EryriLabs/LFM2.5-VL-3B-DragOn

Full fine-tune vs LiquidAI/LFM2.5-VL-3B. Fine-tune: 91% of the weights changed, across 30 of 30 layers.

Tensors changed: Embeddings 0/5, other 45/70, MLP 144/198, Norms 0/186, Attention 140/248

1 derivatives checked

• EryriLabs/LFM2.5-VL-3B-DragOn-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse