File size: 1,670 Bytes
3d6419e |
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 44 45 46 47 48 49 50 |
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
from peft import PeftModel
import torch
import locale
import os
locale.setlocale(locale.LC_ALL, 'en_US.UTF-8')
# Load model directly
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
# Use bitsandbytes to load the model in 8-bit precision
bnb_config = BitsAndBytesConfig(
load_in_8bit=True,
bnb_8bit_use_double_quant=True,
bnb_8bit_quant_type="nf8",
bnb_8bit_compute_dtype=torch.bfloat16
)
model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2", quantization_config=bnb_config)
# Load adapter configuration
adapter_config_dir = "adapter_config"
# Load the adapters into the model
model = PeftModel.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2", adapter_config=adapter_config_dir)
# FastAPI app
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel
app = FastAPI()
class Question(BaseModel):
question: str
class Answer(BaseModel):
answer: str
@app.post("/ask", response_model=Answer)
async def ask_question(question: Question):
try:
inputs = tokenizer(question.question, return_tensors="pt")
outputs = model.generate(**inputs)
answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
return Answer(answer=answer)
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
# To run the FastAPI app, use the following command:
# uvicorn app:app --host 0.0.0.0 --port 8000 |