Add model and tokenizer files

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "facebook/xlm-v-base",
+  "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": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-REDUPLICATION",
+    "2": "I-REDUPLICATION",
+    "3": "B-REPETITION",
+    "4": "I-REPETITION",
+    "5": "B-REDUPLICATION-PARTIAL",
+    "6": "I-REDUPLICATION-PARTIAL",
+    "7": "B-REPETITION-PARTIAL",
+    "8": "I-REPETITION-PARTIAL",
+    "9": "B-SENTENCE-BOUNDARY",
+    "10": "I-SENTENCE-BOUNDARY"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-REDUPLICATION": 1,
+    "B-REDUPLICATION-PARTIAL": 5,
+    "B-REPETITION": 3,
+    "B-REPETITION-PARTIAL": 7,
+    "B-SENTENCE-BOUNDARY": 9,
+    "I-REDUPLICATION": 2,
+    "I-REDUPLICATION-PARTIAL": 6,
+    "I-REPETITION": 4,
+    "I-REPETITION-PARTIAL": 8,
+    "I-SENTENCE-BOUNDARY": 10,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 901629
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a3372a16354a11b50eafc1568966b87cf848d0ba9c7e903e191e8a499069e2f
+size 3111715249

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbee9f6b1c2cba29b335e70d6088eea943c7d5ae55ac7dd17174760bf758e309
+size 18241665

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_config.json

@@ -0,0 +1,19 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "name_or_path": "facebook/xlm-v-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}