NousResearch/Hermes-3-Llama-3.1-405B
Full fine-tune vs meta-llama/Llama-3.1-405B. Fine-tune: 99% of the weights changed, across 126 of 126 layers.
Tensors changed: Embeddings 0/1, Attention 504/504, MLP 378/378, Norms 244/253, lm_head 1/1
2 derivatives checked
- bartowski/Hermes-3-Llama-3.1-405B-GGUF: Quantization
- DevQuasar/NousResearch.Hermes-3-Llama-3.1-405B-GGUF: Quantization
4 other repos hold byte-for-byte identical weight files.