Sujan42024
commited on
Commit
•
01eb498
1
Parent(s):
cf32665
Upload tokenizer
Browse files- added_tokens.json +5 -0
- merges.txt +0 -0
- special_tokens_map.json +11 -0
- tokenizer.json +0 -0
- tokenizer_config.json +49 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"### End": 50257,
|
3 |
+
"### Instruction:": 50258,
|
4 |
+
"### Response:\n": 50259
|
5 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"### End",
|
4 |
+
"### Instruction:",
|
5 |
+
"### Response:\n"
|
6 |
+
],
|
7 |
+
"bos_token": "<|endoftext|>",
|
8 |
+
"eos_token": "<|endoftext|>",
|
9 |
+
"pad_token": "<|endoftext|>",
|
10 |
+
"unk_token": "<|endoftext|>"
|
11 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"50257": {
|
13 |
+
"content": "### End",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"50258": {
|
21 |
+
"content": "### Instruction:",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"50259": {
|
29 |
+
"content": "### Response:\n",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
}
|
36 |
+
},
|
37 |
+
"additional_special_tokens": [
|
38 |
+
"### End",
|
39 |
+
"### Instruction:",
|
40 |
+
"### Response:\n"
|
41 |
+
],
|
42 |
+
"bos_token": "<|endoftext|>",
|
43 |
+
"clean_up_tokenization_spaces": true,
|
44 |
+
"eos_token": "<|endoftext|>",
|
45 |
+
"model_max_length": 1024,
|
46 |
+
"pad_token": "<|endoftext|>",
|
47 |
+
"tokenizer_class": "GPT2Tokenizer",
|
48 |
+
"unk_token": "<|endoftext|>"
|
49 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|