Upload 5 files
Browse files- preprocessor_config.json +11 -0
- special_tokens_map.json +1 -0
- tokenizer.json +177 -0
- tokenizer_config.json +1 -0
- vocab.json +95 -0
preprocessor_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_size": 30,
|
3 |
+
"do_center_crop": true,
|
4 |
+
"do_normalize": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"feature_extractor_type": "CLIPFeatureExtractor",
|
7 |
+
"image_mean": [0.48145466, 0.4578275, 0.40821073],
|
8 |
+
"image_std": [0.26862954, 0.26130258, 0.27577711],
|
9 |
+
"resample": 3,
|
10 |
+
"size": 30
|
11 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}
|
tokenizer.json
ADDED
@@ -0,0 +1,177 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
5 |
+
"added_tokens": [
|
6 |
+
{
|
7 |
+
"id": 0,
|
8 |
+
"special": true,
|
9 |
+
"content": "<|startoftext|>",
|
10 |
+
"single_word": false,
|
11 |
+
"lstrip": false,
|
12 |
+
"rstrip": false,
|
13 |
+
"normalized": true
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"id": 1,
|
17 |
+
"special": true,
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"single_word": false,
|
20 |
+
"lstrip": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"normalized": false
|
23 |
+
}
|
24 |
+
],
|
25 |
+
"normalizer": {
|
26 |
+
"type": "Sequence",
|
27 |
+
"normalizers": [
|
28 |
+
{
|
29 |
+
"type": "NFC"
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"type": "Replace",
|
33 |
+
"pattern": {
|
34 |
+
"Regex": "\\s+"
|
35 |
+
},
|
36 |
+
"content": " "
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"type": "Lowercase"
|
40 |
+
}
|
41 |
+
]
|
42 |
+
},
|
43 |
+
"pre_tokenizer": {
|
44 |
+
"type": "Sequence",
|
45 |
+
"pretokenizers": [
|
46 |
+
{
|
47 |
+
"type": "Split",
|
48 |
+
"pattern": {
|
49 |
+
"Regex": "'s|'t|'re|'ve|'m|'ll|'d|[\\p{L}]+|[\\p{N}]|[^\\s\\p{L}\\p{N}]+"
|
50 |
+
},
|
51 |
+
"behavior": "Removed",
|
52 |
+
"invert": true
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"type": "ByteLevel",
|
56 |
+
"add_prefix_space": false,
|
57 |
+
"trim_offsets": true
|
58 |
+
}
|
59 |
+
]
|
60 |
+
},
|
61 |
+
"post_processor": {
|
62 |
+
"type": "RobertaProcessing",
|
63 |
+
"sep": ["<|endoftext|>", 1],
|
64 |
+
"cls": ["<|startoftext|>", 0],
|
65 |
+
"trim_offsets": false,
|
66 |
+
"add_prefix_space": false
|
67 |
+
},
|
68 |
+
"decoder": {
|
69 |
+
"type": "ByteLevel",
|
70 |
+
"add_prefix_space": true,
|
71 |
+
"trim_offsets": true
|
72 |
+
},
|
73 |
+
"model": {
|
74 |
+
"type": "BPE",
|
75 |
+
"dropout": null,
|
76 |
+
"unk_token": "<|endoftext|>",
|
77 |
+
"continuing_subword_prefix": "",
|
78 |
+
"end_of_word_suffix": "</w>",
|
79 |
+
"fuse_unk": false,
|
80 |
+
"vocab": {
|
81 |
+
"<|startoftext|>": 0,
|
82 |
+
"<|endoftext|>": 1,
|
83 |
+
"!": 2,
|
84 |
+
"\"": 3,
|
85 |
+
"#": 4,
|
86 |
+
"$": 5,
|
87 |
+
"%": 6,
|
88 |
+
"&": 7,
|
89 |
+
"'": 8,
|
90 |
+
"(": 9,
|
91 |
+
")": 10,
|
92 |
+
"*": 11,
|
93 |
+
"+": 12,
|
94 |
+
",": 13,
|
95 |
+
"-": 14,
|
96 |
+
".": 15,
|
97 |
+
"/": 16,
|
98 |
+
"0": 17,
|
99 |
+
"1": 18,
|
100 |
+
"2": 19,
|
101 |
+
"3": 20,
|
102 |
+
"4": 21,
|
103 |
+
"5": 22,
|
104 |
+
"6": 23,
|
105 |
+
"7": 24,
|
106 |
+
"8": 25,
|
107 |
+
"9": 26,
|
108 |
+
":": 27,
|
109 |
+
";": 28,
|
110 |
+
"<": 29,
|
111 |
+
"=": 30,
|
112 |
+
">": 31,
|
113 |
+
"?": 32,
|
114 |
+
"@": 33,
|
115 |
+
"A": 34,
|
116 |
+
"B": 35,
|
117 |
+
"C": 36,
