danielhanchen
commited on
Commit
•
b0593e6
1
Parent(s):
6227797
Upload processor
Browse files- added_tokens.json +4 -0
- chat_template.json +3 -0
- preprocessor_config.json +52 -0
- processor_config.json +6 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +64 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<image>": 32000,
|
3 |
+
"<pad>": 32001
|
4 |
+
}
|
chat_template.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ '<<SYS>>\n' + message['content'][0]['text'] + '\n<</SYS>>\n\n' }}{% elif message['role'] == 'user' %}{{ '[INST] ' }}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>\n' }}{% endfor %}{# Render all text next #}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] }}{% endfor %}{{' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'][0]['text'] + '<\\s> '}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}"
|
3 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"aspect_ratio_setting": "anyres",
|
3 |
+
"crop_size": {
|
4 |
+
"height": 336,
|
5 |
+
"width": 336
|
6 |
+
},
|
7 |
+
"do_center_crop": true,
|
8 |
+
"do_convert_rgb": true,
|
9 |
+
"do_normalize": true,
|
10 |
+
"do_pad": true,
|
11 |
+
"do_rescale": true,
|
12 |
+
"do_resize": true,
|
13 |
+
"image_grid_pinpoints": [
|
14 |
+
[
|
15 |
+
336,
|
16 |
+
672
|
17 |
+
],
|
18 |
+
[
|
19 |
+
672,
|
20 |
+
336
|
21 |
+
],
|
22 |
+
[
|
23 |
+
672,
|
24 |
+
672
|
25 |
+
],
|
26 |
+
[
|
27 |
+
1008,
|
28 |
+
336
|
29 |
+
],
|
30 |
+
[
|
31 |
+
336,
|
32 |
+
1008
|
33 |
+
]
|
34 |
+
],
|
35 |
+
"image_mean": [
|
36 |
+
0.48145466,
|
37 |
+
0.4578275,
|
38 |
+
0.40821073
|
39 |
+
],
|
40 |
+
"image_processor_type": "LlavaNextImageProcessor",
|
41 |
+
"image_std": [
|
42 |
+
0.26862954,
|
43 |
+
0.26130258,
|
44 |
+
0.27577711
|
45 |
+
],
|
46 |
+
"processor_class": "LlavaNextProcessor",
|
47 |
+
"resample": 3,
|
48 |
+
"rescale_factor": 0.00392156862745098,
|
49 |
+
"size": {
|
50 |
+
"shortest_edge": 336
|
51 |
+
}
|
52 |
+
}
|
processor_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"image_token": "<image>",
|
3 |
+
"patch_size": 14,
|
4 |
+
"processor_class": "LlavaNextProcessor",
|
5 |
+
"vision_feature_select_strategy": "default"
|
6 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
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.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
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 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"32000": {
|
31 |
+
"content": "<image>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"32001": {
|
39 |
+
"content": "<pad>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"additional_special_tokens": [],
|
48 |
+
"bos_token": "<s>",
|
49 |
+
"clean_up_tokenization_spaces": false,
|
50 |
+
"eos_token": "</s>",
|
51 |
+
"legacy": true,
|
52 |
+
"max_length": null,
|
53 |
+
"model_max_length": 1000000000000000019884624838656,
|
54 |
+
"pad_to_multiple_of": null,
|
55 |
+
"pad_token": "<pad>",
|
56 |
+
"pad_token_type_id": 0,
|
57 |
+
"padding_side": "left",
|
58 |
+
"processor_class": "LlavaNextProcessor",
|
59 |
+
"sp_model_kwargs": {},
|
60 |
+
"spaces_between_special_tokens": false,
|
61 |
+
"tokenizer_class": "LlamaTokenizer",
|
62 |
+
"unk_token": "<unk>",
|
63 |
+
"use_default_system_prompt": false
|
64 |
+
}
|