Downloads · 30 days
11
2% of all-time downloads
hmteams/flair-icdar-fr
flair-icdar-fr is a token classification model from hmteams. Use it when you need labels on individual words, such as names. It is set up for flair. The card lists the license as mit.
This Flair model was fine-tuned on the French ICDAR-Europeana NER Dataset using hmTEAMS as backbone LM.
Downloads · 30 days
11
2% of all-time downloads
All-time downloads
559
Public
Repo size
442 MB
Likes
0
Public
Click a slice to open those files.
.bin441 MB · 100%
From the Hugging Face model README
This Flair model was fine-tuned on the French ICDAR-Europeana NER Dataset using hmTEAMS as backbone LM.
The ICDAR-Europeana NER Dataset is a preprocessed variant of the Europeana NER Corpora for Dutch and French.
The following NEs were annotated: PER, LOC and ORG.
We performed a hyper-parameter search over the following parameters with 5 different seeds per configuration:
[8, 4][3e-05, 5e-05]And report micro F1-score on development set:
| Configuration | Run 1 | Run 2 | Run 3 | Run 4 | Run 5 | Avg. |
|---|---|---|---|---|---|---|
| bs4-e10-lr3e-05 | 0.7764 | 0.7756 | 0.7723 | 0.7682 | 0.7745 | 77.34 ± 0.29 |
| bs8-e10-lr3e-05 | 0.7773 | 0.7676 | 0.7733 | 0.7675 | 0.7726 | 77.17 ± 0.37 |
| bs8-e10-lr5e-05 | 0.7778 | 0.783 | 0.7654 | 0.767 | 0.7644 | 77.15 ± 0.75 |
| bs4-e10-lr5e-05 | 0.7684 | 0.7582 | 0.7626 | 0.7779 | 0.7693 | 76.73 ± 0.67 |
The training log and TensorBoard logs (only for hmByT5 and hmTEAMS based models) are also uploaded to the model hub.
More information about fine-tuning can be found here.
We thank Luisa März, Katharina Schmid and Erion Çano for their fruitful discussions about Historic Language Models.
Research supported with Cloud TPUs from Google's TPU Research Cloud (TRC). Many Thanks for providing access to the TPUs ❤️