Hugging Face's logo

jinymusim
/
RPGPT

Text Generation
Transformers
PyTorch
English
gpt2
Inference Endpoints
text-generation-inference
Model card Files Community
jinymusim commited on
Commit
abcc03e
•
1 Parent(s): 7d988bc

Upload 9 files

Browse files
Files changed (6) hide show
  1. added_tokens.json +6 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +36 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +58 -0
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<|CHAR|>": 50257,
3
+ "<|CONTEXT|>": 50260,
4
+ "<|INPUT|>": 50259,
5
+ "<|RESPONSE|>": 50258
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|CHAR|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|RESPONSE|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<|INPUT|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<|CONTEXT|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ ],
32
+ "bos_token": "<|endoftext|>",
33
+ "eos_token": "<|endoftext|>",
34
+ "pad_token": "<|endoftext|>",
35
+ "unk_token": "<|endoftext|>"
36
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": "<|CHAR|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50258": {
21
+ "content": "<|RESPONSE|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50259": {
29
+ "content": "<|INPUT|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50260": {
37
+ "content": "<|CONTEXT|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "additional_special_tokens": [
46
+ "<|CHAR|>",
47
+ "<|RESPONSE|>",
48
+ "<|INPUT|>",
49
+ "<|CONTEXT|>"
50
+ ],
51
+ "bos_token": "<|endoftext|>",
52
+ "clean_up_tokenization_spaces": true,
53
+ "eos_token": "<|endoftext|>",
54
+ "model_max_length": 1024,
55
+ "pad_token": "<|endoftext|>",
56
+ "tokenizer_class": "GPT2Tokenizer",
57
+ "unk_token": "<|endoftext|>"
58
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff