hydra-project/OpenHercules-2.5-Mistral-7B

Full fine-tune vs Locutusque/Hercules-2.5-Mistral-7B. 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

2 derivatives checked

• mradermacher/OpenHercules-2.5-Mistral-7B-i1-GGUF: Quantization
• mradermacher/OpenHercules-2.5-Mistral-7B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse