init commit

.gitattributes

@@ -33,3 +33,6 @@ 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
+unigram.json filter=lfs diff=lfs merge=lfs -text
+dense_classifier.pt filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,3 @@
+{
+ "[FK]": 250002
+}

config.json

@@ -0,0 +1,27 @@
+{
+ "_name_or_path": "./roberta-large",
+ "architectures": [
+ "XLMRobertaForMaskedLM"
+ ],
+ "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,
+ "initializer_range": 0.02,
+ "intermediate_size": 4096,
+ "layer_norm_eps": 1e-05,
+ "max_position_embeddings": 514,
+ "model_type": "roberta",
+ "num_attention_heads": 16,
+ "num_hidden_layers": 24,
+ "output_past": true,
+ "pad_token_id": 1,
+ "position_embedding_type": "absolute",
+ "transformers_version": "4.28.1",
+ "type_vocab_size": 1,
+ "use_cache": true,
+ "vocab_size": 250003
+}

dense_classifier.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:945d70ab63af4e8758466b4418408eee66e879afe363f528d4b68041d691a949
+size 2367837321

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:f9390cd22dc6fc6476b86e2751dc3b6410b9b8c485102908e523dbcd835de5a9
+size 17083106

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+ "add_prefix_space": true,
+ "bos_token": "<s>",
+ "clean_up_tokenization_spaces": true,
+ "cls_token": "<s>",
+ "eos_token": "</s>",
+ "errors": "replace",
+ "mask_token": "<mask>",
+ "model_max_length": 512,
+ "pad_token": "<pad>",
+ "sep_token": "</s>",
+ "tokenizer_class": "RobertaTokenizer",
+ "trim_offsets": true,
+ "unk_token": "<unk>"
+}

unigram.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71b44701d7efd054205115acfa6ef126c5d2f84bd3affe0c59e48163674d19a6
+size 14763234