marin-community/marin-8b-instruct
Full fine-tune vs marin-community/marin-8b-base. Fine-tune: 100% 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 1/1
4 derivatives checked
- mradermacher/marin-8b-instruct-i1-GGUF: Quantization
- mradermacher/marin-8b-instruct-GGUF: Same weights, converted
- DevQuasar/marin-community.marin-8b-instruct-GGUF: Same weights, converted
- tensorblock/marin-community_marin-8b-instruct-GGUF: Quantization