mradermacher/marin-8b-instruct-GGUF

Same weights, converted vs marin-community/marin-8b-instruct. Same weights stored in another dtype (F32 → F16/F32), plus 1 new tensors.

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

On the Hub · Downloads on Model Pulse