00000-X/Dolphin-2.6-FC_Hermes-2-DPO

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

Tensors changed: Norms 17/65, MLP 93/96, Attention 124/128

1 derivatives checked

• mradermacher/Dolphin-2.6-FC_Hermes-2-DPO-GGUF: Quantization

On the Hub · Downloads on Model Pulse