Spaces:
Sleeping
Sleeping
File size: 1,285 Bytes
19cd085 bc5f9c0 31cc367 bc5f9c0 19cd085 bc5f9c0 31cc367 bc5f9c0 19cd085 |
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 43 |
from fastapi import FastAPI, HTTPException
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import HTMLResponse
from fastapi.staticfiles import StaticFiles
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
import os
# Set cache directory for Hugging Face Transformers
os.environ["TRANSFORMERS_CACHE"] = "/home/user/.cache"
# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("matsant01/STEMerald-2b")
model = AutoModelForCausalLM.from_pretrained("matsant01/STEMerald-2b")
# Initialize FastAPI app
app = FastAPI()
app.add_middleware(
CORSMiddleware,
allow_origins=["*"],
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
# Serve the HTML file
@app.get("/", response_class=HTMLResponse)
async def read_root():
with open("index.html", "r") as f:
return f.read()
@app.post("/generate/")
async def generate_text(prompt: str):
if not prompt:
raise HTTPException(status_code=400, detail="Prompt cannot be empty")
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(inputs["input_ids"], max_length=50)
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
return {"generated_text": generated_text} |