Update README.md
Browse files
README.md
CHANGED
@@ -1,18 +1,18 @@
|
|
1 |
---
|
2 |
language:
|
3 |
- en
|
4 |
-
|
5 |
tags:
|
6 |
- roberta
|
7 |
- toxic
|
8 |
- toxicity
|
9 |
- hate speech
|
10 |
- offensive language
|
|
|
11 |
---
|
12 |
|
13 |
# Text Classification Toxicity
|
14 |
|
15 |
-
This model is a fined-tuned version of [
|
16 |
The quantized version in ONNX format can be found [here](https://huggingface.co/minuva/MiniLMv2-toxic-jigaw-lite-onnx).
|
17 |
|
18 |
The model contains two labels only (toxicity and severe toxicity). For the model with all labels refer to this [page](https://huggingface.co/minuva/MiniLMv2-toxic-jijgsaw)
|
@@ -47,5 +47,4 @@ The following hyperparameters were used during training:
|
|
47 |
|
48 |
# Deployment
|
49 |
|
50 |
-
Check our [repository](https://github.com/minuva/
|
51 |
-
|
|
|
1 |
---
|
2 |
language:
|
3 |
- en
|
|
|
4 |
tags:
|
5 |
- roberta
|
6 |
- toxic
|
7 |
- toxicity
|
8 |
- hate speech
|
9 |
- offensive language
|
10 |
+
license: apache-2.0
|
11 |
---
|
12 |
|
13 |
# Text Classification Toxicity
|
14 |
|
15 |
+
This model is a fined-tuned version of [MiniLMv2-L6-H384](https://huggingface.co/nreimers/MiniLMv2-L6-H384-distilled-from-BERT-Large) on the on the [Jigsaw 1st Kaggle competition](https://www.kaggle.com/competitions/jigsaw-toxic-comment-classification-challenge) dataset using [unitary/toxic-bert](https://huggingface.co/unitary/toxic-bert) as teacher model.
|
16 |
The quantized version in ONNX format can be found [here](https://huggingface.co/minuva/MiniLMv2-toxic-jigaw-lite-onnx).
|
17 |
|
18 |
The model contains two labels only (toxicity and severe toxicity). For the model with all labels refer to this [page](https://huggingface.co/minuva/MiniLMv2-toxic-jijgsaw)
|
|
|
47 |
|
48 |
# Deployment
|
49 |
|
50 |
+
Check our [fast-nlp-text-toxicity repository](https://github.com/minuva/fast-nlp-text-toxicity) for a FastAPI and ONNX based server to deploy this model on CPU devices.
|
|