Spaces:
Runtime error
Runtime error
File size: 1,851 Bytes
b3dd839 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 |
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
from transformers import AutoModelForCausalLM, AutoTokenizer
from typing import List
import torch
app = FastAPI(title="Language Model API")
# Model configuration
CHECKPOINT = "HuggingFaceTB/SmolLM2-135M-Instruct"
DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
# Initialize model and tokenizer
try:
tokenizer = AutoTokenizer.from_pretrained(CHECKPOINT)
model = AutoModelForCausalLM.from_pretrained(CHECKPOINT).to(DEVICE)
except Exception as e:
raise RuntimeError(f"Failed to load model: {str(e)}")
class ChatMessage(BaseModel):
role: str
content: str
class ChatRequest(BaseModel):
messages: List[ChatMessage]
max_new_tokens: int = 50
temperature: float = 0.2
top_p: float = 0.9
@app.post("/generate")
async def generate_response(request: ChatRequest):
try:
# Convert messages to the format expected by the model
messages = [{"role": msg.role, "content": msg.content} for msg in request.messages]
# Prepare input
input_text = tokenizer.apply_chat_template(messages, tokenize=False)
inputs = tokenizer.encode(input_text, return_tensors="pt").to(DEVICE)
# Generate response
outputs = model.generate(
inputs,
max_new_tokens=request.max_new_tokens,
temperature=request.temperature,
top_p=request.top_p,
do_sample=True
)
# Decode and return response
response_text = tokenizer.decode(outputs[0])
return {
"generated_text": response_text
}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
if __name__ == "__main__":
import uvicorn
uvicorn.run(app, host="0.0.0.0", port=7860)
|