Add files

.pre-commit-config.yaml

@@ -0,0 +1,33 @@
+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: v0.9.6
+    hooks:
+      - id: ruff
+        args: ["--fix"]
+      - id: ruff-format
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.15.0
+    hooks:
+      - id: mypy
+        args: ["--ignore-missing-imports"]
+        additional_dependencies:
+          [
+            "types-python-slugify",
+            "types-pytz",
+            "types-PyYAML",
+            "types-requests",
+          ]

.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 +1,17 @@
+{
+    "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.formatOnSave.enabled": true
+}

README.md

@@ -1,7 +1,7 @@
 ---
 title: Qwen2.5 Bakeneko 32b Instruct Awq
 emoji: ⚡
-colorFrom: green
+colorFrom: red
 colorTo: purple
 sdk: gradio
 sdk_version: 5.16.0

app.py

@@ -0,0 +1,126 @@
+#!/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 = "# rinna/qwen2.5-bakeneko-32b-instruct-awq"
+
+MAX_MAX_NEW_TOKENS = 2048
+DEFAULT_MAX_NEW_TOKENS = 1024
+MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
+
+device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+
+model_id = "rinna/qwen2.5-bakeneko-32b-instruct-awq"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="auto",
+    torch_dtype=torch.bfloat16,
+)
+model.eval()
+
+
+@spaces.GPU(duration=120)
+def generate(
+    message: str,
+    chat_history: list[dict],
+    system_prompt: str = "",
+    max_new_tokens: int = 1024,
+    temperature: float = 0.7,
+    top_p: float = 0.8,
+    top_k: int = 20,
+    repetition_penalty: float = 1.05,
+) -> Iterator[str]:
+    messages = []
+    if system_prompt:
+        messages.append({"role": "system", "content": system_prompt})
+    messages.extend(chat_history.copy())
+    messages.append({"role": "user", "content": message})
+
+    input_ids = tokenizer.apply_chat_template(messages, add_generation_prompt=True, 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=30.0, 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,
+    )
+    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=[
+        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=4.0,
+            step=0.1,
+            value=0.7,
+        ),
+        gr.Slider(
+            label="Top-p (nucleus sampling)",
+            minimum=0.05,
+            maximum=1.0,
+            step=0.05,
+            value=0.8,
+        ),
+        gr.Slider(
+            label="Top-k",
+            minimum=1,
+            maximum=1000,
+            step=1,
+            value=20,
+        ),
+        gr.Slider(
+            label="Repetition penalty",
+            minimum=1.0,
+            maximum=2.0,
+            step=0.05,
+            value=1.05,
+        ),
+    ],
+    stop_btn=None,
+    examples=[
+        ["ゲーム・小説・アニメに登場するアイテムボックスの特徴と、その原理を詳細に推測してください。"],
+    ],
+    cache_examples=False,
+    type="messages",
+    description=DESCRIPTION,
+    css_paths="style.css",
+    fill_height=True,
+)
+
+if __name__ == "__main__":
+    demo.launch()

pyproject.toml

@@ -0,0 +1,62 @@
+[project]
+name = "qwen2-5-bakeneko-32b-instruct-awq"
+version = "0.1.0"
+description = ""
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "accelerate>=1.3.0",
+    "autoawq>=0.2.7.post3",
+    "gradio>=5.16.0",
+    "hf-transfer>=0.1.9",
+    "spaces>=0.32.0",
+    "torch==2.4.0",
+    "transformers>=4.48.3",
+]
+
+[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.lint.pydocstyle]
+convention = "google"
+
+[tool.ruff.lint.per-file-ignores]
+"*.ipynb" = ["T201"]
+
+[tool.ruff.format]
+docstring-code-format = true
+
+[dependency-groups]
+dev = [
+    "setuptools>=75.8.0",
+]

