pranjal01 commited on
Commit
a35b2de
1 Parent(s): 6661a1b

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 50256
3
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": false
12
+ }
13
+ },
14
+ "additional_special_tokens": [],
15
+ "bos_token": "<|endoftext|>",
16
+ "clean_up_tokenization_spaces": true,
17
+ "eos_token": "<|endoftext|>",
18
+ "errors": "replace",
19
+ "model_max_length": 1024,
20
+ "pad_token": "<|endoftext|>",
21
+ "tokenizer_class": "GPT2Tokenizer",
22
+ "tokenizer_file": "/home/p_r_prod/.cache/huggingface/hub/models--gpt2/snapshots/11c5a3d5811f50298f278a704980280950aedb10/tokenizer.json",
23
+ "unk_token": "<|endoftext|>"
24
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff