Goekdeniz-Guelmez/J.O.S.I.E.3-Beta8-slerp

Full fine-tune vs HuggingFaceH4/mistral-7b-anthropic. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 15/65, MLP 93/96, Attention 124/128, lm_head 1/1

1 derivatives checked

• mradermacher/J.O.S.I.E.3-Beta8-slerp-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse