timaeus
/

H1-dh256

Model card Files Files and versions Community

Edit model card

YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

H1-dh256 Checkpoints

This repository contains the final trained model and intermediate checkpoints.

The main directory contains the fully trained model (checkpoint 75000).
The checkpoints directory contains all intermediate checkpoints.

Downloads last month: 3

Safetensors

Model size

5.45M params

Tensor type

F32

·

BOOL

·

Inference API

Unable to determine this model's library. Check the docs .

Collection including timaeus/H1-dh256

Models: H-dh

Attention-only transformers, sweep over number of heads (variable head dimension) • 7 items • Updated Oct 18