Vortex5/MS3.2-24B-Astral-Revenant
Full fine-tune vs ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0. Fine-tune: 98% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 0/81, MLP 117/120, Attention 156/160, lm_head 1/1
2 derivatives checked
- mradermacher/MS3.2-24B-Astral-Revenant-i1-GGUF: Quantization
- mradermacher/MS3.2-24B-Astral-Revenant-GGUF: Quantization