ehristoforu
commited on
Commit
•
9538aee
1
Parent(s):
57abcaa
Upload 5 files
Browse files- tokenizer/added_tokens.json +4 -0
- tokenizer/special_tokens_map.json +3 -21
- tokenizer/tokenizer_config.json +22 -23
tokenizer/added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 49407,
|
3 |
+
"<|startoftext|>": 49406
|
4 |
+
}
|
tokenizer/special_tokens_map.json
CHANGED
@@ -1,24 +1,6 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": true,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "<|endoftext|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": true,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
"pad_token": "<|endoftext|>",
|
17 |
-
"unk_token":
|
18 |
-
"content": "<|endoftext|>",
|
19 |
-
"lstrip": false,
|
20 |
-
"normalized": true,
|
21 |
-
"rstrip": false,
|
22 |
-
"single_word": false
|
23 |
-
}
|
24 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<|startoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
tokenizer/tokenizer_config.json
CHANGED
@@ -1,33 +1,32 @@
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
3 |
-
"
|
4 |
-
"
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
},
|
|
|
|
|
11 |
"clean_up_tokenization_spaces": true,
|
12 |
"do_lower_case": 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": 77,
|
23 |
"pad_token": "<|endoftext|>",
|
24 |
"tokenizer_class": "CLIPTokenizer",
|
25 |
-
"
|
26 |
-
|
27 |
-
"content": "<|endoftext|>",
|
28 |
-
"lstrip": false,
|
29 |
-
"normalized": true,
|
30 |
-
"rstrip": false,
|
31 |
-
"single_word": false
|
32 |
-
}
|
33 |
}
|
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"49406": {
|
5 |
+
"content": "<|startoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": false
|
11 |
+
},
|
12 |
+
"49407": {
|
13 |
+
"content": "<|endoftext|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": false
|
19 |
+
}
|
20 |
},
|
21 |
+
"additional_special_tokens": [],
|
22 |
+
"bos_token": "<|startoftext|>",
|
23 |
"clean_up_tokenization_spaces": true,
|
24 |
"do_lower_case": true,
|
25 |
+
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
"errors": "replace",
|
27 |
"model_max_length": 77,
|
28 |
"pad_token": "<|endoftext|>",
|
29 |
"tokenizer_class": "CLIPTokenizer",
|
30 |
+
"tokenizer_file": "/home/user/.cache/huggingface/hub/models--openai--clip-vit-large-patch14/snapshots/32bd64288804d66eefd0ccbe215aa642df71cc41/tokenizer.json",
|
31 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
}
|