ai-forever/SMITH-Exp
Full fine-tune vs ai-sage/GigaChat3.1-10B-A1.8B-bf16. Fine-tune: 100% of the weights changed, across 26 of 26 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 27/79, MLP 2671/2696, Attention 104/104
Full fine-tune vs ai-sage/GigaChat3.1-10B-A1.8B-bf16. Fine-tune: 100% of the weights changed, across 26 of 26 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 27/79, MLP 2671/2696, Attention 104/104