language-identification

.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

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,85 @@
+{
+  "_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": "ar",
+    "1": "bg",
+    "2": "cs",
+    "3": "de",
+    "4": "el",
+    "5": "en",
+    "6": "es",
+    "7": "fr",
+    "8": "hi",
+    "9": "id",
+    "10": "it",
+    "11": "ja",
+    "12": "ko",
+    "13": "nl",
+    "14": "pl",
+    "15": "pt",
+    "16": "ro",
+    "17": "ru",
+    "18": "sv",
+    "19": "sw",
+    "20": "th",
+    "21": "tr",
+    "22": "uk",
+    "23": "ur",
+    "24": "vi",
+    "25": "zh"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ar": 0,
+    "bg": 1,
+    "cs": 2,
+    "de": 3,
+    "el": 4,
+    "en": 5,
+    "es": 6,
+    "fr": 7,
+    "hi": 8,
+    "id": 9,
+    "it": 10,
+    "ja": 11,
+    "ko": 12,
+    "nl": 13,
+    "pl": 14,
+    "pt": 15,
+    "ro": 16,
+    "ru": 17,
+    "sv": 18,
+    "sw": 19,
+    "th": 20,
+    "tr": 21,
+    "uk": 22,
+    "ur": 23,
+    "vi": 24,
+    "zh": 25
+  },
+  "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": "4.28.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ba875f78588ba0a5f39463f3e1a525ab924dfb160f64894d4e948dbb5cc2b00
+size 1112323373

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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 sha256:1edb0658cb47689db5cf78194ebe041bba3b6b775d1f1069fc9501b372d4acb0
+size 17082758

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>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3e612d261555ab3c6d1d9bc5e2bb4652a3451c50df9f945ee341512eb77a451
+size 3631