Hugging Face's logo

deepseek-ai
/
deepseek-vl2-tiny

Image-Text-to-Text
Transformers
Safetensors
deepseek_vl_v2
Model card Files
xet
Community
16
doubility123 commited on
Commit
46a21c1
·
verified ·
1 Parent(s): 57ea787

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +150 -0
  2. model-00001-of-000001.safetensors +3 -0
  3. model.safetensors.index.json +0 -0
  4. processor_config.json +116 -0
  5. special_tokens_map.json +39 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +0 -0
config.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "candidate_resolutions": [
3
+ [
4
+ 384,
5
+ 384
6
+ ],
7
+ [
8
+ 384,
9
+ 768
10
+ ],
11
+ [
12
+ 768,
13
+ 384
14
+ ],
15
+ [
16
+ 384,
17
+ 1152
18
+ ],
19
+ [
20
+ 1152,
21
+ 384
22
+ ],
23
+ [
24
+ 384,
25
+ 1536
26
+ ],
27
+ [
28
+ 1536,
29
+ 384
30
+ ],
31
+ [
32
+ 768,
33
+ 768
34
+ ],
35
+ [
36
+ 384,
37
+ 1920
38
+ ],
39
+ [
40
+ 1920,
41
+ 384
42
+ ],
43
+ [
44
+ 384,
45
+ 2304
46
+ ],
47
+ [
48
+ 2304,
49
+ 384
50
+ ],
51
+ [
52
+ 768,
53
+ 1152
54
+ ],
55
+ [
56
+ 1152,
57
+ 768
58
+ ],
59
+ [
60
+ 384,
61
+ 2688
62
+ ],
63
+ [
64
+ 2688,
65
+ 384
66
+ ],
67
+ [
68
+ 384,
69
+ 3072
70
+ ],
71
+ [
72
+ 3072,
73
+ 384
74
+ ],
75
+ [
76
+ 768,
77
+ 1536
78
+ ],
79
+ [
80
+ 1536,
81
+ 768
82
+ ],
83
+ [
84
+ 384,
85
+ 3456
86
+ ],
87
+ [
88
+ 3456,
89
+ 384
90
+ ],
91
+ [
92
+ 1152,
93
+ 1152
94
+ ]
95
+ ],
96
+ "global_view_pos": "head",
97
+ "language_config": {
98
+ "architectures": [
99
+ "DeepseekV2ForCausalLM"
100
+ ],
101
+ "auto_map": {
102
+ "AutoConfig": "configuration_deepseek.DeepseekV2Config",
103
+ "AutoModel": "modeling_deepseek.DeepseekV2Model",
104
+ "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
105
+ },
106
+ "bos_token_id": 0,
107
+ "eos_token_id": 1,
108
+ "first_k_dense_replace": 1,
109
+ "hidden_size": 1280,
110
+ "intermediate_size": 6848,
111
+ "kv_lora_rank": null,
112
+ "lm_head": true,
113
+ "max_position_embeddings": 4096,
114
+ "model_type": "deepseek_v2",
115
+ "moe_intermediate_size": 896,
116
+ "n_group": 1,
117
+ "n_routed_experts": 64,
118
+ "n_shared_experts": 2,
119
+ "num_attention_heads": 10,
120
+ "num_experts_per_tok": 6,
121
+ "num_hidden_layers": 12,
122
+ "num_key_value_heads": 10,
123
+ "q_lora_rank": null,
124
+ "qk_nope_head_dim": 0,
125
+ "qk_rope_head_dim": 0,
126
+ "rm_head": false,
127
+ "topk_group": 1,
128
+ "topk_method": "greedy",
129
+ "torch_dtype": "bfloat16",
130
+ "use_mla": false,
131
+ "v_head_dim": 0,
132
+ "vocab_size": 129280
133
+ },
134
+ "model_type": "deepseek_vl_v2",
135
+ "projector_config": {
136
+ "model_type": "mlp_projector",
137
+ "n_embed": 1280
138
+ },
139
+ "tile_tag": "2D",
140
+ "torch_dtype": "bfloat16",
141
+ "transformers_version": "4.38.2",
142
+ "vision_config": {
143
+ "layers": 27,
144
+ "mlp_ratio": 3.7362,
145
+ "model_name": "siglip_so400m_patch14_384",
146
+ "model_type": "vision",
147
+ "patch_size": 14,
148
+ "width": 1152
149
+ }
150
+ }
model-00001-of-000001.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc1e5047280253e224b299677bea16b7960c2436ec676d28911ebd9de3bb0074
3
+ size 6741334208
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
processor_config.json ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_special_token": false,
3
+ "candidate_resolutions": [
4
+ [
5
+ 384,
6
+ 384
7
+ ],
8
+ [
9
+ 384,
10
+ 768
11
+ ],
12
+ [
13
+ 768,
14
+ 384
15
+ ],
16
+ [
17
+ 384,
18
+ 1152
19
+ ],
20
+ [
21
+ 1152,
22
+ 384
23
+ ],
24
+ [
25
+ 384,
26
+ 1536
27
+ ],
28
+ [
29
+ 1536,
30
+ 384
31
+ ],
32
+ [
33
+ 768,
34
+ 768
35
+ ],
36
+ [
37
+ 384,
38
+ 1920
39
+ ],
40
+ [
41
+ 1920,
42
+ 384
43
+ ],
44
+ [
45
+ 384,
46
+ 2304
47
+ ],
48
+ [
49
+ 2304,
50
+ 384
51
+ ],
52
+ [
53
+ 768,
54
+ 1152
55
+ ],
56
+ [
57
+ 1152,
58
+ 768
59
+ ],
60
+ [
61
+ 384,
62
+ 2688
63
+ ],
64
+ [
65
+ 2688,
66
+ 384
67
+ ],
68
+ [
69
+ 384,
70
+ 3072
71
+ ],
72
+ [
73
+ 3072,
74
+ 384
75
+ ],
76
+ [
77
+ 768,
78
+ 1536
79
+ ],
80
+ [
81
+ 1536,
82
+ 768
83
+ ],
84
+ [
85
+ 384,
86
+ 3456
87
+ ],
88
+ [
89
+ 3456,
90
+ 384
91
+ ],
92
+ [
93
+ 1152,
94
+ 1152
95
+ ]
96
+ ],
97
+ "downsample_ratio": 2,
98
+ "ignore_id": -100,
99
+ "image_mean": [
100
+ 0.5,
101
+ 0.5,
102
+ 0.5
103
+ ],
104
+ "image_std": [
105
+ 0.5,
106
+ 0.5,
107
+ 0.5
108
+ ],
109
+ "image_token": "<image>",
110
+ "mask_prompt": false,
111
+ "normalize": true,
112
+ "pad_token": "<\uff5c\u2581pad\u2581\uff5c>",
113
+ "patch_size": 14,
114
+ "processor_class": "DeepseekVLV2Processor",
115
+ "sft_format": "deepseek"
116
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|User|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|Assistant|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<｜begin▁of▁sentence｜>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "<｜end▁of▁sentence｜>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "pad_token": {
33
+ "content": "<｜▁pad▁｜>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ }
39
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff