jslin09 commited on
Commit
0211d1d
1 Parent(s): 8219766

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fa39cd4b1500feb205bcce3b9703a4373414cafe4970e0657b413f7ddd2a9d3
3
- size 14500438
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f6efc66e73f1fd69da4f436e48befb519fdff3fe18910850c1d41bd862293a5
3
+ size 14500443
tokenizer_config.json CHANGED
@@ -1 +1,11 @@
1
- {"unk_token": "<unk>", "eos_token": "</s>", "bos_token": "<s>", "pad_token": "<pad>", "name_or_path": "bigscience/tokenizer", "special_tokens_map_file": null, "tokenizer_class": "BloomTokenizerFast", "padding_side":"left"}
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "name_or_path": "bigscience/bloom-560m",
6
+ "pad_token": "<pad>",
7
+ "padding_side": "left",
8
+ "special_tokens_map_file": null,
9
+ "tokenizer_class": "BloomTokenizer",
10
+ "unk_token": "<unk>"
11
+ }