gyung/lfm2-1.2b-koen-mt-v8-rl-10k-merged

Full fine-tune vs LiquidAI/LFM2-1.2B. Fine-tune: 100% of the weights changed, across 16 of 16 layers.

Tensors changed: Embeddings 2/2, other 30/30, MLP 48/48, Norms 32/44, Attention 24/24

1 derivatives checked

• gyung/lfm2-1.2b-koen-mt-v8-rl-10k-merged-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse