Downloads · 30 days
10
25% of all-time downloads
qwen25math-7b-abstract-cot-warmup
LauraGG/qwen25math-7b-abstract-cot-warmup
qwen25math-7b-abstract-cot-warmup is a machine learning model from LauraGG. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Post-warmup Phase B (iter1) checkpoint used as the starting point for the GRPO compression run at https://huggingface.co/LauraGG/qwen25math-7b-abstract-cot-grpo
All-time downloads
40
Public
Parameters
7.6B
15.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors15.2 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- May 16, 2026
- Updated
- May 16, 2026
- SHA
- 481e1973
Base models
Model card
From the Hugging Face model README
Qwen2.5-Math-7B Abstract-CoT minimal warmup checkpoint
Post-warmup Phase B (iter1) checkpoint used as the starting point for the GRPO compression run at https://huggingface.co/LauraGG/qwen25math-7b-abstract-cot-grpo
Trained with 1 policy-iteration round (Phase A + Phase B), 3k examples from Dolci-Think-SFT-7B, 1 epoch each, full fine-tuning, on 1× H100. ~70 minutes.
Post-warmup MATH-500 cold-start probe: 15.6% (n=32, T=0.7).
Notes
- Format-correct: emits <beginabstract>...<endabstract> followed by an answer.
- Empty-z̃ basin already present: z̃ length pegged at ~9 tokens (the minimum).
- Use as the input to GRPO; not useful standalone.
- Type
- qwen2
- License
- apache-2.0
- Created
- May 16, 2026
- Updated
- May 16, 2026