Cyclone-Labs/Dusky-Rose-31B

Full fine-tune vs MRockatansky/Gemma-4-31B-Storymaxxed3. Fine-tune: 100% of the weights changed, across 60 of 60 layers.

Tensors changed: Embeddings 4/4, Norms 0/523, other 0/62, MLP 261/261, Attention 338/338

2 derivatives checked

• mradermacher/Dusky-Rose-31B-i1-GGUF: Quantization (fewer layers)
• mradermacher/Dusky-Rose-31B-GGUF: Quantization (fewer layers)

On the Hub · Downloads on Model Pulse