692 B
692 B
license, library_name, tags
| license | library_name | tags | ||||
|---|---|---|---|---|---|---|
| apache-2.0 | transformers |
|
Comm-C Qwen3-8B Thinking SFT
This checkpoint is a short 20-step SFT run based on Qwen3-8B.
Training target format:
<think>
reasoning_content
</think>
final response
Training summary:
- Base model: Qwen3-8B
- Data: synthetic Comm-C distillation data from GLM-5.2
- Train rows: 4243
- Validation rows: 99
- Max length: 32768
- Global batch size: 64
- Learning rate: 2e-5
- Training steps: 20
- Output format: Hugging Face safetensors shards
This checkpoint is intended as a quick sanity-check artifact for thinking-format SFT, not a final converged model.