Spaces:
Sleeping
Sleeping
| from fastapi import FastAPI, Depends, HTTPException | |
| from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials | |
| from pydantic import BaseModel | |
| from peft import PeftModel | |
| from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline | |
| import torch | |
| import os | |
| app = FastAPI() | |
| # Root kontrol (HF health check için) | |
| async def root(): | |
| return {"message": "Joke API is running!"} | |
| security = HTTPBearer() | |
| AUTH_TOKEN = os.getenv("AUTH_TOKEN") | |
| # Model yükle (joke modeli) | |
| base_model = AutoModelForCausalLM.from_pretrained("gpt2") | |
| model = PeftModel.from_pretrained(base_model, "skaterx/joke-lora-v1") | |
| model.eval() | |
| tokenizer = AutoTokenizer.from_pretrained("skaterx/joke-lora-v1") | |
| tokenizer.pad_token = tokenizer.eos_token | |
| generator = pipeline("text-generation", model=model, tokenizer=tokenizer, device_map="auto") | |
| class InferRequest(BaseModel): | |
| prompt: str | |
| max_length: int = 100 | |
| temperature: float = 0.9 | |
| async def infer(request: InferRequest, credentials: HTTPAuthorizationCredentials = Depends(security)): | |
| if credentials.credentials != AUTH_TOKEN: | |
| raise HTTPException(status_code=401, detail="Invalid token") | |
| full_prompt = f"Şaka anlat:\n{request.prompt}\n\nŞaka:" | |
| result = generator(full_prompt, max_length=request.max_length, temperature=request.temperature, do_sample=True) | |
| return {"generated_text": result[0]["generated_text"]} |