Mr-Vicky-01
commited on
Commit
•
d9d42d8
1
Parent(s):
1d7cb2c
Upload tokenizer
Browse files- added_tokens.json +5 -0
- merges.txt +0 -0
- special_tokens_map.json +28 -0
- tokenizer_config.json +52 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|im_end|>": 50259,
|
3 |
+
"<|im_start|>": 50258,
|
4 |
+
"[PAD]": 50257
|
5 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"pad_token": "<|endoftext|>",
|
21 |
+
"unk_token": {
|
22 |
+
"content": "<|endoftext|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
}
|
28 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": true,
|
4 |
+
"add_prefix_space": false,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"50256": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"50257": {
|
15 |
+
"content": "[PAD]",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"50258": {
|
23 |
+
"content": "<|im_start|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"50259": {
|
31 |
+
"content": "<|im_end|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
}
|
38 |
+
},
|
39 |
+
"additional_special_tokens": [
|
40 |
+
"<|im_start|>",
|
41 |
+
"<|im_end|>"
|
42 |
+
],
|
43 |
+
"bos_token": "<|endoftext|>",
|
44 |
+
"clean_up_tokenization_spaces": false,
|
45 |
+
"eos_token": "<|endoftext|>",
|
46 |
+
"errors": "replace",
|
47 |
+
"model_max_length": 512,
|
48 |
+
"pad_token": "<|endoftext|>",
|
49 |
+
"padding_side": "right",
|
50 |
+
"tokenizer_class": "GPT2Tokenizer",
|
51 |
+
"unk_token": "<|endoftext|>"
|
52 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|