Cyclone-Labs/Solar-Griffin-26B-A4B
Full fine-tune vs Cyclone-Labs/Eclipsed-Phoenix-26B-A4B. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 4/4, MLP 231/231, Norms 92/433, other 30/122, Attention 223/223
2 derivatives checked
- mradermacher/Solar-Griffin-26B-A4B-i1-GGUF: Quantization
- mradermacher/Solar-Griffin-26B-A4B-GGUF: Quantization