Naphula/Goetia-26B-A4B-v1.4
Full fine-tune vs BeaverAI/Orion-26B-A4B-v1b-GGUF. BeaverAI/Orion-26B-A4B-v1b-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: Norms 211/271, Embeddings 1/1, Attention 115/115, MLP 90/90, other 30/30
3 derivatives checked
- mradermacher/Goetia-26B-A4B-v1.4-i1-GGUF: Quantization
- mradermacher/Goetia-26B-A4B-v1.4-GGUF: Quantization
- 26B-Suite/Goetia-26B-A4B-v1.4-LazyLora-heresy: Full fine-tune