Upload folder using huggingface_hub

README.md

@@ -0,0 +1,45 @@
+---
+license: apache-2.0
+tags:
+- bert
+- kcbert
+- kor-hate-sentence
+- sentimental-analysis
+---
+
+# SJ-Donald/kor-hate-sentence
+
+SJ-Donald/kor-hate-sentence is pretrained model using follow:
+
+## Models
+
+* [beomi/kcbert-large](https://huggingface.co/beomi/kcbert-large)
+
+## Datasets
+
+* [SJ-Donald/kor-hate-sentence](https://huggingface.co/datasets/SJ-Donald/kor-hate-sentence)
+
+## How to use
+
+```Python
+from transformers import TextClassificationPipeline, BertForSequenceClassification, AutoTokenizer+
+
+model_name = 'SJ-Donald/kor-hate-sentence-large'
+model = BertForSequenceClassification.from_pretrained(model_name)
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+pipe = TextClassificationPipeline(
+    model = model,
+    tokenizer = tokenizer,
+    device = 0,   # cpu: -1, gpu: gpu number
+    return_all_scores = True,
+    function_to_apply = 'sigmoid'
+)
+
+for result in pipe("이딴 게임할 거면 방송 그만해라 어휴")[0]:
+    print(result)
+
+{'label': 'hate', 'score': 0.016597675159573555}
+{'label': 'clean', 'score': 0.9842987060546875}
+```

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "beomi/kcbert-large",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "hate",
+    "1": "clean"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "clean": 1,
+    "hate": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 300,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:254c49e80b045593739e0a1bd38f051b62dae738ff73b79bbfd6bc3cd99d6ca2
+size 1337616296

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 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 300,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf886eddc1d43f2f0efdee75b2595756368c96bc5f79257d8ba9c3bc152d5577
+size 4600