Downloads · 30 days
0
mwp-v2-llama1b-base-staged-stage3
GT1999/mwp-v2-llama1b-base-staged-stage3
mwp-v2-llama1b-base-staged-stage3 is a machine learning model from GT1999. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
- LoRA rank / alpha: 32 / 64 (scaling: alpha/r) - Full rank schedule: 32 - 32 - 32 - 32 - 32 - Replay (cumulative levels): True - Stage partition: difficulty - Early stopping patience: 1000000 - Cumulative train examp…
Access
Public
Updated Sep 1, 2026
Repo size
107 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors90.2 MB · 84%
At a glance
- Access
- Public
- Created
- Sep 1, 2026
- Updated
- Sep 1, 2026
- SHA
- 8ec37c27
Model card
From the Hugging Face model README
staged stage 3 -- Curriculum: L1 -> L1,2 -> ... -> L1..5 (constant rank)
- LoRA rank / alpha: 32 / 64 (scaling: alpha/r)
- Full rank schedule: 32 -> 32 -> 32 -> 32 -> 32
- Replay (cumulative levels): True
- Stage partition: difficulty
- Early stopping patience: 1000000
- Cumulative train examples this stage: 3329
- Validation split seed: 42 (5% of train, stratified by level; test set never used for selection)
- Code commit: 1967848696478b02e365550eb6da186f2d5b2bcf
- Created
- Sep 1, 2026
- Updated
- Sep 1, 2026