inclusionAI/Ring-flash-linear-2.0-128k
Full fine-tune vs inclusionAI/Ling-flash-base-2.0. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: MLP 2696/2704, Attention 36/36, Norms 129/129, Embeddings 1/1, lm_head 1/1
Full fine-tune vs inclusionAI/Ling-flash-base-2.0. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: MLP 2696/2704, Attention 36/36, Norms 129/129, Embeddings 1/1, lm_head 1/1