Null-Guard/LFM2.5-230M-distilled-Gemini-3.8-Flash

Partial fine-tune vs LiquidAI/LFM2.5-230M. Partial change: 71% of the weights changed (attention, mlp, other), in 14 of 14 layers.

Tensors changed: Embeddings 0/2, other 16/24, MLP 42/42, Norms 0/40, Attention 24/24

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse