jhyuckkim/DeepSeek-V2-Lite-Dense-3B-ACP-K6
Full fine-tune vs deepseek-ai/DeepSeek-V2-Lite. Fine-tune: 100% of the weights changed, across 27 of 27 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 67/82, Attention 108/108
Full fine-tune vs deepseek-ai/DeepSeek-V2-Lite. Fine-tune: 100% of the weights changed, across 27 of 27 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 67/82, Attention 108/108