KINOX12/DeepSeek-V3.2
Full fine-tune vs deepseek-ai/DeepSeek-V3.2-Exp-Base. Fine-tune: 100% of the weights changed, across 62 of 62 layers.
Tensors changed: Embeddings 2/2, Attention 780/930, Norms 375/376, MLP 1518/1689, lm_head 1/1, other 2/2
Full fine-tune vs deepseek-ai/DeepSeek-V3.2-Exp-Base. Fine-tune: 100% of the weights changed, across 62 of 62 layers.
Tensors changed: Embeddings 2/2, Attention 780/930, Norms 375/376, MLP 1518/1689, lm_head 1/1, other 2/2