I think this model is provided by huggingface and has been downloaded a bunch. However, if you look at the model_config, its only trained on 8 labels (B-PER is missing). Wondering about the training of this model, as conll has a label space of size 9. Thanks!
Related topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
Trying to understand the task-specific head for diff. models + Transformers AutoModel | 0 | 410 | April 20, 2023 | |
How do I fine-tune roberta-large for text classification | 7 | 3714 | December 17, 2021 | |
xlm-Roberta for mlm doesn't predict single one trained sentence properly | 0 | 218 | June 29, 2023 | |
Cant get model jjzha/esco-xlm-roberta-large to run correctly | 0 | 200 | August 24, 2023 | |
Does XLM-R follows RoBERTa or XLM for MLM? | 0 | 396 | June 13, 2022 |