Downloads · 30 days
0
gdn2-cpt-remoe-tk2-fineweb
gyung/gdn2-cpt-remoe-tk2-fineweb
gdn2-cpt-remoe-tk2-fineweb is a machine learning model from gyung. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Continued-pretraining arms on identical data/steps: SSKetch+ReMoE (targetk=2/4), SSC fixed top-4 (paper baseline), vanilla GDN-2. 400 steps x effective batch 64 x 4096 tokens per arm.
Access
Public
Updated Aug 26, 2026
Repo size
1.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth1.7 GB · 100%
At a glance
- Access
- Public
- Created
- Aug 26, 2026
- Updated
- Aug 26, 2026
- SHA
- 1a843c41
Model card
From the Hugging Face model README
GDN-2 CPT comparison checkpoints
Continued-pretraining arms on identical data/steps: SSKetch+ReMoE (target_k=2/4), SSC fixed top-4 (paper baseline), vanilla GDN-2. 400 steps x effective batch 64 x 4096 tokens per arm.
| directory |
|---|
| remoe_fineweb_adaptive |
- Created
- Aug 26, 2026
- Updated
- Aug 26, 2026