Commit
•
f3c83bd
1
Parent(s):
af33e43
Upload processor
Browse files- added_tokens.json +4 -0
- preprocessor_config.json +51 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +79 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<image>": 64001,
|
3 |
+
"<video>": 64000
|
4 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_size": {
|
3 |
+
"height": 336,
|
4 |
+
"width": 336
|
5 |
+
},
|
6 |
+
"do_center_crop": true,
|
7 |
+
"do_convert_rgb": true,
|
8 |
+
"do_normalize": true,
|
9 |
+
"do_pad": true,
|
10 |
+
"do_rescale": true,
|
11 |
+
"do_resize": true,
|
12 |
+
"image_grid_pinpoints": [
|
13 |
+
[
|
14 |
+
336,
|
15 |
+
672
|
16 |
+
],
|
17 |
+
[
|
18 |
+
672,
|
19 |
+
336
|
20 |
+
],
|
21 |
+
[
|
22 |
+
672,
|
23 |
+
672
|
24 |
+
],
|
25 |
+
[
|
26 |
+
1008,
|
27 |
+
336
|
28 |
+
],
|
29 |
+
[
|
30 |
+
336,
|
31 |
+
1008
|
32 |
+
]
|
33 |
+
],
|
34 |
+
"image_mean": [
|
35 |
+
0.48145466,
|
36 |
+
0.4578275,
|
37 |
+
0.40821073
|
38 |
+
],
|
39 |
+
"image_processor_type": "LlavaNextImageProcessor",
|
40 |
+
"image_std": [
|
41 |
+
0.26862954,
|
42 |
+
0.26130258,
|
43 |
+
0.27577711
|
44 |
+
],
|
45 |
+
"processor_class": "LlavaNextVideoProcessor",
|
46 |
+
"resample": 3,
|
47 |
+
"rescale_factor": 0.00392156862745098,
|
48 |
+
"size": {
|
49 |
+
"shortest_edge": 336
|
50 |
+
}
|
51 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|im_end|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<unk>",
|
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 sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
|
3 |
+
size 1033105
|
tokenizer_config.json
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"1": {
|
15 |
+
"content": "<|startoftext|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "<|endoftext|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"6": {
|
31 |
+
"content": "<|im_start|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": false
|
37 |
+
},
|
38 |
+
"7": {
|
39 |
+
"content": "<|im_end|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"64000": {
|
47 |
+
"content": "<video>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": false,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"64001": {
|
55 |
+
"content": "<image>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": false,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": true
|
61 |
+
}
|
62 |
+
},
|
63 |
+
"bos_token": "<|startoftext|>",
|
64 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
65 |
+
"clean_up_tokenization_spaces": false,
|
66 |
+
"eos_token": "<|im_end|>",
|
67 |
+
"legacy": true,
|
68 |
+
"model_max_length": 4096,
|
69 |
+
"pad_token": "<unk>",
|
70 |
+
"padding_side": "left",
|
71 |
+
"processor_class": "LlavaNextVideoProcessor",
|
72 |
+
"sp_model_kwargs": {},
|
73 |
+
"spaces_between_special_tokens": false,
|
74 |
+
"tokenizer_class": "LlamaTokenizer",
|
75 |
+
"trust_remote_code": false,
|
76 |
+
"unk_token": "<unk>",
|
77 |
+
"use_default_system_prompt": false,
|
78 |
+
"use_fast": true
|
79 |
+
}
|