requirements.txt

@@ -0,0 +1,305 @@
+# This file was autogenerated by uv via the following command:
+#    uv pip compile pyproject.toml -o requirements.txt
+accelerate==1.3.0
+    # via
+    #   qwen2-5-bakeneko-32b-instruct-awq (pyproject.toml)
+    #   autoawq
+aiofiles==23.2.1
+    # via gradio
+aiohappyeyeballs==2.4.6
+    # via aiohttp
+aiohttp==3.11.12
+    # via
+    #   datasets
+    #   fsspec
+aiosignal==1.3.2
+    # via aiohttp
+annotated-types==0.7.0
+    # via pydantic
+anyio==4.8.0
+    # via
+    #   gradio
+    #   httpx
+    #   starlette
+async-timeout==5.0.1
+    # via aiohttp
+attrs==25.1.0
+    # via aiohttp
+autoawq==0.2.7.post3
+    # via qwen2-5-bakeneko-32b-instruct-awq (pyproject.toml)
+certifi==2025.1.31
+    # via
+    #   httpcore
+    #   httpx
+    #   requests
+charset-normalizer==3.4.1
+    # via requests
+click==8.1.8
+    # via
+    #   typer
+    #   uvicorn
+datasets==3.3.0
+    # via autoawq
+dill==0.3.8
+    # via
+    #   datasets
+    #   multiprocess
+exceptiongroup==1.2.2
+    # via anyio
+fastapi==0.115.8
+    # via gradio
+ffmpy==0.5.0
+    # via gradio
+filelock==3.17.0
+    # via
+    #   datasets
+    #   huggingface-hub
+    #   torch
+    #   transformers
+    #   triton
+frozenlist==1.5.0
+    # via
+    #   aiohttp
+    #   aiosignal
+fsspec==2024.12.0
+    # via
+    #   datasets
+    #   gradio-client
+    #   huggingface-hub
+    #   torch
+gradio==5.16.0
+    # via
+    #   qwen2-5-bakeneko-32b-instruct-awq (pyproject.toml)
+    #   spaces
+gradio-client==1.7.0
+    # via gradio
+h11==0.14.0
+    # via
+    #   httpcore
+    #   uvicorn
+hf-transfer==0.1.9
+    # via qwen2-5-bakeneko-32b-instruct-awq (pyproject.toml)
+httpcore==1.0.7
+    # via httpx
+httpx==0.28.1
+    # via
+    #   gradio
+    #   gradio-client
+    #   safehttpx
+    #   spaces
+huggingface-hub==0.28.1
+    # via
+    #   accelerate
+    #   autoawq
+    #   datasets
+    #   gradio
+    #   gradio-client
+    #   tokenizers
+    #   transformers
+idna==3.10
+    # via
+    #   anyio
+    #   httpx
+    #   requests
+    #   yarl
+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
+multidict==6.1.0
+    # via
+    #   aiohttp
+    #   yarl
+multiprocess==0.70.16
+    # via datasets
+networkx==3.4.2
+    # via torch
+numpy==2.2.3
+    # via
+    #   accelerate
+    #   datasets
+    #   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==12.8.61
+    # via
+    #   nvidia-cusolver-cu12
+    #   nvidia-cusparse-cu12
+nvidia-nvtx-cu12==12.1.105
+    # via torch
+orjson==3.10.15
+    # via gradio
+packaging==24.2
+    # via
+    #   accelerate
+    #   datasets
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   spaces
+    #   transformers
+pandas==2.2.3
+    # via
+    #   datasets
+    #   gradio
+pillow==11.1.0
+    # via gradio
+propcache==0.2.1
+    # via
+    #   aiohttp
+    #   yarl
+psutil==5.9.8
+    # via
+    #   accelerate
+    #   spaces
+pyarrow==19.0.0
+    # via datasets
+pydantic==2.10.6
+    # via
+    #   fastapi
+    #   gradio
+    #   spaces
+pydantic-core==2.27.2
+    # via pydantic
+pydub==0.25.1
+    # via gradio
+pygments==2.19.1
+    # via rich
+python-dateutil==2.9.0.post0
+    # via pandas
+python-multipart==0.0.20
+    # via gradio
+pytz==2025.1
+    # via pandas
+pyyaml==6.0.2
+    # via
+    #   accelerate
+    #   datasets
+    #   gradio
+    #   huggingface-hub
+    #   transformers
+regex==2024.11.6
+    # via transformers
+requests==2.32.3
+    # via
+    #   datasets
+    #   huggingface-hub
+    #   spaces
+    #   transformers
+rich==13.9.4
+    # via typer
+ruff==0.9.6
+    # via gradio
+safehttpx==0.1.6
+    # via gradio
+safetensors==0.5.2
+    # 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==0.32.0
+    # via qwen2-5-bakeneko-32b-instruct-awq (pyproject.toml)
+starlette==0.45.3
+    # via
+    #   fastapi
+    #   gradio
+sympy==1.13.3
+    # via torch
+tokenizers==0.21.0
+    # via
+    #   autoawq
+    #   transformers
+tomlkit==0.13.2
+    # via gradio
+torch==2.4.0
+    # via
+    #   qwen2-5-bakeneko-32b-instruct-awq (pyproject.toml)
+    #   accelerate
+    #   autoawq
+tqdm==4.67.1
+    # via
+    #   datasets
+    #   huggingface-hub
+    #   transformers
+transformers==4.48.3
+    # via
+    #   qwen2-5-bakeneko-32b-instruct-awq (pyproject.toml)
+    #   autoawq
+triton==3.0.0
+    # via
+    #   autoawq
+    #   torch
+typer==0.15.1
+    # via gradio
+typing-extensions==4.12.2
+    # via
+    #   anyio
+    #   autoawq
+    #   fastapi
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   multidict
+    #   pydantic
+    #   pydantic-core
+    #   rich
+    #   spaces
+    #   torch
+    #   typer
+    #   uvicorn
+tzdata==2025.1
+    # via pandas
+urllib3==2.3.0
+    # via requests
+uvicorn==0.34.0
+    # via gradio
+websockets==14.2
+    # via gradio-client
+xxhash==3.5.0
+    # via datasets
+yarl==1.18.3
+    # via aiohttp
+zstandard==0.23.0
+    # via autoawq

style.css

@@ -0,0 +1,4 @@
+h1 {
+  text-align: center;
+  display: block;
+}