XLM-RoBERTa token classifier
The captured configuration identifies XLMRobertaForTokenClassification with an xlm-roberta model type.
Open Source Model Profile · 51la5
roberta-large-NER
roberta-large-NER is an XLM-RoBERTa token-classification model from 51la5. Its model card describes it as XLM-RoBERTa-large fine-tuned on CoNLL-2003 in English.
- Publisher
- 51la5
- Task
- token-classification
- Model type
- xlm-roberta
- License
- Unknown
- Library
- transformers
- Publication status
- Approved for indexing
Model overview
51la5 publishes roberta-large-NER as a transformers token-classification model. Captured config identifies XLMRobertaForTokenClassification with an xlm-roberta model type. Hub tags include pytorch, rust, multilingual, and many language codes. The captured card heading is xlm-roberta-large-finetuned-conll03-english. No parameter count or license value was extracted.
Recorded capabilities
Publisher CoNLL-2003 note
The model card says this checkpoint is XLM-RoBERTa-large fine-tuned with the CoNLL-2003 dataset in English.
Multilingual hub tags
Hub tags include multilingual plus a long list of language codes. The card also says XLM-RoBERTa was trained on 100 languages, while this fine-tune is described as English CoNLL-2003.
Use cases in the source record
- Token-classification workflows. The model card lists named entity recognition and part-of-speech tagging as potential downstream uses.
Limitations and unknowns
- No evaluation results were extracted from this record.
- No parameter count was extracted from this record.
- No license value was extracted; the captured card says more information is needed.
- Provider state is historical snapshot data, not independently refreshed current availability.
- XLM-RoBERTa-large parentage, CoNLL-2003 fine-tuning, and multilingual pretraining claims come from the publisher model card and have not been independently verified by Ethen.
- The repository name is not treated as independent evidence of a RoBERTa-large English NER head beyond the captured config and card.
Source and provenance
Source: 51la5/roberta-large-NER
Captured: Unknown. Processed: 2026-09-07T19:34:27.913258+00:00.
xlm-roberta-large-finetuned-conll03-english Table of Contents Model Details Uses Bias, Risks, and Limitations Training Evaluation Environmental Impact Technical Specifications Citation Model Card Authors How To Get Started With the Model Model Details Model Description The XLM-RoBERTa model was proposed in Unsupervised Cross-lingual Representation Learning at Scale by Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer and Veselin Stoyanov. It is based on Facebook's RoBERTa model released in 2019. It is a large multi-lingual language model…
F001F002F003F004F005F006F007F008F009F012F013F014