main.py

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

app = FastAPI()

# Load model and tokenizer
model_name = "mistralai/Mistral-7B-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
# model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")

# if these 3 lines didn't work use the one above
from transformers import BitsAndBytesConfig
quant_config = BitsAndBytesConfig(load_in_8bit=True)
model = AutoModelForCausalLM.from_pretrained(model_name, quantization_config=quant_config, device_map="auto")


@app.post("/generate")
async def generate_text(prompt: str):
    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
    outputs = model.generate(**inputs, max_length=200)
    return {"response": tokenizer.decode(outputs[0], skip_special_tokens=True)}