Locutusque/Hercules-1.0-Mistral-7B
Full fine-tune vs mistralai/Mistral-7B-v0.1. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128
2 derivatives checked
- MaziyarPanahi/Hercules-1.0-Mistral-7B-GGUF: Quantization
- mradermacher/Hercules-1.0-Mistral-7B-i1-GGUF: Quantization