Commit
•
d394a01
1
Parent(s):
c6481b5
Upload processor
Browse files- merges.txt +0 -0
- preprocessor_config.json +31 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +28 -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 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_map": {
|
| 3 |
+
"AutoProcessor": "processing_jat.JatProcessor"
|
| 4 |
+
},
|
| 5 |
+
"crop_size": {
|
| 6 |
+
"height": 224,
|
| 7 |
+
"width": 224
|
| 8 |
+
},
|
| 9 |
+
"do_center_crop": true,
|
| 10 |
+
"do_convert_rgb": true,
|
| 11 |
+
"do_normalize": true,
|
| 12 |
+
"do_rescale": true,
|
| 13 |
+
"do_resize": true,
|
| 14 |
+
"image_mean": [
|
| 15 |
+
0.48145466,
|
| 16 |
+
0.4578275,
|
| 17 |
+
0.40821073
|
| 18 |
+
],
|
| 19 |
+
"image_processor_type": "CLIPImageProcessor",
|
| 20 |
+
"image_std": [
|
| 21 |
+
0.26862954,
|
| 22 |
+
0.26130258,
|
| 23 |
+
0.27577711
|
| 24 |
+
],
|
| 25 |
+
"processor_class": "JatProcessor",
|
| 26 |
+
"resample": 3,
|
| 27 |
+
"rescale_factor": 0.00392156862745098,
|
| 28 |
+
"size": {
|
| 29 |
+
"shortest_edge": 224
|
| 30 |
+
}
|
| 31 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 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 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
}
|
| 12 |
+
},
|
| 13 |
+
"auto_map": {
|
| 14 |
+
"AutoProcessor": "processing_jat.JatProcessor"
|
| 15 |
+
},
|
| 16 |
+
"bos_token": "<|endoftext|>",
|
| 17 |
+
"clean_up_tokenization_spaces": true,
|
| 18 |
+
"eos_token": "<|endoftext|>",
|
| 19 |
+
"model_input_names": [
|
| 20 |
+
"input_ids",
|
| 21 |
+
"attention_mask"
|
| 22 |
+
],
|
| 23 |
+
"model_max_length": 512,
|
| 24 |
+
"pad_token": "<|endoftext|>",
|
| 25 |
+
"processor_class": "JatProcessor",
|
| 26 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 27 |
+
"unk_token": "<|endoftext|>"
|
| 28 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|