deepcogito/cogito-671b-v2.1-FP8
Full fine-tune vs deepseek-ai/DeepSeek-V3-Base. Fine-tune: 100% of the weights changed, across 61 of 61 layers.
Tensors changed: Attention 305/305, Norms 244/245, MLP 1050/1108
Full fine-tune vs deepseek-ai/DeepSeek-V3-Base. Fine-tune: 100% of the weights changed, across 61 of 61 layers.
Tensors changed: Attention 305/305, Norms 244/245, MLP 1050/1108