WesPro/OpenDolphin-7B-slerp

Full fine-tune vs dphn/dolphin-2.8-mistral-7b-v02. 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/OpenDolphin-7B-slerp-GGUF: Quantization

On the Hub · Downloads on Model Pulse