mrcuddle/Bagel-Hermes-2-Pro-Llama3-8B

Full fine-tune vs NousResearch/Hermes-2-Pro-Llama-3-8B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 63/65, MLP 93/96, Attention 124/128

2 derivatives checked

• mradermacher/Bagel-Hermes-2-Pro-Llama3-8B-i1-GGUF: Quantization
• mradermacher/Bagel-Hermes-2-Pro-Llama3-8B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse