Update README.md
Browse files
README.md
CHANGED
|
@@ -6,7 +6,34 @@ language:
|
|
| 6 |
pipeline_tag: text-classification
|
| 7 |
---
|
| 8 |
|
| 9 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
|
| 11 |
Citation
|
| 12 |
--------
|
|
|
|
| 6 |
pipeline_tag: text-classification
|
| 7 |
---
|
| 8 |
|
| 9 |
+
|
| 10 |
+
Bloomz-560m-guardrail
|
| 11 |
+
---------------------
|
| 12 |
+
|
| 13 |
+
We introduce the Bloomz-560m-guardrail model, which is a fine-tuning of the [Bloomz-560m-sft-chat](https://huggingface.co/cmarkea/bloomz-560m-sft-chat) model. This model is designed to detect the toxicity of a text in three modes:
|
| 14 |
+
|
| 15 |
+
Obscene: Content that is offensive, indecent, or morally inappropriate, especially in relation to social norms or standards of decency.
|
| 16 |
+
Sexual explicit: Content that presents explicit sexual aspects in a clear and detailed manner.
|
| 17 |
+
Identity attack: Content that aims to attack, denigrate, or harass someone based on their identity, especially related to characteristics such as race, gender, sexual orientation, religion, ethnic origin, or other personal aspects.
|
| 18 |
+
Insult: Offensive, disrespectful, or hurtful content used to attack or denigrate a person.
|
| 19 |
+
Threat: Content that presents a direct threat to an individual.
|
| 20 |
+
|
| 21 |
+
Training
|
| 22 |
+
--------
|
| 23 |
+
|
| 24 |
+
The training dataset consists of 500k examples of comments in English and 500k comments in French (translated by Google Translate), each annotated with a toxicity severity gradient. The dataset used is provided by [Jigsaw](https://jigsaw.google.com/) as part of a Kaggle competition : [Jigsaw Unintended Bias in Toxicity Classification](https://www.kaggle.com/competitions/jigsaw-unintended-bias-in-toxicity-classification/data). Since the scores represent severity gradients, regression was preferred using the following loss function:
|
| 25 |
+
|
| 26 |
+
Benchmark
|
| 27 |
+
---------
|
| 28 |
+
|
| 29 |
+
As the scores range from 0 to 1, a performance measure such as MAE or RMSE may be challenging to interpret. Therefore, Pearson's inter-correlation was chosen as a measure. Pearson's inter-correlation is a measure ranging from -1 to 1, where 0 represents no correlation, -1 represents perfect negative correlation, and 1 represents perfect positive correlation. The goal is to quantitatively measure the correlation between the model's scores and the scores assigned by judges for 750 comments not seen during training.
|
| 30 |
+
|
| 31 |
+
| Model | Language | Obsecene (x100) | Sexual explicit (x100) | Identity attack (x100) | Insult (x100) | Threat (x100) |
|
| 32 |
+
|-------------------------------------------------------------------------------|----------|:-----------------------:|-------------------------------|-------------------------------|----------------------|----------------------|
|
| 33 |
+
| [Bloomz-560m-guardrail](https://huggingface.co/cmarkea/bloomz-560m-guardrail) | French | 62 | 73 | 73 | 68 | 61 |
|
| 34 |
+
| [Bloomz-560m-guardrail](https://huggingface.co/cmarkea/bloomz-560m-guardrail) | English | 63 | 61 | 63 | 67 | 55 |
|
| 35 |
+
| [Bloomz-3b-guardrail](https://huggingface.co/cmarkea/bloomz-3b-guardrail) | Frnech | 72 | 82 | 80 | 78 | 77 |
|
| 36 |
+
| [Bloomz-3b-guardrail](https://huggingface.co/cmarkea/bloomz-3b-guardrail) | English | 76 | 78 | 77 | 75
|
| 37 |
|
| 38 |
Citation
|
| 39 |
--------
|