niranjanh123/lfm-sft-hotter-colder-gemini-simplified-reasoning

Partial fine-tune vs LiquidAI/LFM2.5-1.2B-Thinking. Partial change: 89% of the weights changed (attention, mlp, other), in 16 of 16 layers.

Tensors changed: Embeddings 0/2, other 20/30, MLP 48/48, Norms 0/44, Attention 24/24

On the Hub · Downloads on Model Pulse