Jiang Mj

esm c (esmc-300m-2024-12 or esmc-600m-2024-12): AttributeError: property 'cls_token' of 'EsmSequenceTokenizer' object has no setter.

2

When using the latest version of esmc (esmc==3.2.0), the code "model = ESMC.from_pretrained("esmc_300m")" throws the following error: AttributeError: property 'cls_token' of 'EsmSequenceTokenizer' object has no setter. Currently, there appears to...

Why does the embedding generated by ESMC have two more tokens than the sequence length?

1

When using ESMC to generate embeddings, two additional tokens are added. Suppose the input sequence has length “seq_len” , then the shape of the embedding generated by ESMC is (1,...