NousResearch/Nous-Hermes-2-SOLAR-10.7B
Full fine-tune vs upstage/SOLAR-10.7B-v1.0. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Norms 18/97, MLP 144/144, Attention 192/192
11 derivatives checked
- TheBloke/Nous-Hermes-2-SOLAR-10.7B-GGUF: Quantization
- QuantFactory/Nous-Hermes-2-SOLAR-10.7B-GGUF: Quantization
- mradermacher/Nous-Hermes-2-SOLAR-10.7B-i1-GGUF: Quantization
- mradermacher/Nous-Hermes-2-SOLAR-10.7B-GGUF: Same weights, converted
- qwp4w3hyb/Nous-Hermes-2-SOLAR-10.7B-iMat-GGUF: Quantization
- vicgalle/franken-SOLAR-18B-v1.0-GGUF: Full fine-tune (fewer layers)
- lr1729/Nous-Hermes-2-SOLAR-10.7B-GGUF-imatrix: Quantization
- featherless-ai-quants/NousResearch-Nous-Hermes-2-SOLAR-10.7B-GGUF: Quantization
- vicgalle/franken-SOLAR-18B-v1.0: Partial fine-tune (fewer layers)
- steinzer-narayan/fimbulhermes-15B-v0.1: Partial fine-tune (fewer layers)
- mergekit-community/Topsecret: Full fine-tune (fewer layers)