philipp-zettl/bge-micro-v2-mtg

Full fine-tune vs TaylorAI/bge-micro-v2. Fine-tune: 99% of the weights changed, across 3 of 3 layers.

Tensors changed: Embeddings 5/5, Norms 12/12, Attention 24/24, other 12/14

On the Hub · Downloads on Model Pulse