00000-X/Nous-Hermes-2-Pro_into_Nous_Hermes-2-DPO

Full fine-tune vs NousResearch/Hermes-2-Pro-Mistral-7B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 14/65, MLP 93/96, Attention 124/128

1 derivatives checked

• mradermacher/Nous-Hermes-2-Pro_into_Nous_Hermes-2-DPO-GGUF: Same weights, converted

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

On the Hub · Downloads on Model Pulse