Hugging Face's logo

nlp-waseda
/
tacomet-gpt2-xl-english

Text Generation
Transformers
PyTorch
English
gpt2
text-generation-inference
Inference Endpoints
Model card Files Community
Eiki commited on
Commit
8bcb0be
•
1 Parent(s): 00589f5

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +16 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +32 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +33 -0
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</head>": 50266,
3
+ "</relation>": 50268,
4
+ "<head>": 50265,
5
+ "<relation>": 50267,
6
+ "HinderedBy": 50258,
7
+ "[EOS]": 50257,
8
+ "[GEN]": 50269,
9
+ "[PAD]": 50270,
10
+ "xAttr": 50260,
11
+ "xEffect": 50263,
12
+ "xIntent": 50261,
13
+ "xNeed": 50262,
14
+ "xReact": 50264,
15
+ "xWant": 50259
16
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "HinderedBy",
4
+ "xWant",
5
+ "xAttr",
6
+ "xIntent",
7
+ "xNeed",
8
+ "xEffect",
9
+ "xReact",
10
+ "<head>",
11
+ "</head>",
12
+ "<relation>",
13
+ "</relation>",
14
+ "[GEN]"
15
+ ],
16
+ "bos_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "eos_token": "[EOS]",
24
+ "pad_token": "[EOS]",
25
+ "unk_token": {
26
+ "content": "<|endoftext|>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "tokenizer_class": "GPT2Tokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff