Locutusque/Hercules-2.5-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: Embeddings 1/1, Norms 13/65, MLP 96/96, Attention 128/128, lm_head 1/1
9 derivatives checked
- bartowski/ChatHercules-2.5-Mistral-7B-GGUF: Full fine-tune
- mradermacher/Hercules-2.5-Mistral-7B-i1-GGUF: Quantization
- bartowski/OpenHercules-2.5-Mistral-7B-GGUF: Full fine-tune
- nold/ChatHercules-2.5-Mistral-7B-GGUF: Full fine-tune
- featherless-ai-quants/Locutusque-Hercules-2.5-Mistral-7B-GGUF: Quantization
- mradermacher/Hercules-2.5-Mistral-7B-GGUF: Same weights, converted
- hydra-project/ChatHercules-2.5-Mistral-7B: Full fine-tune
- hydra-project/OpenHercules-2.5-Mistral-7B: Full fine-tune
- Nitral-Archive/Prima-Pastacles-7b: Full fine-tune