allenai/Olmo-Hybrid-Instruct-DPO-7B
Full fine-tune vs allenai/Olmo-Hybrid-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 105/105, Attention 320/320, MLP 96/96
Full fine-tune vs allenai/Olmo-Hybrid-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 105/105, Attention 320/320, MLP 96/96