mabaochang commited on
Commit
a6a42a8
1 Parent(s): 0884137

add tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +3 -0
  2. tokenizer_config.json +11 -0
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f6efc66e73f1fd69da4f436e48befb519fdff3fe18910850c1d41bd862293a5
3
+ size 14500443
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "name_or_path": "/nfs/a100-80G-20/jiyunjie/finetuned_ckpt/bloom-7b1/stanford_zh_seed_tasks_new_tokenized_bloom_epoch=0-step=1491",
7
+ "pad_token": "<pad>",
8
+ "special_tokens_map_file": null,
9
+ "tokenizer_class": "BloomTokenizer",
10
+ "unk_token": "<unk>"
11
+ }