yamatazen/Ayla-Light-12B-v2

Full fine-tune vs NeverSleep/Lumimaid-v0.2-12B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

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

3 derivatives checked

• mradermacher/Ayla-Light-12B-v2-i1-GGUF: Quantization
• mradermacher/Ayla-Light-12B-v2-GGUF: Quantization
• MaziyarPanahi/Ayla-Light-12B-v2-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse