Downloads · 30 days
6
13% of all-time downloads
baseline-1.25B-l48w1250-fwedu-s63999
SubspaceTransformer/baseline-1.25B-l48w1250-fwedu-s63999
baseline-1.25B-l48w1250-fwedu-s63999 is a machine learning model from SubspaceTransformer. 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.
Single baseline transformer checkpoint snapshot.
All-time downloads
47
Public
Repo size
11.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt11.8 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- baseline
- Access
- Public
- Created
- Apr 16, 2026
- Updated
- Apr 16, 2026
- SHA
- b487b325
Model card
From the Hugging Face model README
baseline-1.25B-l48w1250-fwedu-s63999
Single baseline transformer checkpoint snapshot.
Model Details
| Model Type | baseline |
| Parameters | 1,279,228,550 |
| Layers | 48 |
| Width | 1250 |
| Heads | 25 |
| MLP Ratio | 4.0 |
| Training Steps | 61,999 |
| Context Length | 2048 |
| Vocab Size | 151,665 |
| Best Val Loss | 2.5774 |
Files
model.pt- Checkpoint (weights + optimizer + RNG state)config.json- Resolved training config
- Type
- baseline
- License
- apache-2.0
- Created
- Apr 16, 2026
- Updated
- Apr 16, 2026