|
118 |
+
"D": 37,
|
119 |
+
"E": 38,
|
120 |
+
"F": 39,
|
121 |
+
"G": 40,
|
122 |
+
"H": 41,
|
123 |
+
"I": 42,
|
124 |
+
"J": 43,
|
125 |
+
"K": 44,
|
126 |
+
"L": 45,
|
127 |
+
"M": 46,
|
128 |
+
"N": 47,
|
129 |
+
"O": 48,
|
130 |
+
"P": 49,
|
131 |
+
"Q": 50,
|
132 |
+
"R": 51,
|
133 |
+
"S": 52,
|
134 |
+
"T": 53,
|
135 |
+
"U": 54,
|
136 |
+
"V": 55,
|
137 |
+
"W": 56,
|
138 |
+
"X": 57,
|
139 |
+
"Y": 58,
|
140 |
+
"Z": 59,
|
141 |
+
"[": 60,
|
142 |
+
"\\": 61,
|
143 |
+
"]": 62,
|
144 |
+
"^": 63,
|
145 |
+
"_": 64,
|
146 |
+
"`": 65,
|
147 |
+
"a": 66,
|
148 |
+
"b": 67,
|
149 |
+
"c": 68,
|
150 |
+
"d": 69,
|
151 |
+
"e": 70,
|
152 |
+
"f": 71,
|
153 |
+
"g": 72,
|
154 |
+
"h": 73,
|
155 |
+
"i": 74,
|
156 |
+
"j": 75,
|
157 |
+
"k": 76,
|
158 |
+
"l": 77,
|
159 |
+
"m": 78,
|
160 |
+
"n": 79,
|
161 |
+
"o": 80,
|
162 |
+
"p": 81,
|
163 |
+
"q": 82,
|
164 |
+
"r": 83,
|
165 |
+
"s": 84,
|
166 |
+
"t": 85,
|
167 |
+
"u": 86,
|
168 |
+
"v": 87,
|
169 |
+
"w": 88,
|
170 |
+
"x": 89,
|
171 |
+
"y": 90,
|
172 |
+
"z": 91,
|
173 |
+
"|": 92
|
174 |
+
},
|
175 |
+
"merges": []
|
176 |
+
}
|
177 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": "<|endoftext|>", "add_prefix_space": false, "errors": "replace", "do_lower_case": true, "name_or_path": "hf-internal-testing/tiny-random-clip", "model_max_length": 77, "special_tokens_map_file": "/home/lysandre/.cache/huggingface/transformers/18a566598f286c9139f88160c99f84eec492a26bd22738fa9cb44d5b7e0a5c76.cce1206abbad28826f000510f22f354e53e66a97f7c23745a7dfe27609cc07f5", "from_slow": true, "tokenizer_class": "CLIPTokenizer"}
|
vocab.json
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|startoftext|>": 0,
|
3 |
+
"<|endoftext|>": 1,
|
4 |
+
"!": 2,
|
5 |
+
"\"": 3,
|
6 |
+
"#": 4,
|
7 |
+
"$": 5,
|
8 |
+
"%": 6,
|
9 |
+
"&": 7,
|
10 |
+
"'": 8,
|
11 |
+
"(": 9,
|
12 |
+
")": 10,
|
13 |
+
"*": 11,
|
14 |
+
"+": 12,
|
15 |
+
",": 13,
|
16 |
+
"-": 14,
|
17 |
+
".": 15,
|
18 |
+
"/": 16,
|
19 |
+
"0": 17,
|
20 |
+
"1": 18,
|
21 |
+
"2": 19,
|
22 |
+
"3": 20,
|
23 |
+
"4": 21,
|
24 |
+
"5": 22,
|
25 |
+
"6": 23,
|
26 |
+
"7": 24,
|
27 |
+
"8": 25,
|
28 |
+
"9": 26,
|
29 |
+
":": 27,
|
30 |
+
";": 28,
|
31 |
+
"<": 29,
|
32 |
+
"=": 30,
|
33 |
+
">": 31,
|
34 |
+
"?": 32,
|
35 |
+
"@": 33,
|
36 |
+
"A": 34,
|
37 |
+
"B": 35,
|
38 |
+
"C": 36,
|
39 |
+
"D": 37,
|
40 |
+
"E": 38,
|
41 |
+
"F": 39,
|
42 |
+
"G": 40,
|
43 |
+
"H": 41,
|
44 |
+
"I": 42,
|
45 |
+
"J": 43,
|
46 |
+
"K": 44,
|
47 |
+
"L": 45,
|
48 |
+
"M": 46,
|
49 |
+
"N": 47,
|
50 |
+
"O": 48,
|
51 |
+
"P": 49,
|
52 |
+
"Q": 50,
|
53 |
+
"R": 51,
|
54 |
+
"S": 52,
|
55 |
+
"T": 53,
|
56 |
+
"U": 54,
|
57 |
+
"V": 55,
|
58 |
+
"W": 56,
|
59 |
+
"X": 57,
|
60 |
+
"Y": 58,
|
61 |
+
"Z": 59,
|
62 |
+
"[": 60,
|
63 |
+
"\\": 61,
|
64 |
+
"]": 62,
|
65 |
+
"^": 63,
|
66 |
+
"_": 64,
|
67 |
+
"`": 65,
|
68 |
+
"a": 66,
|
69 |
+
"b": 67,
|
70 |
+
"c": 68,
|
71 |
+
"d": 69,
|
72 |
+
"e": 70,
|
73 |
+
"f": 71,
|
74 |
+
"g": 72,
|
75 |
+
"h": 73,
|
76 |
+
"i": 74,
|
77 |
+
"j": 75,
|
78 |
+
"k": 76,
|
79 |
+
"l": 77,
|
80 |
+
"m": 78,
|
81 |
+
"n": 79,
|
82 |
+
"o": 80,
|
83 |
+
"p": 81,
|
84 |
+
"q": 82,
|
85 |
+
"r": 83,
|
86 |
+
"s": 84,
|
87 |
+
"t": 85,
|
88 |
+
"u": 86,
|
89 |
+
"v": 87,
|
90 |
+
"w": 88,
|
91 |
+
"x": 89,
|
92 |
+
"y": 90,
|
93 |
+
"z": 91,
|
94 |
+
"|": 92
|
95 |
+
}
|