emplitude/Hermes-2-Pro-Llama-3-8B
Full fine-tune vs NousResearch/Meta-Llama-3-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 63/65, MLP 96/96, Attention 128/128
2 derivatives checked
- mradermacher/Hermes-2-Pro-Llama-3-8B-i1-GGUF: Quantization
- mradermacher/Hermes-2-Pro-Llama-3-8B-GGUF: Same weights, converted
6 other repos hold byte-for-byte identical weight files.