Upload 12 files

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,2 @@
+test.py
+.venv

.vscode/settings.json

@@ -0,0 +1,3 @@
+{
+  "editor.wordWrap": "on"
+}

Dockerfile

@@ -0,0 +1,20 @@
+FROM python:3.11
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+# ARG HF_TOKEN
+
+# RUN --mount=type=secret,id=HF_TOKEN,mode=0444,required=true \
+#     HF_TOKEN=$(cat /run/secrets/HF_TOKEN)
+
+# ENV HF_TOKEN=HF_TOKEN
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -1,10 +1,10 @@
----
-title: Lumbus
-emoji: 🏢
-colorFrom: indigo
-colorTo: blue
-sdk: docker
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Llm
+emoji: 🏆
+colorFrom: pink
+colorTo: blue
+sdk: docker
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,13 @@
+from huggingface_hub import InferenceClient
+from fastapi import FastAPI
+from routes import chatCompletion, textToImage, automaticSpeechRecognition
+
+app = FastAPI()
+
+@app.get("/")
+async def root():
+    return {"message": "Hello World"}
+
+app.include_router(chatCompletion.router)
+app.include_router(textToImage.router)
+app.include_router(automaticSpeechRecognition.router)

models/chat_completion.py

@@ -0,0 +1,24 @@
+from pydantic import BaseModel, Field
+from typing import List, Optional
+from huggingface_hub import ChatCompletionInputMessage, ChatCompletionInputGrammarType, ChatCompletionInputStreamOptions, ChatCompletionInputToolChoiceClass, ChatCompletionInputTool
+
+class ChatRequest(BaseModel):
+    model: str = Field(..., description="The model to use for chat-completion. Can be a model ID hosted on the Hugging Face Hub or a URL to a deployed Inference Endpoint. If not provided, the default recommended model for chat-based text-generation will be used. See https://huggingface.co/tasks/text-generation for more details.")
+    messages: List[ChatCompletionInputMessage] = Field(..., description="Conversation history consisting of roles and content pairs.")
+    frequency_penalty: Optional[float] = Field(0.0, ge=-2.0, le=2.0, description="Penalizes new tokens based on their existing frequency in the text so far. Range: [-2.0, 2.0]. Defaults to 0.0.")
+    logit_bias: Optional[dict] = Field(None, description="Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens to an associated bias value from -100 to 100.")
+    logprobs: Optional[bool] = Field(None, description="Whether to return log probabilities of the output tokens or not.")
+    max_tokens: Optional[int] = Field(8192, description="Maximum number of tokens allowed in the response. Defaults to 100.")
+    n: Optional[int] = Field(None, description="UNUSED.")
+    presence_penalty: Optional[float] = Field(None, ge=-2.0, le=2.0, description="Positive values penalize new tokens based on whether they appear in the text so far.")
+    response_format: Optional[ChatCompletionInputGrammarType] = Field(None, description="Grammar constraints. Can be either a JSONSchema or a regex.")
+    seed: Optional[int] = Field(None, description="Seed for reproducible control flow.")
+    stop: Optional[str] = Field(None, description="Up to four strings which trigger the end of the response.")
+    stream: Optional[bool] = Field(False, description="Enable realtime streaming of responses. Defaults to False.")
+    stream_options: Optional[ChatCompletionInputStreamOptions] = Field(None, description="Options for streaming completions.")
+    temperature: Optional[float] = Field(1.0, ge=0.0, le=2.0, description="Controls randomness of the generations. Lower values ensure less random completions.")
+    top_logprobs: Optional[int] = Field(None, ge=0, le=5, description="Specifying the number of most likely tokens to return at each token position.")
+    top_p: Optional[float] = Field(0.95, gt=0.0, lt=1.0, description="Fraction of the most likely next words to sample from.")
+    tool_choice: Optional[ChatCompletionInputToolChoiceClass] = Field("auto", description="The tool to use for the completion. Defaults to 'auto'.")
+    tool_prompt: Optional[str] = Field(None, description="A prompt to be appended before the tools.")
+    tools: Optional[List] = Field(None, description="A list of tools the model may call.")

models/text_to_image.py

@@ -0,0 +1,14 @@
+from pydantic import BaseModel, Field
+from typing import List, Optional
+
+class TextToImageRequest(BaseModel):
+    prompt: str = Field(..., description="The prompt to generate an image from.")
+    negative_prompt: Optional[str] = Field(None, description="One or several prompts to guide what NOT to include in image generation.")
+    height: Optional[int] = Field(None, description="The height in pixels of the image to generate.", ge=64, le=2048)
+    width: Optional[int] = Field(None, description="The width in pixels of the image to generate.", ge=64, le=2048)
+    num_inference_steps: Optional[int] = Field(None, description="The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference.", ge=1, le=500)
+    guidance_scale: Optional[float] = Field(None, description="A higher guidance scale value encourages the model to generate images closely linked to the text prompt, but values too high may cause saturation and other artifacts.", ge=1, le=20)
+    model: Optional[str] = Field(None, description="The model to use for inference. Can be a model ID hosted on the Hugging Face Hub or a URL to a deployed Inference Endpoint. If not provided, the default recommended text-to-image model will be used.")
+    scheduler: Optional[str] = Field(None, description="Override the scheduler with a compatible one.")
+    #target_size: Optional[TextToImageTargetSize] = Field(None, description="The size in pixel of the output image")
+    seed: Optional[int] = Field(None, description="Seed for the random number generator.")

requirements.txt

@@ -0,0 +1,5 @@
+fastapi
+uvicorn[standard]
+huggingface_hub==0.27.1
+Pillow
+python-multipart

routes/automaticSpeechRecognition.py

@@ -0,0 +1,23 @@
+from fastapi import APIRouter, File, UploadFile, Form
+from huggingface_hub import InferenceClient
+
+router = APIRouter()
+
+@router.post("/v1/audio/transcriptions", tags=["Automatic Speech Recognition"])
+# Add model and audio parameters to the function signature
+async def automatic_speech_recognition(
+    model: str = Form(..., description="The model to use for ASR. Can be a model ID hosted on the Hugging Face Hub or a URL to a deployed Inference Endpoint. If not provided, the default recommended model for ASR will be used."),
+    audio: UploadFile = File(..., description="The content to transcribe. It can be raw audio bytes, local audio file, or a URL to an audio file.")
+):
+    # Use the 'model' parameter from the form data
+    client = InferenceClient(model=model)
+
+    # Read the uploaded file content
+    audio_bytes = await audio.read()
+
+    # Pass the audio bytes to the client method
+    res = client.automatic_speech_recognition(
+        audio=audio_bytes
+    )
+    # Return the result
+    return res

routes/chatCompletion.py

@@ -0,0 +1,52 @@
+from fastapi import APIRouter
+from fastapi.responses import StreamingResponse
+from models.chat_completion import ChatRequest
+from huggingface_hub import InferenceClient
+import json
+
+router = APIRouter()
+
+def generate_stream(response):
+    try:
+        for chunk in response:
+            try:
+                # Attempt to process and yield the chunk
+                yield f"data: {json.dumps(chunk.__dict__, separators=(',', ':'))}\n\n"
+            except Exception as e:
+                # Optional: Log the error for debugging
+                print(f"Error during stream processing: {e}")
+                # Stop sending chunks if an error occurs
+                break
+    finally:
+        # Ensure the [DONE] message is always sent, even if an error occurred
+        yield "data: [DONE]\n\n"
+
+@router.post("/v1/chat/completions", tags=["Chat Completion"])
+async def chat_completion(body: ChatRequest):
+    client = InferenceClient(model=body.model)
+
+    res = client.chat_completion(
+        messages=body.messages,
+        frequency_penalty=body.frequency_penalty,
+        logit_bias=body.logit_bias,
+        logprobs=body.logprobs,
+        max_tokens=body.max_tokens,
+        n=body.n,
+        presence_penalty=body.presence_penalty,
+        response_format=body.response_format,
+        seed=body.seed,
+        stop=body.stop,
+        stream=body.stream,
+        stream_options=body.stream_options,
+        temperature=body.temperature,
+        top_logprobs=body.top_logprobs,
+        top_p=body.top_p,
+        tool_choice=body.tool_choice,
+        tool_prompt=body.tool_prompt,
+        tools=body.tools
+    )
+
+    if not body.stream:
+        return json.dumps(res.__dict__, indent=2)
+    else:
+        return StreamingResponse(generate_stream(res), media_type="text/event-stream")

routes/textToImage.py

@@ -0,0 +1,42 @@
+from fastapi import APIRouter, Response
+from models.text_to_image import TextToImageRequest
+from huggingface_hub import InferenceClient
+import io
+
+router = APIRouter()
+
+@router.post("/v1/images/generations", tags=["Text to Image"])
+async def text_to_image(t2i_body: TextToImageRequest):
+    client = InferenceClient(model=t2i_body.model)
+    res = client.text_to_image(
+        t2i_body.prompt,
+        negative_prompt=t2i_body.negative_prompt,
+        height=t2i_body.height,
+        width=t2i_body.width,
+        num_inference_steps=t2i_body.num_inference_steps,
+        guidance_scale=t2i_body.guidance_scale,
+        scheduler=t2i_body.scheduler,
+       # target_size=t2i_body.target_size,
+        seed=t2i_body.seed
+    )
+    img_byte_arr = io.BytesIO()
+    res.save(img_byte_arr, format="PNG")
+    img_byte_arr.seek(0)
+    try:
+        res = client.text_to_image(
+            prompt=t2i_body.prompt,
+            negative_prompt=t2i_body.negative_prompt,
+            height=t2i_body.height,
+            width=t2i_body.width,
+            num_inference_steps=t2i_body.num_inference_steps,
+            guidance_scale=t2i_body.guidance_scale,
+            scheduler=t2i_body.scheduler,
+            seed=t2i_body.seed
+        )
+        img_byte_arr = io.BytesIO()
+        res.save(img_byte_arr, format="PNG")
+        img_byte_arr.seek(0)
+        return Response(content=img_byte_arr.getvalue(), media_type="image/png")
+    except Exception as e:
+        print(f"Error generating image: {e}")
+        return {"error": str(e)}, 500