Skip to content

Commit

Permalink
[wip] Update
Browse files Browse the repository at this point in the history
  • Loading branch information
ljvmiranda921 committed Aug 8, 2024
1 parent ebceb8f commit 8c160ce
Show file tree
Hide file tree
Showing 2 changed files with 11 additions and 6 deletions.
9 changes: 6 additions & 3 deletions models/v0.1.0-gliner/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,21 +2,22 @@

# 🪐 Weasel Project: Release v0.1.0-gliner

oijwiofj
This is a spaCy project that trains and evaluates new v0.1.0-gliner models.
[GliNER](https://github.com/urchade/GLiNER) (Generalist and Lightweight Model for Named Entity Recognition) is a powerful model capable of identifying any entity type using a BERT-like encoder.
In this project, we finetune the GliNER model with the TLUnified-NER training dataset.

To replicate training, first you need to install the required dependencies:

```
```sh
pip install -r requirements.txt
```

## Training

To train a GliNER model, run the `finetune-*` workflow like so:

```
```sh
python -m spacy project run finetune-gliner-sm
python -m spacy project run finetune-gliner-md
python -m spacy project run finetune-gliner-lg
Expand All @@ -30,10 +31,12 @@ The models are currently [based on the v2.5 version of GliNER](https://huggingfa

To perform evals, run the `eval-*` workflows:

```
```sh
python -m spacy project run eval-gliner-sm
python -m spacy project run eval-gliner-md
python -m spacy project run eval-gliner-lg
# eval all at once
python -m spacy project run eval-all
```

This will evaluate on TLUnified-NER's test set ([Miranda, 2023](https://aclanthology.org/2023.sealp-1.2.pdf) and the Tagalog subsets of
Expand Down
8 changes: 5 additions & 3 deletions models/v0.1.0-gliner/project.yml
Original file line number Diff line number Diff line change
Expand Up @@ -7,15 +7,15 @@ description: |
To replicate training, first you need to install the required dependencies:
```
```sh
pip install -r requirements.txt
```
## Training
To train a GliNER model, run the `finetune-*` workflow like so:
```
```sh
python -m spacy project run finetune-gliner-sm
python -m spacy project run finetune-gliner-md
python -m spacy project run finetune-gliner-lg
Expand All @@ -29,10 +29,12 @@ description: |
To perform evals, run the `eval-*` workflows:
```
```sh
python -m spacy project run eval-gliner-sm
python -m spacy project run eval-gliner-md
python -m spacy project run eval-gliner-lg
# eval all at once
python -m spacy project run eval-all
```
This will evaluate on TLUnified-NER's test set ([Miranda, 2023](https://aclanthology.org/2023.sealp-1.2.pdf) and the Tagalog subsets of
Expand Down

0 comments on commit 8c160ce

Please sign in to comment.