inclusionAI/Ring-mini-linear-2.0
Full fine-tune vs inclusionAI/Ling-mini-base-2.0-20T. Fine-tune: 100% of the weights changed, across 20 of 20 layers.
Tensors changed: MLP 2725/2729, Embeddings 1/1, lm_head 1/1, Attention 24/24, Norms 81/81
Full fine-tune vs inclusionAI/Ling-mini-base-2.0-20T. Fine-tune: 100% of the weights changed, across 20 of 20 layers.
Tensors changed: MLP 2725/2729, Embeddings 1/1, lm_head 1/1, Attention 24/24, Norms 81/81