Cyclone-Labs/Starless-Seraph-31B

Full fine-tune vs BirdToast/Gemma-4-31B-glimmer-rp-v0.1. Fine-tune: 94% of the weights changed, across 60 of 60 layers.

Tensors changed: Embeddings 1/4, Norms 0/523, other 0/62, MLP 180/261, Attention 230/338

2 derivatives checked

• mradermacher/Starless-Seraph-31B-i1-GGUF: Quantization (fewer layers)
• mradermacher/Starless-Seraph-31B-GGUF: Quantization (fewer layers)

On the Hub · Downloads on Model Pulse