yrhong/llama-3.1-8b-instruct-sft-seed44

LoRA adapter for meta-llama/Llama-3.1-8B-Instruct.

• Training setting: SFT
• Seed: 44
• Adapter format: PEFT LoRA

Usage (Transformers + PEFT)

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model = "meta-llama/Llama-3.1-8B-Instruct"
adapter_repo = "yrhong/llama-3.1-8b-instruct-sft-seed44"

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

Notes

• This repository contains adapter weights only, not full base model weights.
• Use only for research and evaluation purposes.