Spaces:
Sleeping
Sleeping
File size: 1,429 Bytes
4f1031e | 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 | 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)
@app.get("/")
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
@app.post("/infer")
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"]} |