AI NEWS.ccIgBert
Model pretrained on protein and antibody sequences using a masked language modeling (MLM) objective. It was introduced in the paper Large scale paired antibody language models. The model is finetuned from IgBert-unpaired using paired antibody sequences from the Observed Antibody Space. Note that the tokeniser adds a `[CLS]` token at the beginning of each paired sequence, a `[SEP]` token at the end of each paired sequence and pads using the `[PAD]` token. For example a batch containing sequences `V Q L [SEP] E V V`, `Q V [SEP] A L` will be tokenised to `[CLS] V Q L [SEP] E V V [SEP]` and `[CLS] Q V [SEP] A L [SEP] [PAD] [PAD]`.
번역 준비 중입니다. 원문을 표시합니다.
Model pretrained on protein and antibody sequences using a masked language modeling (MLM) objective. It was introduced in the paper Large scale paired antibody language models. The model is finetuned from IgBert-unpaired using paired antibody sequences from the Observed Antibody Space. Note that the tokeniser adds a `[CLS]` token at the beginning of each paired sequence, a `[SEP]` token at the end of each paired sequence and pads using the `[PAD]` token. For example a batch containing sequences `V Q L [SEP] E V V`, `Q V [SEP] A L` will be tokenised to `[CLS] V Q L [SEP] E V V [SEP]` and `[CLS] Q V [SEP] A L [SEP] [PAD] [PAD]`.