File size: 908 Bytes
ab04017 b06b189 215df44 ab04017 215df44 ab04017 215df44 b06b189 ab04017 b06b189 ab04017 b06b189 ab04017 215df44 ab04017 215df44 ab04017 215df44 ab04017 215df44 ab04017 308afe6 ab04017 308afe6 215df44 ab04017 | 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 42 | from fastapi import FastAPI
from transformers import AutoTokenizer, AutoModelForCausalLM, AutoConfig
import torch
app = FastAPI()
model_name = "Jaswant1801/qwen_nutrisync"
tokenizer = AutoTokenizer.from_pretrained(
model_name,
trust_remote_code=True
)
# Load config and remove quantization
config = AutoConfig.from_pretrained(model_name)
config.quantization_config = None
model = AutoModelForCausalLM.from_pretrained(
model_name,
config=config,
trust_remote_code=True,
device_map="cpu",
dtype=torch.float32
)
@app.get("/")
def home():
return {"message": "NutriSync API running"}
@app.post("/generate")
def generate(prompt: str):
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(
**inputs,
max_new_tokens=150
)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
return {"response": response} |