Downloads · 30 days
0
mamba_lenses
sfeucht/mamba_lenses
mamba_lenses is a machine learning model from sfeucht. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
To load checkpoint, use the TunedLens class in the traintunedlensmamba.py file.
Access
Public
Updated Feb 14, 2024
Repo size
2.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.3 GB · 100%
At a glance
- Access
- Public
- Created
- Feb 8, 2024
- Updated
- Feb 14, 2024
- SHA
- 409d7e03
Model card
From the Hugging Face model README
To load checkpoint, use the TunedLens class in the train_tunedlens_mamba.py file.
import accelerate
lens = TunedLens(model.backbone.layers, d_model_hidden_states).to("cuda")
ckpt = 'tunedlens_34_mamba-130m.safetensors'
lens = accelerate.load_checkpoint_and_dispatch(lens, ckpt)
- Created
- Feb 8, 2024
- Updated
- Feb 14, 2024