Flolep2607/grpo-product-search-lfm
Full fine-tune vs LiquidAI/LFM2.5-230M. Fine-tune: 100% of the weights changed, across 14 of 14 layers.
Tensors changed: Embeddings 1/2, other 24/24, MLP 42/42, Norms 9/40, Attention 24/24
Full fine-tune vs LiquidAI/LFM2.5-230M. Fine-tune: 100% of the weights changed, across 14 of 14 layers.
Tensors changed: Embeddings 1/2, other 24/24, MLP 42/42, Norms 9/40, Attention 24/24