talentguide/talentclef-biencoder-v1

Full fine-tune vs jjzha/esco-xlm-roberta-large. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: Embeddings 3/3, Attention 192/192, other 96/98

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse