qwen3-4b-nothink-baseline-lora-sft/README.md

license, base_model, tags, language, library_name, pipeline_tag

license	base_model	tags	language	library_name	pipeline_tag
apache-2.0	Qwen/Qwen3-4B-Base	qwen3 code sft lora lora-merged nothink	en zh	transformers	text-generation

Qwen3-4B Code SFT - No-Think Baseline (LoRA Merged)

LoRA supervised fine-tuning of Qwen/Qwen3-4B-Base, with adapters merged into full weights for direct inference.

This repo is LoRA-based SFT (rank 64), not full-parameter fine-tuning.

Model Details

• Base model: Qwen/Qwen3-4B-Base
• Fine-tuning: LoRA SFT (rank 64, alpha 128), merged into full weights
• Mode: No-think (enable_thinking=false)
• Training cutoff length: 8192 tokens

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "modrill/qwen3-4b-nothink-baseline-lora-sft"
tok = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id, trust_remote_code=True, torch_dtype="auto", device_map="auto"
)

Inference Tips

• Set enable_thinking=false in chat template
• Recommended max_tokens: 8192

License

Apache 2.0, consistent with the Qwen3 base model license.