Commit
•
9ef0b64
1
Parent(s):
d24667f
add processor
Browse files- merges.txt +0 -0
- preprocessor_config.json +39 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +31 -0
- vocab.json +0 -0
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
preprocessor_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_rescale",
|
8 |
+
"rescale_factor",
|
9 |
+
"do_normalize",
|
10 |
+
"image_mean",
|
11 |
+
"image_std",
|
12 |
+
"do_convert_rgb",
|
13 |
+
"return_tensors",
|
14 |
+
"data_format",
|
15 |
+
"input_data_format"
|
16 |
+
],
|
17 |
+
"do_convert_rgb": true,
|
18 |
+
"do_normalize": true,
|
19 |
+
"do_rescale": true,
|
20 |
+
"do_resize": true,
|
21 |
+
"image_mean": [
|
22 |
+
0.48145466,
|
23 |
+
0.4578275,
|
24 |
+
0.40821073
|
25 |
+
],
|
26 |
+
"image_processor_type": "BlipImageProcessor",
|
27 |
+
"image_std": [
|
28 |
+
0.26862954,
|
29 |
+
0.26130258,
|
30 |
+
0.27577711
|
31 |
+
],
|
32 |
+
"processor_class": "Blip2Processor",
|
33 |
+
"resample": 3,
|
34 |
+
"rescale_factor": 0.00392156862745098,
|
35 |
+
"size": {
|
36 |
+
"height": 224,
|
37 |
+
"width": 224
|
38 |
+
}
|
39 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "</s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "</s>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"1": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"2": {
|
14 |
+
"content": "</s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
}
|
21 |
+
},
|
22 |
+
"bos_token": "</s>",
|
23 |
+
"clean_up_tokenization_spaces": true,
|
24 |
+
"eos_token": "</s>",
|
25 |
+
"errors": "replace",
|
26 |
+
"model_max_length": 1000000000000000019884624838656,
|
27 |
+
"pad_token": "<pad>",
|
28 |
+
"processor_class": "Blip2Processor",
|
29 |
+
"tokenizer_class": "GPT2Tokenizer",
|
30 |
+
"unk_token": "</s>"
|
31 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|