breadlicker45 commited on
Commit
72bf550
1 Parent(s): e3c5d14

Upload 3 files

Browse files
special_tokens_map.json CHANGED
@@ -1,11 +1,5 @@
1
  {
2
- "additional_special_tokens": [
3
- "<|endoftext|>",
4
- "<|sep|>",
5
- "<|acc|>",
6
- "<|tel|>",
7
- "<|rrn|>"
8
- ],
9
  "eos_token": "<|endoftext|>",
10
- "pad_token": "<|endoftext|>"
11
  }
 
1
  {
2
+ "bos_token": "<|endoftext|>",
 
 
 
 
 
 
3
  "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,6 +1,9 @@
1
  {
2
- "name_or_path": "EleutherAI/polyglot-ko-1.3b",
 
3
  "eos_token": "<|endoftext|>",
4
- "pad_token": "<|endoftext|>",
5
- "tokenizer_class": "PreTrainedTokenizerFast"
 
 
6
  }
 
1
  {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
  "eos_token": "<|endoftext|>",
5
+ "name_or_path": "EleutherAI/gpt-neox-20b",
6
+ "special_tokens_map_file": "/fsx/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/3523781c8df75f7741687a4284f6f70e1afa12f4/special_tokens_map.json",
7
+ "tokenizer_class": "GPTNeoXTokenizer",
8
+ "unk_token": "<|endoftext|>"
9
  }