mavis8368/Xing4.0-29B-A4B-MTDR
Full fine-tune vs XingChen-AGI/Xing4.0-29B-A4B. Fine-tune: 100% of the weights changed, across 41 of 41 layers.
Tensors changed: Embeddings 2/2, Norms 168/168, MLP 1982/1982, Attention 205/205, lm_head 1/1, other 2/2
Full fine-tune vs XingChen-AGI/Xing4.0-29B-A4B. Fine-tune: 100% of the weights changed, across 41 of 41 layers.
Tensors changed: Embeddings 2/2, Norms 168/168, MLP 1982/1982, Attention 205/205, lm_head 1/1, other 2/2