Upload files

.gitattributes

@@ -1,35 +1,27 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text 
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,36 @@
----
-license: mit
----
+---
+language:
+- en
+tags:
+- toxic comments classification
+licenses:
+- cc-by-nc-sa
+---
+
+## Toxicity Classification Model
+
+This model is trained for toxicity classification task. The dataset used for training is the merge of the English parts of the three datasets by **Jigsaw** ([Jigsaw 2018](https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge), [Jigsaw 2019](https://www.kaggle.com/c/jigsaw-unintended-bias-in-toxicity-classification), [Jigsaw 2020](https://www.kaggle.com/c/jigsaw-multilingual-toxic-comment-classification)), containing around 2 million examples. We split it into two parts and fine-tune a RoBERTa model ([RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://arxiv.org/abs/1907.11692)) on it. The classifiers perform closely on the test set of the first Jigsaw competition, reaching the **AUC-ROC** of 0.98 and **F1-score** of 0.76.
+
+## How to use
+```python
+from transformers import RobertaTokenizer, RobertaForSequenceClassification
+
+# load tokenizer and model weights
+tokenizer = RobertaTokenizer.from_pretrained('SkolkovoInstitute/roberta_toxicity_classifier')
+model = RobertaForSequenceClassification.from_pretrained('SkolkovoInstitute/roberta_toxicity_classifier')
+
+# prepare the input
+batch = tokenizer.encode('you are amazing', return_tensors='pt')
+
+# inference
+model(batch)
+```
+
+## Licensing Information
+
+[Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License][cc-by-nc-sa].
+
+[![CC BY-NC-SA 4.0][cc-by-nc-sa-image]][cc-by-nc-sa]
+
+[cc-by-nc-sa]: http://creativecommons.org/licenses/by-nc-sa/4.0/
+[cc-by-nc-sa-image]: https://i.creativecommons.org/l/by-nc-sa/4.0/88x31.png

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "neutral",
+    "1": "toxic"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "neutral": 0,
+    "toxic": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.8.2",
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:896f52af161757594994d1fefe85ac79cbb57c9a96b26fba8ab93139b6426b8c
+size 501037970

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 512}