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

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

LoRA supervised fine-tuning of [Qwen/Qwen3-4B-Base](https://huggingface.co/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

```python
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.