NousResearch/Hermes-2-Pro-Llama-3-70B
Full fine-tune vs NousResearch/Meta-Llama-3-70B. Fine-tune: 99% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 0/1, Norms 157/161, MLP 240/240, Attention 320/320, lm_head 1/1
5 derivatives checked
- mradermacher/Hermes-2-Pro-Llama-3-70B-i1-GGUF: Quantization
- mradermacher/Hermes-2-Pro-Llama-3-70B-GGUF: Quantization
- featherless-ai-quants/NousResearch-Hermes-2-Pro-Llama-3-70B-GGUF: Quantization
- DevQuasar-9/NousResearch.Hermes-2-Pro-Llama-3-70B-GGUF: Quantization
- CaioXapelaum/Hermes-2-Pro-Llama-3.1-70B: Full fine-tune