Upload 5 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,166 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "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": 1024,
+  "id2label": {
+    "0": "B-AerospaceManufacturer",
+    "1": "B-AnatomicalStructure",
+    "2": "B-ArtWork",
+    "3": "B-Artist",
+    "4": "B-Athlete",
+    "5": "B-CarManufacturer",
+    "6": "B-Cleric",
+    "7": "B-Clothing",
+    "8": "B-Disease",
+    "9": "B-Drink",
+    "10": "B-Facility",
+    "11": "B-Food",
+    "12": "B-HumanSettlement",
+    "13": "B-MedicalProcedure",
+    "14": "B-Medication/Vaccine",
+    "15": "B-MusicalGRP",
+    "16": "B-MusicalWork",
+    "17": "B-ORG",
+    "18": "B-OtherLOC",
+    "19": "B-OtherPER",
+    "20": "B-OtherPROD",
+    "21": "B-Politician",
+    "22": "B-PrivateCorp",
+    "23": "B-PublicCorp",
+    "24": "B-Scientist",
+    "25": "B-Software",
+    "26": "B-SportsGRP",
+    "27": "B-SportsManager",
+    "28": "B-Station",
+    "29": "B-Symptom",
+    "30": "B-Vehicle",
+    "31": "B-VisualWork",
+    "32": "B-WrittenWork",
+    "33": "I-AerospaceManufacturer",
+    "34": "I-AnatomicalStructure",
+    "35": "I-ArtWork",
+    "36": "I-Artist",
+    "37": "I-Athlete",
+    "38": "I-CarManufacturer",
+    "39": "I-Cleric",
+    "40": "I-Clothing",
+    "41": "I-Disease",
+    "42": "I-Drink",
+    "43": "I-Facility",
+    "44": "I-Food",
+    "45": "I-HumanSettlement",
+    "46": "I-MedicalProcedure",
+    "47": "I-Medication/Vaccine",
+    "48": "I-MusicalGRP",
+    "49": "I-MusicalWork",
+    "50": "I-ORG",
+    "51": "I-OtherLOC",
+    "52": "I-OtherPER",
+    "53": "I-OtherPROD",
+    "54": "I-Politician",
+    "55": "I-PrivateCorp",
+    "56": "I-PublicCorp",
+    "57": "I-Scientist",
+    "58": "I-Software",
+    "59": "I-SportsGRP",
+    "60": "I-SportsManager",
+    "61": "I-Station",
+    "62": "I-Symptom",
+    "63": "I-Vehicle",
+    "64": "I-VisualWork",
+    "65": "I-WrittenWork",
+    "66": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-AerospaceManufacturer": 0,
+    "B-AnatomicalStructure": 1,
+    "B-ArtWork": 2,
+    "B-Artist": 3,
+    "B-Athlete": 4,
+    "B-CarManufacturer": 5,
+    "B-Cleric": 6,
+    "B-Clothing": 7,
+    "B-Disease": 8,
+    "B-Drink": 9,
+    "B-Facility": 10,
+    "B-Food": 11,
+    "B-HumanSettlement": 12,
+    "B-MedicalProcedure": 13,
+    "B-Medication/Vaccine": 14,
+    "B-MusicalGRP": 15,
+    "B-MusicalWork": 16,
+    "B-ORG": 17,
+    "B-OtherLOC": 18,
+    "B-OtherPER": 19,
+    "B-OtherPROD": 20,
+    "B-Politician": 21,
+    "B-PrivateCorp": 22,
+    "B-PublicCorp": 23,
+    "B-Scientist": 24,
+    "B-Software": 25,
+    "B-SportsGRP": 26,
+    "B-SportsManager": 27,
+    "B-Station": 28,
+    "B-Symptom": 29,
+    "B-Vehicle": 30,
+    "B-VisualWork": 31,
+    "B-WrittenWork": 32,
+    "I-AerospaceManufacturer": 33,
+    "I-AnatomicalStructure": 34,
+    "I-ArtWork": 35,
+    "I-Artist": 36,
+    "I-Athlete": 37,
+    "I-CarManufacturer": 38,
+    "I-Cleric": 39,
+    "I-Clothing": 40,
+    "I-Disease": 41,
+    "I-Drink": 42,
+    "I-Facility": 43,
+    "I-Food": 44,
+    "I-HumanSettlement": 45,
+    "I-MedicalProcedure": 46,
+    "I-Medication/Vaccine": 47,
+    "I-MusicalGRP": 48,
+    "I-MusicalWork": 49,
+    "I-ORG": 50,
+    "I-OtherLOC": 51,
+    "I-OtherPER": 52,
+    "I-OtherPROD": 53,
+    "I-Politician": 54,
+    "I-PrivateCorp": 55,
+    "I-PublicCorp": 56,
+    "I-Scientist": 57,
+    "I-Software": 58,
+    "I-SportsGRP": 59,
+    "I-SportsManager": 60,
+    "I-Station": 61,
+    "I-Symptom": 62,
+    "I-Vehicle": 63,
+    "I-VisualWork": 64,
+    "I-WrittenWork": 65,
+    "O": 66
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a859dfefac361bf86833c28702ff5ec4755be86a1aa0de5a729c94f021e54d5
+size 2235686564

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>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
+size 17082832

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "add_prefix_space": true,
+  "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": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}