|
|
from fastapi import FastAPI, HTTPException |
|
|
from fastapi.middleware.cors import CORSMiddleware |
|
|
from pydantic import BaseModel |
|
|
from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM |
|
|
import torch |
|
|
|
|
|
app = FastAPI() |
|
|
|
|
|
|
|
|
app.add_middleware( |
|
|
CORSMiddleware, |
|
|
allow_origins=["*"], |
|
|
allow_methods=["*"], |
|
|
allow_headers=["*"], |
|
|
) |
|
|
|
|
|
|
|
|
model_name = "SkillForge45/CyberFuture-A1" |
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name) |
|
|
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16) |
|
|
|
|
|
|
|
|
device = "cuda" if torch.cuda.is_available() else "cpu" |
|
|
model.to(device) |
|
|
|
|
|
class ChatRequest(BaseModel): |
|
|
prompt: str |
|
|
max_length: int = 100 |
|
|
|
|
|
@app.post("/chat/") |
|
|
async def chat(request: ChatRequest): |
|
|
try: |
|
|
inputs = tokenizer(request.prompt, return_tensors="pt").to(device) |
|
|
outputs = model.generate( |
|
|
**inputs, |
|
|
max_length=request.max_length, |
|
|
temperature=0.7, |
|
|
do_sample=True |
|
|
) |
|
|
response = tokenizer.decode(outputs[0], skip_special_tokens=True) |
|
|
return {"response": response} |
|
|
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=8000) |
