public upload

README.md

@@ -0,0 +1,33 @@
+---
+language: en
+tags:
+- text classification
+- hate speech
+- offensive language
+- hatecheck
+datasets:
+- unhcr-hatespeech
+metrics:
+- f1
+- hatecheck
+---
+
+Frederik Gaasdal Jensen • Henry Stoll • Sippo Rossi • Raghava Rao Mukkamala
+
+# UNHCR Hate Speech Detection Model
+This is a transformer model that can detect hate and offensive speech for English text. The primary use-case of this model is to detect hate speech targeted at refugees.  The model is based on *roberta-uncased* and was fine-tuned on 12 abusive language datasets.
+
+The model has been developed as a collaboration between UNHCR, the UN Refugee Agency, and Copenhagen Business School.
+
+- F1-score on test set (10% of the overall dataset): 81%
+- Hatecheck score: 90.3% 
+
+## Labels
+
+```python
+{
+  0: "Normal",
+  1: "Offensive",
+  2: "Hate speech",
+}
+```

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "./artifacts/model-3hpf0mjh:v0",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Normal",
+    "1": "Offensive",
+    "2": "Hate speech"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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": "4.16.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53665af5a4f1a98622efb8141bea03e05fc525cd6887b284e07f28befba37a37
+size 498674349

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 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}