LiquidAI/LFM2.5-VL-1.6B-Extract

Full fine-tune vs LiquidAI/LFM2.5-VL-1.6B. Fine-tune: 100% of the weights changed, across 27 of 27 layers.

Tensors changed: Embeddings 5/5, other 34/34, MLP 150/156, Norms 121/154, Attention 235/240

1 derivatives checked

• LiquidAI/LFM2.5-VL-1.6B-Extract-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse