Update app.py

app.py

@@ -1,69 +1,105 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from typing import List, Dict, Optional
+import torch
+import uvicorn
 
+# ============ FASTAPI SETUP ============
+app = FastAPI()
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-    """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
+# ============ MODEL LOADING ============
+model_name = "mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated"
 
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
+quant_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_compute_dtype=torch.float16,
+    bnb_4bit_use_double_quant=True
+)
 
-    messages.append({"role": "user", "content": message})
+print("Loading tokenizer...")
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-    response = ""
+print("Loading model (4-bit)...")
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    device_map="auto",
+    quantization_config=quant_config,
+    torch_dtype=torch.float16
+)
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+# ============ API MODELS ============
+class Message(BaseModel):
+    role: str
+    content: str
 
-        response += token
-        yield response
+class ChatRequest(BaseModel):
+    model: Optional[str] = None
+    messages: List[Message]
 
+class Choice(BaseModel):
+    index: int
+    message: Message
+    finish_reason: str
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+class ChatResponse(BaseModel):
+    id: str
+    object: str
+    created: int
+    model: str
+    choices: List[Choice]
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+# ============ CHAT COMPLETIONS ENDPOINT ============
+@app.post("/v1/chat/completions")
+async def chat_completions(request: ChatRequest):
+    try:
+        # Build prompt from messages
+        prompt = ""
+        for msg in request.messages:
+            if msg.role == "system":
+                prompt += f"System: {msg.content}\n"
+            elif msg.role == "user":
+                prompt += f"User: {msg.content}\n"
+            elif msg.role == "assistant":
+                prompt += f"Assistant: {msg.content}\n"
+        
+        prompt += "Assistant:"
+        
+        # Generate response
+        inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+        outputs = model.generate(
+            **inputs,
+            max_new_tokens=256,
+            temperature=0.7,
+            do_sample=True,
+            pad_token_id=tokenizer.eos_token_id
+        )
+        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        response = response.split("Assistant:")[-1].strip()
+        
+        # Return in OpenAI-compatible format
+        return ChatResponse(
+            id="chatcmpl-123",
+            object="chat.completion",
+            created=int(torch.tensor(0)),
+            model="abliterated-model",
+            choices=[
+                Choice(
+                    index=0,
+                    message=Message(role="assistant", content=response),
+                    finish_reason="stop"
+                )
+            ]
+        )
+    
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
 
+# ============ HEALTH CHECK ============
+@app.get("/")
+async def root():
+    return {"status": "ok", "model": "abliterated"}
 
+# ============ RUN ============
 if __name__ == "__main__":
-    demo.launch()
+    uvicorn.run(app, host="0.0.0.0", port=7860)