locuslab/safety-classifier_gte-large-en-v1.5
Full fine-tune vs Alibaba-NLP/gte-large-en-v1.5. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 4/4, Attention 144/144, MLP 120/120
Full fine-tune vs Alibaba-NLP/gte-large-en-v1.5. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 4/4, Attention 144/144, MLP 120/120