Files
math-think-s1-v2-qwen3-4b/README.md

15 lines
230 B
Markdown
Raw Normal View History

---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen3-4B-Base
tags:
- qwen3
- math
- sft
- llama-factory
---
# math-think-s1-v2-qwen3-4b
Light-R1 stage1 think SFT. cutoff=24576, 2 epoch, lr=1e-5, packing on.