dataautogpt3
commited on
Commit
•
fcca51e
1
Parent(s):
8811756
Upload 5 files
Browse files
tokenizer_2/added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"!": 0,
|
3 |
+
"<|endoftext|>": 49407,
|
4 |
+
"<|startoftext|>": 49406
|
5 |
+
}
|
tokenizer_2/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_2/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|startoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "!",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer_2/tokenizer_config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "!",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"49406": {
|
13 |
+
"content": "<|startoftext|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": false
|
19 |
+
},
|
20 |
+
"49407": {
|
21 |
+
"content": "<|endoftext|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": false
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [],
|
30 |
+
"bos_token": "<|startoftext|>",
|
31 |
+
"clean_up_tokenization_spaces": true,
|
32 |
+
"do_lower_case": true,
|
33 |
+
"eos_token": "<|endoftext|>",
|
34 |
+
"errors": "replace",
|
35 |
+
"model_max_length": 77,
|
36 |
+
"pad_token": "!",
|
37 |
+
"tokenizer_class": "CLIPTokenizer",
|
38 |
+
"tokenizer_file": "/home/user/.cache/huggingface/hub/models--laion--CLIP-ViT-bigG-14-laion2B-39B-b160k/snapshots/8c7a3583335de4dba1b07182dbf81c75137ce67b/tokenizer.json",
|
39 |
+
"unk_token": "<|endoftext|>"
|
40 |
+
}
|
tokenizer_2/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|