L-0-G-1-C/Behemoth-128B-v3-FP8-Dynamic
Full fine-tune vs mistralai/Mistral-Medium-3.5-128B. Fine-tune: 100% of the weights changed, across 88 of 88 layers.
Tensors changed: Embeddings 1/1, Norms 0/177, MLP 264/264, Attention 352/352, lm_head 1/1
Full fine-tune vs mistralai/Mistral-Medium-3.5-128B. Fine-tune: 100% of the weights changed, across 88 of 88 layers.
Tensors changed: Embeddings 1/1, Norms 0/177, MLP 264/264, Attention 352/352, lm_head 1/1