argilla/notus-7b-v1
Full fine-tune vs alignment-handbook/zephyr-7b-sft-full. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 19/65, MLP 96/96, Attention 128/128, lm_head 1/1
6 derivatives checked
- TheBloke/notus-7B-v1-GGUF: Quantization
- QuantFactory/notus-7b-v1-GGUF: Quantization
- MaziyarPanahi/notus-7b-v1-GGUF: Quantization
- tensorblock/notus-7b-v1-GGUF: Quantization
- powermove72/Trinity_Notus2-xb: Full fine-tune (fewer layers)
- powermove72/Stealth-Notus-xb: Full fine-tune (fewer layers)