Hugging Face's logo

mesolitica
/
malaysian-mistral-mmmmodal

Feature Extraction
Transformers
Safetensors
mm_llms
custom_code
Model card Files Community
huseinzol05 commited on
Commit
7fef0fc
•
1 Parent(s): fc2d559

Upload processor

Browse files
Files changed (3) hide show
  1. preprocessor_config.json +21 -12
  2. special_tokens_map.json +7 -19
  3. tokenizer_config.json +18 -67
preprocessor_config.json CHANGED
@@ -1,14 +1,23 @@
1
  {
2
- "chunk_length": 30,
3
- "feature_extractor_type": "WhisperFeatureExtractor",
4
- "feature_size": 80,
5
- "hop_length": 160,
6
- "n_fft": 400,
7
- "n_samples": 480000,
8
- "nb_max_frames": 3000,
9
- "padding_side": "right",
10
- "padding_value": 0.0,
11
- "processor_class": "WhisperProcessor",
12
- "return_attention_mask": false,
13
- "sampling_rate": 16000
 
 
 
 
 
 
 
 
 
14
  }
 
1
  {
2
+ "do_normalize": true,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_processor_type": "SiglipImageProcessor",
11
+ "image_std": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "processor_class": "SiglipProcessor",
17
+ "resample": 3,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 384,
21
+ "width": 384
22
+ }
23
  }
special_tokens_map.json CHANGED
@@ -1,35 +1,23 @@
1
  {
2
- "additional_special_tokens": [
3
- "<unk>",
4
- "<s>",
5
- "</s>"
6
- ],
7
- "bos_token": {
8
- "content": "<s>",
9
- "lstrip": false,
10
- "normalized": false,
11
- "rstrip": false,
12
- "single_word": false
13
- },
14
  "eos_token": {
15
  "content": "</s>",
16
- "lstrip": false,
17
  "normalized": false,
18
- "rstrip": false,
19
  "single_word": false
20
  },
21
  "pad_token": {
22
- "content": "<unk>",
23
- "lstrip": false,
24
  "normalized": false,
25
- "rstrip": false,
26
  "single_word": false
27
  },
28
  "unk_token": {
29
  "content": "<unk>",
30
- "lstrip": false,
31
  "normalized": false,
32
- "rstrip": false,
33
  "single_word": false
34
  }
35
  }
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
2
  "eos_token": {
3
  "content": "</s>",
4
+ "lstrip": true,
5
  "normalized": false,
6
+ "rstrip": true,
7
  "single_word": false
8
  },
9
  "pad_token": {
10
+ "content": "</s>",
11
+ "lstrip": true,
12
  "normalized": false,
13
+ "rstrip": true,
14
  "single_word": false
15
  },
16
  "unk_token": {
17
  "content": "<unk>",
18
+ "lstrip": true,
19
  "normalized": false,
20
+ "rstrip": true,
21
  "single_word": false
22
  }
23
  }
tokenizer_config.json CHANGED
@@ -1,83 +1,34 @@
1
  {
2
- "add_bos_token": false,
3
- "add_eos_token": false,
4
  "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
  "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
  "normalized": false,
17
- "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  },
21
  "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
  "normalized": false,
25
- "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
- },
29
- "32000": {
30
- "content": "<image>",
31
- "lstrip": false,
32
- "normalized": true,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": false
36
- },
37
- "32001": {
38
- "content": "</image>",
39
- "lstrip": false,
40
- "normalized": true,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": false
44
- },
45
- "32002": {
46
- "content": "<audio>",
47
- "lstrip": false,
48
- "normalized": true,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": false
52
- },
53
- "32003": {
54
- "content": "</audio>",
55
- "lstrip": false,
56
- "normalized": true,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": false
60
  }
61
  },
62
- "additional_special_tokens": [
63
- "<unk>",
64
- "<s>",
65
- "</s>"
66
- ],
67
- "bos_token": "<s>",
68
- "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
69
- "clean_up_tokenization_spaces": false,
70
  "eos_token": "</s>",
71
- "legacy": true,
72
- "max_length": 2048,
73
- "model_max_length": 1000000000000000019884624838656,
74
- "pad_token": "<unk>",
 
 
75
  "sp_model_kwargs": {},
76
- "spaces_between_special_tokens": false,
77
- "stride": 0,
78
- "tokenizer_class": "LlamaTokenizer",
79
- "truncation_side": "right",
80
- "truncation_strategy": "longest_first",
81
- "unk_token": "<unk>",
82
- "use_default_system_prompt": true
83
  }
 
1
  {
 
 
2
  "added_tokens_decoder": {
 
 
 
 
 
 
 
 
3
  "1": {
4
+ "content": "</s>",
5
+ "lstrip": true,
6
  "normalized": false,
7
+ "rstrip": true,
8
  "single_word": false,
9
  "special": true
10
  },
11
  "2": {
12
+ "content": "<unk>",
13
+ "lstrip": true,
14
  "normalized": false,
15
+ "rstrip": true,
16
  "single_word": false,
17
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
  }
19
  },
20
+ "additional_special_tokens": [],
21
+ "clean_up_tokenization_spaces": true,
22
+ "do_lower_case": true,
 
 
 
 
 
23
  "eos_token": "</s>",
24
+ "model_input_names": [
25
+ "input_ids"
26
+ ],
27
+ "model_max_length": 64,
28
+ "pad_token": "</s>",
29
+ "processor_class": "SiglipProcessor",
30
  "sp_model_kwargs": {},
31
+ "tokenizer_class": "SiglipTokenizer",
32
+ "trust_remote_code": false,
33
+ "unk_token": "<unk>"
 
 
 
 
34
  }