Naphula/Goetia-24B-v1

Full fine-tune vs CrucibleLab/M3.2-24B-Loki-V1.3. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Norms 81/81, MLP 120/120, Attention 160/160, lm_head 1/1, Embeddings 1/1

2 derivatives checked

• mradermacher/Goetia-24B-v1-i1-GGUF: Quantization
• mradermacher/Goetia-24B-v1-GGUF: Quantization

On the Hub · Downloads on Model Pulse