juancavallotti commited on
Commit
712e489
1 Parent(s): 2afcb66

add tokenizer

Browse files
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Apr20_23-54-12_0ca3f37e5e6e/1650502218.2028623/events.out.tfevents.1650502218.0ca3f37e5e6e.696.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f97c422ae2d6a627c3fffbb38c8df30e9a05bf25cfa7f21b88f329dc0b5acd4b
3
+ size 4912
runs/Apr20_23-54-12_0ca3f37e5e6e/events.out.tfevents.1650502218.0ca3f37e5e6e.696.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b3adca1597f1894c33751c614a4fc9dd6b09a7ca1a6e15c717aa08771de9f4c
3
+ size 4078
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilroberta-base", "tokenizer_class": "RobertaTokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff