config files uploaded

.gitattributes

@@ -32,3 +32,4 @@ 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 +1,77 @@
+{
+  "_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,
+  "id2label": {
+    "0": "Arabic",
+    "1": "Chinese",
+    "2": "Dutch",
+    "3": "English",
+    "4": "Estonian",
+    "5": "French",
+    "6": "Hindi",
+    "7": "Indonesian",
+    "8": "Japanese",
+    "9": "Korean",
+    "10": "Latin",
+    "11": "Persian",
+    "12": "Portugese",
+    "13": "Pushto",
+    "14": "Romanian",
+    "15": "Russian",
+    "16": "Spanish",
+    "17": "Swedish",
+    "18": "Tamil",
+    "19": "Thai",
+    "20": "Turkish",
+    "21": "Urdu"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Arabic": 0,
+    "Chinese": 1,
+    "Dutch": 2,
+    "English": 3,
+    "Estonian": 4,
+    "French": 5,
+    "Hindi": 6,
+    "Indonesian": 7,
+    "Japanese": 8,
+    "Korean": 9,
+    "Latin": 10,
+    "Persian": 11,
+    "Portugese": 12,
+    "Pushto": 13,
+    "Romanian": 14,
+    "Russian": 15,
+    "Spanish": 16,
+    "Swedish": 17,
+    "Tamil": 18,
+    "Thai": 19,
+    "Turkish": 20,
+    "Urdu": 21
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

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 sha256:46afe88da5fd71bdbab5cfab5e84c1adce59c246ea5f9341bbecef061891d0a7
+size 17082913

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}