ehristoforu
commited on
Commit
•
32bf835
1
Parent(s):
b3c7437
Upload 4 files
Browse files
tokenizer_2/special_tokens_map.json
CHANGED
@@ -9,15 +9,21 @@
|
|
9 |
"eos_token": {
|
10 |
"content": "<|endoftext|>",
|
11 |
"lstrip": false,
|
12 |
-
"normalized":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token": "!",
|
17 |
"unk_token": {
|
18 |
"content": "<|endoftext|>",
|
19 |
"lstrip": false,
|
20 |
-
"normalized":
|
21 |
"rstrip": false,
|
22 |
"single_word": false
|
23 |
}
|
|
|
9 |
"eos_token": {
|
10 |
"content": "<|endoftext|>",
|
11 |
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "!",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
"rstrip": false,
|
21 |
"single_word": false
|
22 |
},
|
|
|
23 |
"unk_token": {
|
24 |
"content": "<|endoftext|>",
|
25 |
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
"rstrip": false,
|
28 |
"single_word": false
|
29 |
}
|
tokenizer_2/tokenizer_config.json
CHANGED
@@ -1,33 +1,38 @@
|
|
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": "!",
|
24 |
"tokenizer_class": "CLIPTokenizer",
|
25 |
-
"unk_token":
|
26 |
-
"__type": "AddedToken",
|
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 |
+
"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": true
|
19 |
+
},
|
20 |
+
"49407": {
|
21 |
+
"content": "<|endoftext|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
},
|
29 |
+
"bos_token": "<|startoftext|>",
|
30 |
"clean_up_tokenization_spaces": true,
|
31 |
"do_lower_case": true,
|
32 |
+
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
"errors": "replace",
|
34 |
"model_max_length": 77,
|
35 |
"pad_token": "!",
|
36 |
"tokenizer_class": "CLIPTokenizer",
|
37 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
}
|