Foxlum/VioletLight

Full fine-tune vs ohyeah1/Violet-Lyra-Gutenberg-v2. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Norms 33/81, MLP 120/120, Attention 160/160

3 derivatives checked

• mradermacher/VioletLight-i1-GGUF: Quantization
• mradermacher/VioletLight-GGUF: Quantization
• Foxlum/NeonViolin: Full fine-tune

On the Hub · Downloads on Model Pulse