Vortex5/MS3.2-24B-Stellar-Skies

Full fine-tune vs TheDrummer/Cydonia-24B-v4. Fine-tune: 95% of the weights changed, across 40 of 40 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 0/81, MLP 113/120, Attention 160/160

2 derivatives checked

• mradermacher/MS3.2-24B-Stellar-Skies-i1-GGUF: Quantization
• mradermacher/MS3.2-24B-Stellar-Skies-GGUF: Quantization

On the Hub · Downloads on Model Pulse