andreaskoepf commited on
Commit
a92da22
1 Parent(s): 20229c6

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +14 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +10 -0
special_tokens_map.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|prefix_begin|>",
4
+ "<|prompter|>",
5
+ "<|system|>",
6
+ "<|prefix_end|>",
7
+ "<|assistant|>"
8
+ ],
9
+ "bos_token": "<|endoftext|>",
10
+ "eos_token": "<|endoftext|>",
11
+ "pad_token": "<|padding|>",
12
+ "sep_token": "<|endoftext|>",
13
+ "unk_token": "<|endoftext|>"
14
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "name_or_path": "/home/ubuntu/Open-Assistant/model/model_training/.saved_models/oasst-sft-1_12b/checkpoint-4500/",
7
+ "special_tokens_map_file": "/fsx/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/3523781c8df75f7741687a4284f6f70e1afa12f4/special_tokens_map.json",
8
+ "tokenizer_class": "GPTNeoXTokenizer",
9
+ "unk_token": "<|endoftext|>"
10
+ }