Initial commit

README.md

@@ -0,0 +1,47 @@
+---
+language:
+- en
+metrics:
+- f1
+- accuracy
+pipeline_tag: text-classification
+widget:
+ - text: "Every woman wants to be a model. It's codeword for 'I get everything for free and people want me'"
+---
+### distilbert-base-sexism-detector
+This is a fine-tuned model of distilbert-base on the Explainable Detection of Online Sexism (EDOS) dataset. It is intended to be used as a classification model for identifying tweets (0 - not sexist; 1 - sexist). 
+
+**This is a light model with an 81.2 F1 score. Use this model for fase prediction using the online API, if you like to see our best model with 86.3 F1 score , use this [link](https://huggingface.co/NLP-LTU/BERTweet-large-sexism-detector).**
+
+Classification examples (use these example in the Hosted Inference API in the right panel ):
+
+|Prediction|Tweet|
+|-----|--------|
+|sexist         |Every woman wants to be a model. It's codeword for "I get everything for free and people want me" |
+|not sexist     |basically I placed more value on her than I should then?|
+# More Details 
+For more details  about the datasets and eval results, see (we will updated the page with our paper link)
+# How to use
+```python
+from transformers import AutoModelForSequenceClassification, AutoTokenizer,pipeline
+import torch
+model = AutoModelForSequenceClassification.from_pretrained('NLP-LTU/distilbert-sexism-detector')
+tokenizer = AutoTokenizer.from_pretrained('distilbert-base-uncased') 
+classifier = pipeline("text-classification", model=model, tokenizer=tokenizer)
+prediction=classifier("Every woman wants to be a model. It's codeword for 'I get everything for free and people want me' ")
+label_pred = 'not sexist' if prediction == 0 else 'sexist' 
+
+print(label_pred)
+
+```
+```
+              precision    recall  f1-score   support
+
+  not sexsit     0.9000    0.9264    0.9130      3030
+      sexist     0.7469    0.6784    0.7110       970
+
+    accuracy                         0.8662      4000
+   macro avg     0.8234    0.8024    0.8120      4000
+weighted avg     0.8628    0.8662    0.8640      4000
+
+```

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "distilbert-base-uncased-best-train-dev",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "not sexist",
+    "1": "sexist"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "not sexist": 0,
+    "sexist": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.2",
+  "vocab_size": 30522
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e1995f398a4ca179202ed8e92d78ba758857b8155a1280305adcf821c61d69f
+size 267933570

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a717035cc3023d13b2c4bcb928442181327fed40de336c80caab21a14f4455f6
+size 267852913

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "distilbert-base-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:353096663285e7ec1e521b466139f951bf625aa156dd1ca96c17e60636b29d57
+size 3375