bokesyo commited on
Commit
d529ae0
1 Parent(s): fb6aea8

Upload 5 files

Browse files
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openbmb/MiniCPM-V-2",
3
+ "architectures": [
4
+ "MiniCPMV"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "configuration_minicpm.MiniCPMVConfig",
10
+ "AutoModel": "modeling_minicpmv.MiniCPMV",
11
+ "AutoModelForCausalLM": "modeling_minicpmv.MiniCPMV"
12
+ },
13
+ "bos_token_id": 1,
14
+ "dim_model_base": 256,
15
+ "drop_vision_last_layer": true,
16
+ "eos_token_id": 2,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 2304,
19
+ "image_size": 448,
20
+ "initializer_range": 0.1,
21
+ "intermediate_size": 5760,
22
+ "max_position_embeddings": 4096,
23
+ "max_slice_nums": 9,
24
+ "mm_use_im_start_end": true,
25
+ "model_type": "minicpmv",
26
+ "num_attention_heads": 36,
27
+ "num_hidden_layers": 40,
28
+ "num_key_value_heads": 36,
29
+ "patch_size": 14,
30
+ "pretraining_tp": 1,
31
+ "query_num": 64,
32
+ "rms_norm_eps": 1e-05,
33
+ "rope_scaling": null,
34
+ "rope_theta": 10000.0,
35
+ "scale_depth": 1.4,
36
+ "scale_emb": 12,
37
+ "scale_resolution": 448,
38
+ "slice_mode": true,
39
+ "tie_word_embeddings": false,
40
+ "torch_dtype": "bfloat16",
41
+ "transformers_version": "4.36.0",
42
+ "use_cache": true,
43
+ "vision_encoder": "vit_so400m_patch14_siglip_384.webli",
44
+ "vocab_size": 122753
45
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<image>",
4
+ "</image>",
5
+ "<ref>",
6
+ "</ref>",
7
+ "<box>",
8
+ "</box>",
9
+ "<quad>",
10
+ "</quad>",
11
+ "<point>",
12
+ "</point>",
13
+ "<slice>",
14
+ "</slice>"
15
+ ],
16
+ "bos_token": {
17
+ "content": "<s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "eos_token": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": "<unk>",
31
+ "unk_token": {
32
+ "content": "<unk>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ }
38
+ }
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:b046f377b2f09a90623a46611bd5d23cb76ac89ca7804a372408f37aff7b96a0
3
+ size 1994817
tokenizer_config.json ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
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
+ "101": {
30
+ "content": "<image>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "102": {
38
+ "content": "</image>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "103": {
46
+ "content": "<ref>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "104": {
54
+ "content": "</ref>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "105": {
62
+ "content": "<box>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "106": {
70
+ "content": "</box>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "107": {
78
+ "content": "<quad>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "108": {
86
+ "content": "</quad>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "109": {
94
+ "content": "<point>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "110": {
102
+ "content": "</point>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "111": {
110
+ "content": "<slice>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "112": {
118
+ "content": "</slice>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ }
125
+ },
126
+ "additional_special_tokens": [
127
+ "<image>",
128
+ "</image>",
129
+ "<ref>",
130
+ "</ref>",
131
+ "<box>",
132
+ "</box>",
133
+ "<quad>",
134
+ "</quad>",
135
+ "<point>",
136
+ "</point>",
137
+ "<slice>",
138
+ "</slice>"
139
+ ],
140
+ "auto_map": {
141
+ "AutoTokenizer": [
142
+ "modeling_minicpmv.LlamaTokenizerWrapper",
143
+ null
144
+ ]
145
+ },
146
+ "bos_token": "<s>",
147
+ "clean_up_tokenization_spaces": false,
148
+ "eos_token": "</s>",
149
+ "legacy": true,
150
+ "model_max_length": 1000000000000000019884624838656,
151
+ "pad_token": "<unk>",
152
+ "padding_side": "right",
153
+ "sp_model_kwargs": {},
154
+ "spaces_between_special_tokens": false,
155
+ "tokenizer_class": "LlamaTokenizerWrapper",
156
+ "truncation_side": "right",
157
+ "unk_token": "<unk>",
158
+ "use_default_system_prompt": false
159
+ }