KittyLM/kittylm-lfm2.5-2.6b

Partial fine-tune vs LiquidAI/LFM2.5-2.6B. Partial change: 16% of the weights changed (attention, other), in 30 of 30 layers.

Tensors changed: Embeddings 0/2, other 43/66, MLP 0/90, Norms 0/76, Attention 32/32

1 derivatives checked

• KittyLM/kittylm-lfm2.5-2.6b-gguf: Quantization

On the Hub · Downloads on Model Pulse