Update

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
+    rev: v5.0.0
     hooks:
       - id: check-executables-have-shebangs
       - id: check-json
@@ -18,13 +18,15 @@ repos:
     hooks:
       - id: docformatter
         args: ["--in-place"]
-  - repo: https://github.com/pycqa/isort
-    rev: 5.13.2
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.8.4
     hooks:
-      - id: isort
-        args: ["--profile", "black"]
+      - id: ruff
+        args: ["--fix"]
+      - id: ruff-format
+        args: ["--line-length", "119"]
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.9.0
+    rev: v1.14.0
     hooks:
       - id: mypy
         args: ["--ignore-missing-imports"]
@@ -35,14 +37,8 @@ repos:
             "types-PyYAML",
             "types-pytz",
           ]
-  - repo: https://github.com/psf/black
-    rev: 24.4.0
-    hooks:
-      - id: black
-        language_version: python3.10
-        args: ["--line-length", "119"]
   - repo: https://github.com/kynan/nbstripout
-    rev: 0.7.1
+    rev: 0.8.1
     hooks:
       - id: nbstripout
         args:
@@ -51,7 +47,7 @@ repos:
             "metadata.interpreter metadata.kernelspec cell.metadata.pycharm",
           ]
   - repo: https://github.com/nbQA-dev/nbQA
-    rev: 1.8.5
+    rev: 1.9.1
     hooks:
       - id: nbqa-black
       - id: nbqa-pyupgrade

.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

@@ -2,29 +2,20 @@
     "editor.formatOnSave": true,
     "files.insertFinalNewline": false,
     "[python]": {
-        "editor.defaultFormatter": "ms-python.black-formatter",
+        "editor.defaultFormatter": "charliermarsh.ruff",
         "editor.formatOnType": true,
         "editor.codeActionsOnSave": {
+            "source.fixAll.ruff": "explicit",
             "source.organizeImports": "explicit"
         }
     },
     "[jupyter]": {
         "files.insertFinalNewline": false
     },
-    "black-formatter.args": [
-        "--line-length=119"
-    ],
-    "isort.args": ["--profile", "black"],
-    "flake8.args": [
-        "--max-line-length=119"
-    ],
-    "ruff.lint.args": [
-        "--line-length=119"
-    ],
     "notebook.output.scrolling": true,
     "notebook.formatOnCellExecution": true,
     "notebook.formatOnSave.enabled": true,
-        "notebook.codeActionsOnSave": {
-            "source.organizeImports": "explicit"
-        }
+    "notebook.codeActionsOnSave": {
+        "source.organizeImports": "explicit"
+    }
 }

README.md

@@ -4,7 +4,7 @@ emoji: 🐨
 colorFrom: pink
 colorTo: blue
 sdk: gradio
-sdk_version: 4.36.1
+sdk_version: 5.9.1
 app_file: app.py
 pinned: false
 license: mit

app.py

@@ -1,15 +1,15 @@
 #!/usr/bin/env python
 
 import os
+from collections.abc import Iterator
 from threading import Thread
-from typing import Iterator
 
 import gradio as gr
 import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 
-DESCRIPTION = "# Mistral-7B v0.2"
+DESCRIPTION = "# Mistral-7B v0.3"
 
 if not torch.cuda.is_available():
     DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
@@ -19,7 +19,7 @@ DEFAULT_MAX_NEW_TOKENS = 1024
 MAX_INPUT_TOKEN_LENGTH = int(os.getenv("MAX_INPUT_TOKEN_LENGTH", "4096"))
 
 if torch.cuda.is_available():
-    model_id = "mistralai/Mistral-7B-Instruct-v0.2"
+    model_id = "mistralai/Mistral-7B-Instruct-v0.3"
     model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")
     tokenizer = AutoTokenizer.from_pretrained(model_id)
 
