Spaces:
Sleeping
Sleeping
File size: 721 Bytes
ab2704b fb9dd56 ab2704b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 |
from transformers import AutoModelForCausalLM, AutoTokenizer
from fastapi import FastAPI, Request
import uvicorn
model_name = "ibm-granite/granite-7b-base"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
app = FastAPI()
@app.post("/generate")
async def generate_text(request: Request):
data = await request.json()
prompt = data.get("prompt", "")
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=150)
response_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
return {"output": response_text}
if __name__ == "__main__":
uvicorn.run(app, host="0.0.0.0", port=7860)
|