Downloads · 30 days
3
7% of all-time downloads
G4-31B-configCA-GRPO-r4-100
ApocalypseParty/G4-31B-configCA-GRPO-r4-100
G4-31B-configCA-GRPO-r4-100 is a machine learning model from ApocalypseParty. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
G4-31B-configCA with a GRPO LoRA (diversity training, run 4 step 100) merged in. A lighter-touch checkpoint than G4-31B-configCA-GRPO-r4b100: less diversity gain, weights closer to the base model. Same chat template a…
All-time downloads
41
Public
Parameters
31.3B
62.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors62.5 GB · 100%
At a glance
- Model type
- gemma4
- Access
- Public
- Created
- Jul 28, 2026
- Updated
- Jul 28, 2026
- SHA
- 7eba0847
Model card
From the Hugging Face model README
G4-31B-configCA-GRPO-r4-100
G4-31B-configCA with a GRPO LoRA (diversity training, run 4 step 100) merged in. A lighter-touch checkpoint than G4-31B-configCA-GRPO-r4b100: less diversity gain, weights closer to the base model. Same chat template and usage as the base model.
- Type
- gemma4
- Created
- Jul 28, 2026
- Updated
- Jul 28, 2026