Nitral-Archive/NightWing3_Virtuoso-10B-v0.2
Full fine-tune vs Nitral-Archive/NightWing3-10B-v0.1. Fine-tune: 98% of the weights changed, across 40 of 40 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 55/81, MLP 117/120, Attention 156/160
3 derivatives checked
- mradermacher/NightWing3_Virtuoso-10B-v0.2-i1-GGUF: Quantization
- mradermacher/NightWing3_Virtuoso-10B-v0.2-GGUF: Same weights, converted
- LWDCLS/NightWing3_Virtuoso-10B-v0.2-GGUF-IQ-Imatrix: Same weights, converted