Qwen3-4B Instruct rewrite LoRA

LoRA adapter from SFT on self-rewritten reasoning traces (Qwen/Qwen3-4B-Instruct-2507).

Load

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = "Qwen/Qwen3-4B-Instruct-2507"
adapter = "talzoomanzoo/qwen3-4b-instruct-rewrite-sft"

tokenizer = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="auto", device_map="auto")
model = PeftModel.from_pretrained(model, adapter)

Downloads last month: 1

Model tree for talzoomanzoo/qwen3-4b-instruct-rewrite-sft

Base model

Qwen/Qwen3-4B-Instruct-2507

Adapter

(5598)

this model