Visual Question Answering
Transformers
PyTorch
omnilmm
text-generation
Inference Endpoints
finalf0 commited on
Commit
d99da91
1 Parent(s): c85f2f5
added_tokens.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 32004,
3
+ "</quad>": 32008,
4
+ "</ref>": 32006,
5
+ "<box>": 32003,
6
+ "<im_end>": 32002,
7
+ "<im_patch>": 32000,
8
+ "<im_start>": 32001,
9
+ "<quad>": 32007,
10
+ "<ref>": 32005
11
+ }
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/yutianyu/Zephyr_checkpoints/SFT_exp/zephyr_mm_12b_SFT-knowledge_v0-caterpillar-stage2_mix#caterpillar-stage3_lvis#caterpillar-stage3_svit#caterpillar-stage3_sharegpt4v#llava#unimm-chat#mme_art500k#google_landmark-train#places_365-train#wit-en-13#22#60#10#16#12#15#10#2#20/checkpionts/checkpoint-4000",
3
+ "architectures": [
4
+ "ZephyrMMForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "fully_tune": true,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "image_size": 448,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 32768,
15
+ "mm_use_im_start_end": true,
16
+ "mm_vision_tower": "eva02_enormous_patch14_clip_224.laion2b_plus",
17
+ "model_type": "zephyr_mm",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "num_query": 256,
22
+ "pad_token_id": 2,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_theta": 10000.0,
25
+ "sliding_window": 4096,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.35.0",
29
+ "tune_CLIP": true,
30
+ "tune_mm_mlp_adapter": false,
31
+ "use_cache": false,
32
+ "use_mm_proj": true,
33
+ "vocab_size": 32009
34
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.35.0"
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8b8bc958406ad8de704860fc9d772e16aff0c1759936eaacbf82c5912d68654
3
+ size 23232471087
special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>",
6
+ "<im_patch>",
7
+ "<im_start>",
8
+ "<im_end>",
9
+ "<box>",
10
+ "</box>",
11
+ "<ref>",
12
+ "</ref>",
13
+ "<quad>",
14
+ "</quad>"
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": {
31
+ "content": "</s>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "unk_token": {
38
+ "content": "<unk>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ }
44
+ }
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 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32000": {
30
+ "content": "<im_patch>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<im_start>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<im_end>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<box>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "</box>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<ref>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32006": {
78
+ "content": "</ref>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32007": {
86
+ "content": "<quad>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32008": {
94
+ "content": "</quad>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ }
101
+ },
102
+ "additional_special_tokens": [
103
+ "<unk>",
104
+ "<s>",
105
+ "</s>",
106
+ "<im_patch>",
107
+ "<im_start>",
108
+ "<im_end>",
109
+ "<box>",
110
+ "</box>",
111
+ "<ref>",
112
+ "</ref>",
113
+ "<quad>",
114
+ "</quad>"
115
+ ],
116
+ "bos_token": "<s>",
117
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
118
+ "clean_up_tokenization_spaces": false,
119
+ "eos_token": "</s>",
120
+ "legacy": true,
121
+ "model_max_length": 2048,
122
+ "pad_token": "</s>",
123
+ "padding_side": "right",
124
+ "sp_model_kwargs": {},
125
+ "spaces_between_special_tokens": false,
126
+ "tokenizer_class": "LlamaTokenizer",
127
+ "truncation_side": "right",
128
+ "unk_token": "<unk>",
129
+ "use_default_system_prompt": true
130
+ }