AmberYifan/capsd-less-fast-opc-marin-8b-base-code_less_b8000_s0

Full fine-tune vs marin-community/marin-8b-base. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

Tensors changed: MLP 96/96, Attention 128/128, Norms 65/65, lm_head 1/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse