inference.py

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

BASE_MODEL = "deepseek-ai/deepseek-coder-1.3b-base"
LORA_REPO  = "your-username/deepseek-lora-monthly"

tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL, trust_remote_code=True)
base = AutoModelForCausalLM.from_pretrained(BASE_MODEL, trust_remote_code=True)
model = PeftModel.from_pretrained(base, LORA_REPO)

def generate_response(prompt:str)->str:
    inputs = tokenizer(prompt, return_tensors="pt")
    out = model.generate(**inputs, max_new_tokens=200)
    return tokenizer.decode(out[0], skip_special_tokens=True)