Duplicate from Hate-speech-CNERG/bert-base-uncased-hatexplain

Co-authored-by: Satya <[email protected]>

.gitattributes

@@ -0,0 +1,9 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,25 @@
+---
+language: en
+license: apache-2.0
+datasets:
+  - hatexplain
+---
+The model is used for classifying a text as **Hatespeech**, **Offensive**, or **Normal**. The model is trained using data from Gab and Twitter and *Human Rationales* were included as part of the training data to boost the performance.
+
+The dataset and models are available here: https://github.com/punyajoy/HateXplain
+
+
+**For more details about our paper**
+
+Binny Mathew, Punyajoy Saha, Seid Muhie Yimam, Chris Biemann, Pawan Goyal, and Animesh Mukherjee "[HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection)". Accepted at AAAI 2021.
+
+***Please cite our paper in any published work that uses any of these resources.***
+
+~~~
+@article{mathew2020hatexplain,
+  title={HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection},
+  author={Mathew, Binny and Saha, Punyajoy and Yimam, Seid Muhie and Biemann, Chris and Goyal, Pawan and Mukherjee, Animesh},
+  journal={arXiv preprint arXiv:2012.10289},
+  year={2020}
+}
+~~~

config.json

@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "do_sample": false,
+  "eos_token_ids": null,
+  "finetuning_task": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "hate speech",
+    "1": "normal",
+    "2": "offensive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "hate speech": 0,
+    "normal": 1,
+    "offensive":2
+  },
+  "layer_norm_eps": 1e-12,
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_beams": 1,
+  "num_hidden_layers": 12,
+  "num_labels": 3,
+  "num_return_sequences": 1,
+  "output_attentions": true,
+  "output_hidden_states": false,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pruned_heads": {},
+  "repetition_penalty": 1.0,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "torchscript": false,
+  "type_vocab_size": 2,
+  "use_bfloat16": false,
+  "vocab_size": 30522
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc92239e1ca3c00bf29066fd2422d44134eddd96870b95e531cffcb3db41ab6b
+size 437945404

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7939d499f5c2ec887db9c09d9e790f33321686a4993c6b3da7d89db059a7452e
+size 437988463

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "max_len": 512}