yrhong/qwen3-8b-sft-seed42

LoRA adapter for Qwen/Qwen3-8B.

• Training setting: SFT
• Seed: 42
• Adapter format: PEFT LoRA

Usage (Transformers + PEFT)

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model = "Qwen/Qwen3-8B"
adapter_repo = "yrhong/qwen3-8b-sft-seed42"

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.