Upload 7 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model_v24_hf_compatible/tokenizer.json filter=lfs diff=lfs merge=lfs -text

model_v24_hf_compatible/README.md

@@ -0,0 +1,25 @@
+# Korean XLM-RoBERTa Classifier (HF Compatible)
+
+This model is converted from a custom classifier to be compatible with Hugging Face Inference API.
+
+## Model Info
+- Base Model: xlm-roberta-base
+- Task: text-classification
+- Language: Korean
+- Labels: 66
+
+## Usage
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+tokenizer = AutoTokenizer.from_pretrained("app/data/studied/model_v24_hf_compatible")
+model = AutoModelForSequenceClassification.from_pretrained("app/data/studied/model_v24_hf_compatible")
+
+# Predict
+inputs = tokenizer("원본 투입물명", return_tensors="pt")
+outputs = model(**inputs)
+predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
+```
+
+## License
+MIT License

model_v24_hf_compatible/config.json

@@ -0,0 +1,166 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002,
+  "problem_type": "single_label_classification",
+  "id2label": {
+    "0": "점결탄",
+    "1": "산화마그네슘",
+    "2": "오븐 코크스",
+    "3": "콜타르",
+    "4": "직접 환원철",
+    "5": "일산화탄소",
+    "6": "천연가스",
+    "7": "갈탄",
+    "8": "페트롤 및 SBP",
+    "9": "역청",
+    "10": "냉각수",
+    "11": "강철",
+    "12": "석회석",
+    "13": "산업폐기물",
+    "14": "메탄",
+    "15": "고로 슬래그",
+    "16": "철 스크랩",
+    "17": "분진",
+    "18": "윤활유",
+    "19": "액화석유가스",
+    "20": "강철 스크랩",
+    "21": "탄산리튬",
+    "22": "경유",
+    "23": "잔류 연료유",
+    "24": "전기",
+    "25": "무연탄",
+    "26": "오일 셰일",
+    "27": "철광석",
+    "28": "탄산수소나트륨",
+    "29": "탄산바륨",
+    "30": "포장재",
+    "31": "액화 천연가스",
+    "32": "슬러지",
+    "33": "소다회",
+    "34": "산화바륨",
+    "35": "가스공장 가스",
+    "36": "폐유",
+    "37": "EAF 탄소 전극",
+    "38": "압연 스케일",
+    "39": "코크스 오븐 가스",
+    "40": "EAF 충전 탄소",
+    "41": "고로가스",
+    "42": "열간성형철 (HBI)",
+    "43": "피트 (Peat)",
+    "44": "선철",
+    "45": "원유",
+    "46": "산소 제강로 가스",
+    "47": "열유입",
+    "48": "절삭칩",
+    "49": "아역청탄",
+    "50": "마그네사이트",
+    "51": "석유 코크스",
+    "52": "펠렛",
+    "53": "오리멀전",
+    "54": "액화 석유가스",
+    "55": "등유",
+    "56": "소성가스",
+    "57": "에탄",
+    "58": "산화칼슘",
+    "59": "나프타",
+    "60": "철",
+    "61": "능철광",
+    "62": "소결광",
+    "63": "고온 성형 환원철",
+    "64": "휘발유",
+    "65": "탄산스트론튬"
+  },
+  "label2id": {
+    "점결탄": 0,
+    "산화마그네슘": 1,
+    "오븐 코크스": 2,
+    "콜타르": 3,
+    "직접 환원철": 4,
+    "일산화탄소": 5,
+    "천연가스": 6,
+    "갈탄": 7,
+    "페트롤 및 SBP": 8,
+    "역청": 9,
+    "냉각수": 10,
+    "강철": 11,
+    "석회석": 12,
+    "산업폐기물": 13,
+    "메탄": 14,
+    "고로 슬래그": 15,
+    "철 스크랩": 16,
+    "분진": 17,
+    "윤활유": 18,
+    "액화석유가스": 19,
+    "강철 스크랩": 20,
+    "탄산리튬": 21,
+    "경유": 22,
+    "잔류 연료유": 23,
+    "전기": 24,
+    "무연탄": 25,
+    "오일 셰일": 26,
+    "철광석": 27,
+    "탄산수소나트륨": 28,
+    "탄산바륨": 29,
+    "포장재": 30,
+    "액화 천연가스": 31,
+    "슬러지": 32,
+    "소다회": 33,
+    "산화바륨": 34,
+    "가스공장 가스": 35,
+    "폐유": 36,
+    "EAF 탄소 전극": 37,
+    "압연 스케일": 38,
+    "코크스 오븐 가스": 39,
+    "EAF 충전 탄소": 40,
+    "고로가스": 41,
+    "열간성형철 (HBI)": 42,
+    "피트 (Peat)": 43,
+    "선철": 44,
+    "원유": 45,
+    "산소 제강로 가스": 46,
+    "열유입": 47,
+    "절삭칩": 48,
+    "아역청탄": 49,
+    "마그네사이트": 50,
+    "석유 코크스": 51,
+    "펠렛": 52,
+    "오리멀전": 53,
+    "액화 석유가스": 54,
+    "등유": 55,
+    "소성가스": 56,
+    "에탄": 57,
+    "산화칼슘": 58,
+    "나프타": 59,
+    "철": 60,
+    "능철광": 61,
+    "소결광": 62,
+    "고온 성형 환원철": 63,
+    "휘발유": 64,
+    "탄산스트론튬": 65
+  },
+  "num_labels": 66
+}

model_v24_hf_compatible/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa9f78463531db7ec98f441bf5676f517c701cc4554814198711c1b465e9c3b8
+size 1112197096

model_v24_hf_compatible/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa9f78463531db7ec98f441bf5676f517c701cc4554814198711c1b465e9c3b8
+size 1112197096

model_v24_hf_compatible/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

model_v24_hf_compatible/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1cc44ad7faaeec47241864835473fd5403f2da94673f3f764a77ebcb0a803ec
+size 17083009

model_v24_hf_compatible/tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}