shruthi-09/llama3-code-lora

from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
from peft import PeftModel
import torch

base_model_id = "meta-llama/Llama-3.2-3B-Instruct"
adapter_id    = "shruthi-09/llama3-code-lora"

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.float16,
)

tokenizer = AutoTokenizer.from_pretrained(adapter_id)
base = AutoModelForCausalLM.from_pretrained(
    base_model_id, quantization_config=bnb_config, device_map="auto"
)
model = PeftModel.from_pretrained(base, adapter_id)

messages = [
    {"role": "system", "content": "You are an expert Python developer."},
    {"role": "user", "content": "Write a binary search function."},
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

with torch.no_grad():
    out = model.generate(**inputs, max_new_tokens=300, temperature=0.3, do_sample=True)

print(tokenizer.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))