Upload processor
Browse files- preprocessor_config.json +21 -0
- special_tokens_map.json +10 -0
- tokenizer.model +3 -0
- tokenizer_config.json +27 -0
preprocessor_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_transform": null,
|
3 |
+
"auto_map": {
|
4 |
+
"AutoImageProcessor": "vision_processor.AriaVisionProcessor",
|
5 |
+
"AutoProcessor": "processing_aria.AriaProcessor"
|
6 |
+
},
|
7 |
+
"image_mean": [
|
8 |
+
0.5,
|
9 |
+
0.5,
|
10 |
+
0.5
|
11 |
+
],
|
12 |
+
"image_processor_type": "AriaVisionProcessor",
|
13 |
+
"image_std": [
|
14 |
+
0.5,
|
15 |
+
0.5,
|
16 |
+
0.5
|
17 |
+
],
|
18 |
+
"max_image_size": 980,
|
19 |
+
"min_image_size": 336,
|
20 |
+
"processor_class": "AriaProcessor"
|
21 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"pad_token": "<unk>",
|
3 |
+
"unk_token": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
}
|
10 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e429a008ed1045d14464933311e0b3258575980efc9db4e61f368e399c719d2a
|
3 |
+
size 1696299
|
tokenizer_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
}
|
14 |
+
},
|
15 |
+
"bos_token": null,
|
16 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}{% elif message['content'] is iterable %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<fim_prefix><|img|><fim_suffix>{% endif %}{% endfor %}{% endif %}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
17 |
+
"clean_up_tokenization_spaces": false,
|
18 |
+
"eos_token": null,
|
19 |
+
"legacy": true,
|
20 |
+
"model_max_length": 1000000000000000019884624838656,
|
21 |
+
"pad_token": "<unk>",
|
22 |
+
"sp_model_kwargs": {},
|
23 |
+
"spaces_between_special_tokens": false,
|
24 |
+
"tokenizer_class": "LlamaTokenizer",
|
25 |
+
"unk_token": "<unk>",
|
26 |
+
"use_default_system_prompt": false
|
27 |
+
}
|