congruence-engine
/

gliner_2.5_textile_industry_historic

Token Classification

Model card Files Files and versions Community

max-long commited on Jan 10

Commit

e5e08e3

·

verified ·

1 Parent(s): f503f3d

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -102,7 +102,7 @@ The model was fine-tuned using the following sources:
 1. Synthetic sentences generated using OpenAI's GPT4o model, based on historic textile glossaries compiled from digitised books (2,504 examples)
 2. A subset of the Pile-NER-type dataset (4,000 examples, to avoid overfitting)
-Dataset card: [max-long/textile_glossaries_and_pile_ner](https://huggingface.co/datasets/max-long/textile_glossaries_and_pile_ner)
 For a full description of how the synthetic data was generated, you can consult [this notebook](https://github.com/congruence-engine/universal-ner-with-gliner/blob/main/code/gliner_synthetic_data.ipynb). A Colab version is available [here](https://colab.research.google.com/drive/1SBRU3RMiWcwAskJ18UD2MgwME8FALt8J?usp=sharing).

 1. Synthetic sentences generated using OpenAI's GPT4o model, based on historic textile glossaries compiled from digitised books (2,504 examples)
 2. A subset of the Pile-NER-type dataset (4,000 examples, to avoid overfitting)
+Dataset card: [max-long/textile_glossaries_and_pile_ner](https://huggingface.co/datasets/congruence-engine/textile_glossaries_and_pile_ner)
 For a full description of how the synthetic data was generated, you can consult [this notebook](https://github.com/congruence-engine/universal-ner-with-gliner/blob/main/code/gliner_synthetic_data.ipynb). A Colab version is available [here](https://colab.research.google.com/drive/1SBRU3RMiWcwAskJ18UD2MgwME8FALt8J?usp=sharing).