powermove72/Stealth-Notus-xb
Full fine-tune (fewer layers) vs argilla/notus-7b-v1. argilla/notus-7b-v1 matches part of powermove72/Stealth-Notus-xb (291 of its 453 tensors; the rest of powermove72/Stealth-Notus-xb has no counterpart). On the shared part: Fine-tune: 98% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 46/65, MLP 96/96, Attention 128/128, lm_head 0/1
1 derivatives checked
- mradermacher/Stealth-Notus-xb-GGUF: Quantization