YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Celerity 906m 8K — ld_0.4_cbcore2.6.0
Official Celerity 906m LayerDrop checkpoint converted from Cerebras CS format to Hugging Face format.
Training provenance
- Original experiment:
ld_0.4_cbcore2.6.0 - Source checkpoint:
checkpoint_29117.mdl - LayerDrop probability: 0.4
- LayerDrop schedule: uniform LayerDrop
- Attention dropout rate: 0.0
- Residual dropout rate: 0.0
- Stochastic depth: 0.0
- Converter commit:
0e3d5d375695293479df9d2a3717f05f71a345b4
LayerDrop is a training-time regularizer. Its effect is represented in the
learned model weights; Hugging Face evaluation is performed with
model.eval().
This repository uses custom Celerity Hugging Face modeling code and should be
loaded with trust_remote_code=True.
- Downloads last month
- 17
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support