gradio==5.1.0

.python-version

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

README.md

@@ -4,7 +4,7 @@ emoji: ⚡
 colorFrom: red
 colorTo: purple
 sdk: gradio
-sdk_version: 4.27.0
+sdk_version: 5.1.0
 app_file: app.py
 pinned: false
 license: mit

app.py

@@ -65,6 +65,7 @@ def generate(
         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()
@@ -75,10 +76,10 @@ def generate(
         yield "".join(outputs)
 
 
-chat_interface = gr.ChatInterface(
+demo = gr.ChatInterface(
     fn=generate,
-    chatbot=gr.Chatbot(show_label=False, layout="panel", height=600),
-    additional_inputs_accordion_name="詳細設定",
+    type="tuples",
+    additional_inputs_accordion=gr.Accordion(label="詳細設定", open=False),
     additional_inputs=[
         gr.Slider(
             label="Max new tokens",
@@ -123,16 +124,10 @@ chat_interface = gr.ChatInterface(
         ["暴れん坊将軍って誰のこと？"],
         ["人がヘリを食べるのにかかる時間は？"],
     ],
+    description=DESCRIPTION,
+    css_paths="style.css",
+    fill_height=True,
 )
 
-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()
+    demo.launch()

pyproject.toml

@@ -0,0 +1,15 @@
+[project]
+name = "rakutenai-7b-chat"
+version = "0.1.0"
+description = ""
+readme = "README.md"
+requires-python = ">=3.10"
+dependencies = [
+    "accelerate>=1.0.1",
+    "bitsandbytes>=0.44.1",
+    "gradio>=5.1.0",
+    "hf-transfer>=0.1.8",
+    "spaces>=0.30.4",
+    "torch==2.4.0",
+    "transformers>=4.45.2",
+]

requirements.txt

@@ -1,8 +1,241 @@
-accelerate==0.29.3
-bitsandbytes==0.43.1
-gradio==4.27.0
-scipy==1.13.0
-sentencepiece==0.1.99
-spaces==0.26.1
-torch==2.0.0
-transformers==4.40.0
+# This file was autogenerated by uv via the following command:
+#    uv pip compile pyproject.toml -o requirements.txt
+accelerate==1.0.1
+    # via rakutenai-7b-chat (pyproject.toml)
+aiofiles==23.2.1
+    # via gradio
+annotated-types==0.7.0
+    # via pydantic
+anyio==4.6.2.post1
+    # via
+    #   gradio
+    #   httpx
+    #   starlette
+bitsandbytes==0.44.1
+    # via rakutenai-7b-chat (pyproject.toml)
+certifi==2024.8.30
+    # via
+    #   httpcore
+    #   httpx
+    #   requests
+charset-normalizer==3.4.0
+    # via requests
+click==8.1.7
+    # via
+    #   typer
+    #   uvicorn
+exceptiongroup==1.2.2
+    # via anyio
+fastapi==0.115.2
+    # via gradio
+ffmpy==0.4.0
+    # via gradio
+filelock==3.16.1
+    # via
+    #   huggingface-hub
+    #   torch
+    #   transformers
+    #   triton
+fsspec==2024.9.0
+    # via
+    #   gradio-client
+    #   huggingface-hub
+    #   torch
+gradio==5.1.0
+    # via
+    #   rakutenai-7b-chat (pyproject.toml)
+    #   spaces
+gradio-client==1.4.0
+    # via gradio
+h11==0.14.0
+    # via
+    #   httpcore
+    #   uvicorn
+hf-transfer==0.1.8
+    # via rakutenai-7b-chat (pyproject.toml)
+httpcore==1.0.6
+    # via httpx
+httpx==0.27.2
+    # via
+    #   gradio
+    #   gradio-client
+    #   spaces
+huggingface-hub==0.26.0
+    # via
+    #   accelerate
+    #   gradio
+    #   gradio-client
+    #   tokenizers
+    #   transformers
+idna==3.10
+    # via
+    #   anyio
+    #   httpx
+    #   requests
+jinja2==3.1.4
+    # 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==3.4.1
+    # via torch
+numpy==2.1.2
+    # 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==12.6.77
+    # via
+    #   nvidia-cusolver-cu12
+    #   nvidia-cusparse-cu12
+nvidia-nvtx-cu12==12.1.105
+    # via torch
+orjson==3.10.9
+    # via gradio
+packaging==24.1
+    # via
+    #   accelerate
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   spaces
+    #   transformers
+pandas==2.2.3
+    # via gradio
+pillow==10.4.0
+    # via gradio
+psutil==5.9.8
+    # via
+    #   accelerate
+    #   spaces
+pydantic==2.9.2
+    # via
+    #   fastapi
+    #   gradio
+    #   spaces
+pydantic-core==2.23.4
+    # via pydantic
+pydub==0.25.1
+    # via gradio
+pygments==2.18.0
+    # via rich
+python-dateutil==2.9.0.post0
+    # via pandas
+python-multipart==0.0.12
+    # via gradio
+pytz==2024.2
+    # via pandas
+pyyaml==6.0.2
+    # via
+    #   accelerate
+    #   gradio
+    #   huggingface-hub
+    #   transformers
+regex==2024.9.11
+    # via transformers
+requests==2.32.3
+    # via
+    #   huggingface-hub
+    #   spaces
+    #   transformers
+rich==13.9.2
+    # via typer
+ruff==0.7.0
+    # via gradio
+safetensors==0.4.5
+    # via
+    #   accelerate
+    #   transformers
+semantic-version==2.10.0
+    # via gradio
+shellingham==1.5.4
+    # via typer
+six==1.16.0
+    # via python-dateutil
+sniffio==1.3.1
+    # via
+    #   anyio
+    #   httpx
+spaces==0.30.4
+    # via rakutenai-7b-chat (pyproject.toml)
+starlette==0.40.0
+    # via fastapi
+sympy==1.13.3
+    # via torch
+tokenizers==0.20.1
+    # via transformers
+tomlkit==0.12.0
+    # via gradio
+torch==2.4.0
+    # via
+    #   rakutenai-7b-chat (pyproject.toml)
+    #   accelerate
+    #   bitsandbytes
+tqdm==4.66.5
+    # via
+    #   huggingface-hub
+    #   transformers
+transformers==4.45.2
+    # via rakutenai-7b-chat (pyproject.toml)
+triton==3.0.0
+    # via torch
+typer==0.12.5
+    # 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==2.2.3
+    # via requests
+uvicorn==0.32.0
+    # via gradio
+websockets==12.0
+    # 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;
-}