perplexity-ai/pplx-embed-v1-late-0.6b

Full fine-tune vs perplexity-ai/pplx-embed-v1-0.6b. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Norms 113/113, MLP 84/84, Attention 112/112

On the Hub · Downloads on Model Pulse