BidirLM/BidirLM-1B-Embedding
Full fine-tune vs BidirLM/BidirLM-1B-Base. Fine-tune: 100% of the weights changed, across 26 of 26 layers.
Tensors changed: Embeddings 1/1, Norms 77/157, MLP 78/78, Attention 104/104
Full fine-tune vs BidirLM/BidirLM-1B-Base. Fine-tune: 100% of the weights changed, across 26 of 26 layers.
Tensors changed: Embeddings 1/1, Norms 77/157, MLP 78/78, Attention 104/104