Salesforce/SweRankEmbed-Large

Full fine-tune vs Alibaba-NLP/gte-Qwen2-7B-instruct. Fine-tune: 92% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 37/57, MLP 84/84, Attention 191/196

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

On the Hub · Downloads on Model Pulse