chrisc36 commited on
Commit
37daec6
1 Parent(s): 8c0e6d6

Upload processor

Browse files
added_tokens.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<im_col>": 151649,
3
+ "<im_end>": 151647,
4
+ "<im_patch>": 151648,
5
+ "<im_start>": 151646,
6
+ "<|endoftext|>": 151643,
7
+ "<|im_end|>": 151645,
8
+ "<|im_start|>": 151644,
9
+ "<|image|>": 151650
10
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_image_input_size": [
3
+ 336,
4
+ 336
5
+ ],
6
+ "do_normalize": true,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_padding_mask": true,
13
+ "image_patch_size": 14,
14
+ "image_processor_type": "MolmoImageProcessor",
15
+ "image_std": [
16
+ 0.26862954,
17
+ 0.26130258,
18
+ 0.27577711
19
+ ],
20
+ "image_token_length_h": 12,
21
+ "image_token_length_w": 12,
22
+ "max_crops": 12,
23
+ "overlap_margins": [
24
+ 4,
25
+ 4
26
+ ],
27
+ "processor_class": "MolmoProcessor"
28
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<im_start>",
4
+ "<im_end>",
5
+ "<im_patch>",
6
+ "<im_col>",
7
+ "<|image|>"
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<im_start>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<im_end>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<im_patch>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<im_col>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|image|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ }
68
+ },
69
+ "additional_special_tokens": [
70
+ "<im_start>",
71
+ "<im_end>",
72
+ "<im_patch>",
73
+ "<im_col>",
74
+ "<|image|>"
75
+ ],
76
+ "bos_token": null,
77
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
78
+ "clean_up_tokenization_spaces": false,
79
+ "eos_token": "<|endoftext|>",
80
+ "errors": "replace",
81
+ "model_max_length": 32768,
82
+ "pad_token": "<|endoftext|>",
83
+ "processor_class": "MolmoProcessor",
84
+ "split_special_tokens": false,
85
+ "tokenizer_class": "Qwen2Tokenizer",
86
+ "unk_token": null
87
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff