Downloads · 30 days
0
gpt1900-d34-math-rl
mhla/gpt1900-d34-math-rl
gpt1900-d34-math-rl is a machine learning model from mhla. 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 mit.
3.29B parameter GPT-1900 with math RL. GSM8K (30%) + MATH (70%), SymPy verification, format reward. Chain: base - physics CLM expanded - v3 SFT safe - R1 SFT - math RL.
Access
Public
Updated Mar 17, 2026
Repo size
10.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt10.6 GB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Mar 17, 2026
- Updated
- Mar 17, 2026
- SHA
- df6ad4b1
Model card
From the Hugging Face model README
GPT-1900 D34 Math RL
3.29B parameter GPT-1900 with math RL. GSM8K (30%) + MATH (70%), SymPy verification, format reward. Chain: base -> physics CLM expanded -> v3 SFT safe -> R1 SFT -> math RL.
Training
- Training: Math RL (step 60), from r1-reasoning-sft
- Parameters: 3.29B
- Architecture: Custom GPT with RoPE, QK-norm, ReLU², value embeddings
- License
- mit
- Languages
- en
- Created
- Mar 17, 2026
- Updated
- Mar 17, 2026