---
license: apache-2.0
base_model: Qwen/Qwen3-4B-Base
tags:
  - qwen3
  - code
  - sft
  - full-sft
  - think
  - llama-factory
language:
  - en
  - zh
library_name: transformers
pipeline_tag: text-generation
---

# Qwen3-4B Code SFT - Think Baseline (Full SFT)

Full-parameter supervised fine-tuning (not LoRA) of [Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base) on the think_all dataset with thinking mode enabled.

**This repo contains native full fine-tuned weights** (single `model.safetensors`, ~7.5 GB). For LoRA adapters merged into base weights, see [modrill/qwen3-4b-think-baseline-lora-sft](https://huggingface.co/modrill/qwen3-4b-think-baseline-lora-sft).

## Model Details

- **Base model:** Qwen/Qwen3-4B-Base
- **Fine-tuning:** Full SFT (DeepSpeed ZeRO-3), finetuning_type: full
- **Dataset:** think_all
- **Mode:** Think (`enable_thinking=true`)
- **Training cutoff length:** 24576 tokens
- **Epochs:** 2
- **Learning rate:** 2e-5
- **Train loss:** ~0.67
- **Finished:** 2026-06-08

## Usage

### HuggingFace Transformers

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "modrill/qwen3-4b-think-baseline-full-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"
)
```

### vLLM

```bash
python -m vllm.entrypoints.openai.api_server \
  --model modrill/qwen3-4b-think-baseline-full-sft \
  --served-model-name think-baseline-full \
  --port 8801
```

## Inference Tips

- Set `enable_thinking=true` in the chat template
- Recommended `max_tokens`: 24576

## License

Apache 2.0, consistent with the Qwen3 base model license.