Naphula/Goetia-8B-v1

Full fine-tune vs Babsie/ThetaBlackGorgon-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128

3 derivatives checked

• mradermacher/Goetia-8B-v1-i1-GGUF: Quantization
• mradermacher/Goetia-8B-v1-GGUF: Same weights, converted
• Naphula/Goetia-8B-v1-GGUF: Quantization

On the Hub · Downloads on Model Pulse