==1.5.2
+    # via gradio
+h11==0.14.0
+    # via
+    #   httpcore
+    #   uvicorn
+httpcore==1.0.7
+    # via httpx
+httpx==0.28.1
+    # via
+    #   gradio
+    #   gradio-client
+    #   safehttpx
+    #   spaces
+huggingface-hub==0.27.0
+    # via
+    #   accelerate
+    #   gradio
+    #   gradio-client
+    #   tokenizers
+    #   transformers
+idna==3.10
+    # via
+    #   anyio
+    #   httpx
+    #   requests
+jinja2==3.1.5
+    # via
+    #   gradio
+    #   torch
+markdown-it-py==3.0.0
+    # via rich
+markupsafe==2.1.5
+    # via
+    #   gradio
+    #   jinja2
+mdurl==0.1.2
+    # via markdown-it-py
+mpmath==1.3.0
+    # via sympy
+networkx==3.4.2
+    # via torch
+numpy==2.2.1
+    # via
+    #   accelerate
+    #   gradio
+    #   pandas
+    #   transformers
+nvidia-cublas-cu12==12.1.3.1
+    # via
+    #   nvidia-cudnn-cu12
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-cuda-cupti-cu12==12.1.105
+    # via torch
+nvidia-cuda-nvrtc-cu12==12.1.105
+    # via torch
+nvidia-cuda-runtime-cu12==12.1.105
+    # via torch
+nvidia-cudnn-cu12==9.1.0.70
+    # via torch
+nvidia-cufft-cu12==11.0.2.54
+    # via torch
+nvidia-curand-cu12==10.3.2.106
+    # via torch
+nvidia-cusolver-cu12==11.4.5.107
+    # via torch
+nvidia-cusparse-cu12==12.1.0.106
+    # via
+    #   nvidia-cusolver-cu12
+    #   torch
+nvidia-nccl-cu12==2.20.5
+    # via torch
+nvidia-nvjitlink-cu12==12.6.85
+    # via
+    #   nvidia-cusolver-cu12
+    #   nvidia-cusparse-cu12
+nvidia-nvtx-cu12==12.1.105
+    # via torch
+orjson==3.10.13
+    # via gradio
+packaging==24.2
+    # via
+    #   accelerate
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   spaces
+    #   transformers
+pandas==2.2.3
+    # via gradio
+pillow==11.1.0
+    # via gradio
+psutil==5.9.8
+    # via
+    #   accelerate
+    #   spaces
+pydantic==2.10.4
+    # via
+    #   fastapi
+    #   gradio
+    #   spaces
+pydantic-core==2.27.2
+    # via pydantic
+pydub==0.25.1
+    # via gradio
+pygments==2.18.0
+    # via rich
+python-dateutil==2.9.0.post0
+    # via pandas
+python-multipart==0.0.20
+    # via gradio
+pytz==2024.2
+    # via pandas
+pyyaml==6.0.2
+    # via
+    #   accelerate
+    #   gradio
+    #   huggingface-hub
+    #   transformers
+regex==2024.11.6
+    # via transformers
+requests==2.32.3
+    # via
+    #   huggingface-hub
+    #   spaces
+    #   transformers
+rich==13.9.4
+    # via typer
+ruff==0.8.5
+    # via gradio
+safehttpx==0.1.6
+    # via gradio
+safetensors==0.4.5
+    # via
+    #   accelerate
+    #   transformers
+semantic-version==2.10.0
+    # via gradio
+shellingham==1.5.4
+    # via typer
+six==1.17.0
+    # via python-dateutil
+sniffio==1.3.1
+    # via anyio
+spaces==0.31.1
+    # via llama-3-1-swallow-8b-instruct-v0-3 (pyproject.toml)
+starlette==0.41.3
+    # via
+    #   fastapi
+    #   gradio
+sympy==1.13.3
+    # via torch
+tokenizers==0.21.0
+    # via transformers
+tomlkit==0.13.2
+    # via gradio
+torch==2.4.0
+    # via
+    #   llama-3-1-swallow-8b-instruct-v0-3 (pyproject.toml)
+    #   accelerate
+tqdm==4.67.1
+    # via
+    #   huggingface-hub
+    #   transformers
+transformers==4.47.1
+    # via llama-3-1-swallow-8b-instruct-v0-3 (pyproject.toml)
+triton==3.0.0
+    # via torch
+typer==0.15.1
+    # via gradio
+typing-extensions==4.12.2
+    # via
+    #   anyio
+    #   fastapi
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   pydantic
+    #   pydantic-core
+    #   rich
+    #   spaces
+    #   torch
+    #   typer
+    #   uvicorn
+tzdata==2024.2
+    # via pandas
+urllib3==2.3.0
+    # via requests
+uvicorn==0.34.0
+    # via gradio
+websockets==14.1
+    # via gradio-client

style.css

@@ -0,0 +1,11 @@
+h1 {
+  text-align: center;
+  display: block;
+}
+
+#duplicate-button {
+  margin: auto;
+  color: white;
+  background: #1565c0;
+  border-radius: 100vh;
+}