nehuggingface/Hermes2pro-mistral-saul-instruct-slerp

Full fine-tune vs Equall/Saul-7B-Instruct-v1. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 18/65, MLP 93/96, Attention 124/128, lm_head 1/1

1 derivatives checked

• mradermacher/Hermes2pro-mistral-saul-instruct-slerp-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse