jiahuizhang/esm-150m-peptide-fine-tune

Full fine-tune vs facebook/esm2_t30_150M_UR50D. Fine-tune: 100% of the weights changed, across 30 of 30 layers.

Tensors changed: other 122/122, Embeddings 1/31, Norms 122/122, Attention 240/240, lm_head 5/5

On the Hub · Downloads on Model Pulse