Upload folder using huggingface_hub

README.md

@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+tags:
+- bert
+- kcbert
+- unsmile
+---
+
+# SJ-Donald/kcbert-large-unsmile
+
+SJ-Donald/kcbert-large-unsmile is pretrained model using follow:
+
+## Models
+
+* [beomi/kcbert-large](https://huggingface.co/beomi/kcbert-large)
+
+## Datasets
+
+* [smilegate-ai/kor_unsmile](smilegate-ai/kor_unsmile)
+
+## How to use
+
+```Python
+from transformers import TextClassificationPipeline, BertForSequenceClassification, AutoTokenizer+
+
+model_name = 'SJ-Donald/kcbert-large-unsmile'
+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("이래서 여자는 게임을 하면 안된다")[0]:
+    print(result)
+    
+{'label': '여성/가족', 'score': 0.9793611168861389}
+{'label': '남성', 'score': 0.006330598145723343}
+{'label': '성소수자', 'score': 0.007870828732848167}
+{'label': '인종/국적', 'score': 0.010810344479978085}
+{'label': '연령', 'score': 0.020540334284305573}
+{'label': '지역', 'score': 0.015790466219186783}
+{'label': '종교', 'score': 0.014563685283064842}
+{'label': '기타 혐오', 'score': 0.04097242280840874}
+{'label': '악플/욕설', 'score': 0.019168635830283165}
+{'label': 'clean', 'score': 0.014866289682686329}
+```

config.json

@@ -0,0 +1,56 @@
+{
+  "_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": "\uc5ec\uc131/\uac00\uc871",
+    "1": "\ub0a8\uc131",
+    "2": "\uc131\uc18c\uc218\uc790",
+    "3": "\uc778\uc885/\uad6d\uc801",
+    "4": "\uc5f0\ub839",
+    "5": "\uc9c0\uc5ed",
+    "6": "\uc885\uad50",
+    "7": "\uae30\ud0c0 \ud610\uc624",
+    "8": "\uc545\ud50c/\uc695\uc124",
+    "9": "clean"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "clean": 9,
+    "\uae30\ud0c0 \ud610\uc624": 7,
+    "\ub0a8\uc131": 1,
+    "\uc131\uc18c\uc218\uc790": 2,
+    "\uc545\ud50c/\uc695\uc124": 8,
+    "\uc5ec\uc131/\uac00\uc871": 0,
+    "\uc5f0\ub839": 4,
+    "\uc778\uc885/\uad6d\uc801": 3,
+    "\uc885\uad50": 6,
+    "\uc9c0\uc5ed": 5
+  },
+  "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 sha256:4d3cef41ebb62cb11229c8daa3ac71055a4a823c260498ab2c97e3fe703edfaa
+size 1337649096

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 sha256:3f2aecbc050c591477fb82059d7fd0f2620d3975c89fd14a78c34e6318bf6720
+size 4600