joseeangel/bert-base-uncased-conll2003-ner
token-classification model by joseeangel
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
bert-base-uncased adapted to Named entity recognition (CoNLL-2003) with Full fine-tuning. Produced for the assignment U2T01 - Adapting BERT for NLP tasks (Trends in Data Science). The delivered method was chosen by measurement, not by default: the table below is the full set of adaptation methods trained for this task, and this repository holds the winner. Tagging English newswire text with PER / ORG / LOC / MISC entity spans in BIO format. Out of scope: any use where an error carries real cost without a human in the loop, and any language or domain other than the one above. A freshly initialised head and pretrained encoder weights are trained in two parameter groups with separate learning rates; a single shared rate either starves the head or destroys pretrained features. Held-out test split, never seen during training or model selection. Single run per configuration with a fixed seed.…
Read the full model card ↗ · Preview checked 2026-09-21T07:41:42.195Z
Inside the original model card — Document outline
- joseeangel/bert-base-uncased-conll2003-ner
- Intended use
- Training data
- Adaptation method
- Evaluation
- What every method scored on this task
- Labels
- How to use
- Limitations and bias
- References
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
joseeangel/bert-base-uncased-conll2003-ner is a token-classification model repository published by joseeangel on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- token-classification
- Library
- transformers
- Recent downloads (30 days)
- 0
- Cumulative likes
- 0
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 108,898,569
- Architecture
- BertForTokenClassification
- License
- apache-2.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-21T06:26:25.000Z
- Last modified
- 2026-09-21T06:26:45.000Z
Compatibility and lineage
Reported languages: en
Reported base models: bert-base-uncased
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-09-21T06:36:48.800Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.