tokenizer

generate_pytorch_model.py

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a633e6d25d36ec4587ea7ca14c42b0cb987fcd1be3a260750b4d3f537158e70d
-size 256
+oid sha256:70b56773cc736fd97960c4a46e13fbf775752f27db9b276f7e51ccc07f4cadcd
+size 349

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": ".", "tokenizer_class": "RobertaTokenizer"}