app.py

from fastapi import FastAPI
from pydantic import BaseModel
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

app = FastAPI()

MODEL_NAME = "mjpsm/progress-generation-model"

device = "cuda" if torch.cuda.is_available() else "cpu"

tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForCausalLM.from_pretrained(MODEL_NAME).to(device)

tokenizer.pad_token = tokenizer.eos_token

class Request(BaseModel):
    text: str

def generate_response(user_input):
    prompt = f"""<|system|>
You describe what progress was achieved in one sentence.
<|user|>
{user_input}
<|assistant|>
"""

    inputs = tokenizer(prompt, return_tensors="pt").to(device)

    with torch.no_grad():
        outputs = model.generate(
            **inputs,
            max_new_tokens=50,
            temperature=0.6,
            top_p=0.9,
            repetition_penalty=1.2,
            pad_token_id=tokenizer.eos_token_id
        )

    decoded = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return decoded.split("<|assistant|>")[-1].strip()

@app.get("/")
def root():
    return {"message": "Progress Model API running"}

@app.post("/predict")
def predict(req: Request):
    result = generate_response(req.text)
    return {"output": result}