Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp
Full fine-tune vs Intel/neural-chat-7b-v3-3. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 16/65, MLP 93/96, Attention 124/128, lm_head 1/1
3 derivatives checked
- TheBloke/OpenHermes-2.5-neural-chat-v3-3-Slerp-GGUF: Quantization
- mradermacher/OpenHermes-2.5-neural-chat-v3-3-Slerp-i1-GGUF: Quantization
- mradermacher/OpenHermes-2.5-neural-chat-v3-3-Slerp-GGUF: Same weights, converted