Hugging Face's logo

KnowledgeXLab
/
PUST-Experiments

Safetensors
Model card Files
xet
 Community
fudaocheng commited on
Commit
3f6b5f0
路
verified 路
1 Parent(s): 38e147f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -1
README.md CHANGED
@@ -2,4 +2,12 @@
2
  license: mit
3
  ---
4
 
5
- GRPO models trained on DeepMath-103K
 
 
 
 
 
 
 
 
 
2
  license: mit
3
  ---
4
 
5
+ ## 馃摝 Model Weights
6
+
7
+ Pre-trained GRPO checkpoints are available on <a href="https://huggingface.co/KnowledgeXLab/PUST-Experiments"><img src="https://huggingface.co/front/assets/huggingface_logo-noborder.svg" width="20" height="20" align="absmiddle"/> <b>Hugging Face</b></a>.
8
+
9
+ | Checkpoint | Role | Training |
10
+ |:--|:--|:--|
11
+ | [`Qwen3-1.7B-Math-GRPO-Steps500`](https://huggingface.co/KnowledgeXLab/PUST-Experiments/tree/main/Qwen3-1.7B-Math-GRPO-Steps500) | Proxy | DeepMath-103K 路 GRPO 路 500 steps |
12
+ | [`Qwen3-1.7B-Math-GRPO-Steps800`](https://huggingface.co/KnowledgeXLab/PUST-Experiments/tree/main/Qwen3-1.7B-Math-GRPO-Steps800) | Proxy | DeepMath-103K 路 GRPO 路 800 steps |
13
+ | [`Qwen3-8B-Math-GRPO-Steps400`](https://huggingface.co/KnowledgeXLab/PUST-Experiments/tree/main/Qwen3-8B-Math-GRPO-Steps400) | Primary | DeepMath-103K 路 GRPO 路 400 steps |