NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT
Full fine-tune vs mistralai/Mixtral-8x7B-v0.1. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: MLP 768/768, other 32/32, Norms 37/65, Attention 128/128
7 derivatives checked
- mradermacher/Nous-Hermes-2-Mixtral-8x7B-SFT-i1-GGUF: Quantization
- TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF: Not comparable yet
- mradermacher/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF: Quantization
- second-state/Nous-Hermes-2-Mixtral-8x7B-SFT-GGUF: Not comparable yet
- TheBloke/Nous-Hermes-2-Mixtral-8x7B-SFT-GPTQ: Quantization
- MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Wikihow: Adapter
- MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Alpaca: Adapter