from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model = "meta-llama/Llama-3.1-8B-Instruct"
adapter_id = "YOUR_USERNAME/YOUR_REPO_NAME"

tokenizer = AutoTokenizer.from_pretrained(adapter_id)
model = AutoModelForCausalLM.from_pretrained(
    base_model,
    device_map="auto",
    torch_dtype="auto",
)
model = PeftModel.from_pretrained(model, adapter_id)

messages = [{"role": "user", "content": "Your question here"}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt",
).to(model.device)
outputs = model.generate(inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

doupari/Llama-3.1-8B-Instruct-question

Llama-3.1-8B-Instruct-question LoRA Adapter

Checkpoint Selection

Usage

doupari/
Llama-3.1-8B-Instruct-question