@@ -27,17 +27,14 @@ if torch.cuda.is_available():
 @spaces.GPU
 def generate(
     message: str,
-    chat_history: list[tuple[str, str]],
+    chat_history: list[dict],
     max_new_tokens: int = 1024,
     temperature: float = 0.6,
     top_p: float = 0.9,
     top_k: int = 50,
     repetition_penalty: float = 1.2,
 ) -> Iterator[str]:
-    conversation = []
-    for user, assistant in chat_history:
-        conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
-    conversation.append({"role": "user", "content": message})
+    conversation = [*chat_history, {"role": "user", "content": message}]
 
     input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
     if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
@@ -66,7 +63,7 @@ def generate(
         yield "".join(outputs)
 
 
-chat_interface = gr.ChatInterface(
+demo = gr.ChatInterface(
     fn=generate,
     additional_inputs=[
         gr.Slider(
@@ -113,16 +110,10 @@ chat_interface = gr.ChatInterface(
         ["How many hours does it take a man to eat a Helicopter?"],
         ["Write a 100-word article on 'Benefits of Open-Source in AI research'"],
     ],
+    type="messages",
+    description=DESCRIPTION,
+    css_paths="style.css",
 )
 
-with gr.Blocks(css="style.css") as demo:
-    gr.Markdown(DESCRIPTION)
-    gr.DuplicateButton(
-        value="Duplicate Space for private use",
-        elem_id="duplicate-button",
-        visible=os.getenv("SHOW_DUPLICATE_BUTTON") == "1",
-    )
-    chat_interface.render()
-
 if __name__ == "__main__":
     demo.queue(max_size=20).launch()

pyproject.toml

@@ -0,0 +1,53 @@
+[project]
+name = "mistral-7b"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "accelerate>=1.2.1",
+    "bitsandbytes>=0.45.0",
+    "gradio>=5.9.1",
+    "hf-transfer>=0.1.8",
+    "protobuf>=5.29.2",
+    "sentencepiece>=0.2.0",
+    "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

@@ -1,8 +1,249 @@
-accelerate==0.31.0
-bitsandbytes==0.43.1
-gradio==4.36.1
-scipy==1.13.0
+# This file was autogenerated by uv via the following command:
+#    uv pip compile pyproject.toml -o requirements.txt
+accelerate==1.2.1
+    # via mistral-7b (pyproject.toml)
+aiofiles==23.2.1
+    # via gradio
+annotated-types==0.7.0
+    # via pydantic
+anyio==4.7.0
+    # via
+    #   gradio
+    #   httpx
+    #   starlette
+bitsandbytes==0.45.0
+    # via mistral-7b (pyproject.toml)
+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
+    #   mistral-7b (pyproject.toml)
+    #   spaces
+gradio-client==1.5.2
+    # via gradio
+h11==0.14.0
+    # via
+    #   httpcore
+    #   uvicorn
+hf-transfer==0.1.8
+    # via mistral-7b (pyproject.toml)
+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
+    #   bitsandbytes
+    #   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==11.0.0
+    # via gradio
+protobuf==5.29.2
+    # via mistral-7b (pyproject.toml)
+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==0.8.4
+    # via gradio
+safehttpx==0.1.6
+    # via gradio
+safetensors==0.4.5
+    # via
+    #   accelerate
+    #   transformers
+semantic-version==2.10.0
+    # via gradio
 sentencepiece==0.2.0
-spaces==0.28.3
-torch==2.0.1
-transformers==4.41.2
+    # via mistral-7b (pyproject.toml)
+shellingham==1.5.4
+    # via typer
+six==1.17.0
+    # via python-dateutil
+sniffio==1.3.1
+    # via anyio
+spaces==0.31.1
+    # via mistral-7b (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
+    #   mistral-7b (pyproject.toml)
+    #   accelerate
+    #   bitsandbytes
+tqdm==4.67.1
+    # via
+    #   huggingface-hub
+    #   transformers
+transformers==4.47.1
+    # via mistral-7b (pyproject.toml)
+triton==3.0.0
+    # via torch
+typer==0.15.1
+    # via gradio
+typing-extensions==4.12.2
+    # via
+    #   anyio
+    #   bitsandbytes
+    #   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

@@ -9,9 +9,3 @@ h1 {
   background: #1565c0;
   border-radius: 100vh;
 }
-
-.contain {
-  max-width: 900px;
-  margin: auto;
-  padding-top: 1.5rem;
-}