Hate speech model

added_tokens.json

@@ -0,0 +1 @@
+{"<mask>": 64000}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "vinai/bertweet-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "hateful",
+    "1": "targeted",
+    "2": "aggressive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "aggressive": 2,
+    "hateful": 0,
+    "targeted": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 130,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "tokenizer_class": "BertweetTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdde92a6fa3e710373cdbf8c6ab1fe99918955312351a3344807cdbe15583d6e
+size 539691437

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": "<mask>"}

test_results.json

@@ -0,0 +1,21 @@
+{
+    "test_loss": 0.9019122123718262,
+    "test_hs_f1": 0.6540642722117203,
+    "test_hs_precision": 0.49570200573065903,
+    "test_hs_recall": 0.9611111111111111,
+    "test_tr_f1": 0.6102635228848822,
+    "test_tr_precision": 0.4819277108433735,
+    "test_tr_recall": 0.831758034026465,
+    "test_ag_f1": 0.482573726541555,
+    "test_ag_precision": 0.35405192761605037,
+    "test_ag_recall": 0.7575757575757576,
+    "test_macro_hs_f1_score": 0.548190168321794,
+    "test_emr_no_gating": 0.41133333333333333,
+    "test_emr": 0.4116666666666667,
+    "test_macro_f1": 0.5823004841804504,
+    "test_macro_precision": 0.4438938796520233,
+    "test_macro_recall": 0.8501482605934143,
+    "test_runtime": 6.346,
+    "test_samples_per_second": 472.739,
+    "test_steps_per_second": 29.625
+}

tokenizer_config.json

@@ -0,0 +1 @@
+{"normalization": false, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 128, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "vinai/bertweet-base", "tokenizer_class": "BertweetTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc84f5788a93cec1f8d9335849f002452a3748a72ff1b74818e7a8d827c4e89
+size 2799