An untrained precursor MoE created from Cosmo using mergekit.

Gate routing initialized using prompt hidden state method. Five are based on the visualized topic clusters of Cosmopedia data, three are task-oriented.

Degenerate layers were 0, 1, and 2. Expert gates for layers 0, 1, and 2 have been randomly initialized to with luck mitigate this.

Downloads last month
6
Safetensors
Model size
10.2B params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for Lambent/cosmoem-8x1B

Adapters
1 model
Quantizations
1 model

Dataset used to train Lambent/cosmoem-8x1B