Goekdeniz-Guelmez/J.O.S.I.E.3-Beta3-slerp-gguf

Full fine-tune vs Locutusque/Hercules-3.1-Mistral-7B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128, lm_head 1/1

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse