Upload 2 files
Browse files
tokenizer/special_tokens_map.json
CHANGED
@@ -1,30 +1,6 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
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": "<|endoftext|>",
|
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 |
-
}
|
30 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<|startoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
tokenizer/tokenizer_config.json
CHANGED
@@ -7,7 +7,7 @@
|
|
7 |
"normalized": true,
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
-
"special":
|
11 |
},
|
12 |
"49407": {
|
13 |
"content": "<|endoftext|>",
|
@@ -15,9 +15,10 @@
|
|
15 |
"normalized": false,
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
-
"special":
|
19 |
}
|
20 |
},
|
|
|
21 |
"bos_token": "<|startoftext|>",
|
22 |
"clean_up_tokenization_spaces": true,
|
23 |
"do_lower_case": true,
|
@@ -26,5 +27,6 @@
|
|
26 |
"model_max_length": 77,
|
27 |
"pad_token": "<|endoftext|>",
|
28 |
"tokenizer_class": "CLIPTokenizer",
|
|
|
29 |
"unk_token": "<|endoftext|>"
|
30 |
-
}
|
|
|
7 |
"normalized": true,
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
+
"special": false
|
11 |
},
|
12 |
"49407": {
|
13 |
"content": "<|endoftext|>",
|
|
|
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,
|
|
|
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 |
+
}
|