Hugging Face's logo

stockmark
/
Stockmark-2-VL-100B-beta

Image-Text-to-Text
Transformers
Safetensors
Japanese
English
llava_onevision
image-to-text
multimodal
conversational
Model card Files
xet
Community
shichenpy commited on
Commit
145a623
·
1 Parent(s): 0136496

Upload

Browse files
Files changed (50) hide show
  1. README.md +3 -3
  2. chat_template.json +3 -0
  3. config.json +207 -0
  4. generation_config.json +10 -0
  5. model-00001-of-00040.safetensors +3 -0
  6. model-00002-of-00040.safetensors +3 -0
  7. model-00003-of-00040.safetensors +3 -0
  8. model-00004-of-00040.safetensors +3 -0
  9. model-00005-of-00040.safetensors +3 -0
  10. model-00006-of-00040.safetensors +3 -0
  11. model-00007-of-00040.safetensors +3 -0
  12. model-00008-of-00040.safetensors +3 -0
  13. model-00009-of-00040.safetensors +3 -0
  14. model-00010-of-00040.safetensors +3 -0
  15. model-00011-of-00040.safetensors +3 -0
  16. model-00012-of-00040.safetensors +3 -0
  17. model-00013-of-00040.safetensors +3 -0
  18. model-00014-of-00040.safetensors +3 -0
  19. model-00015-of-00040.safetensors +3 -0
  20. model-00016-of-00040.safetensors +3 -0
  21. model-00017-of-00040.safetensors +3 -0
  22. model-00018-of-00040.safetensors +3 -0
  23. model-00019-of-00040.safetensors +3 -0
  24. model-00020-of-00040.safetensors +3 -0
  25. model-00021-of-00040.safetensors +3 -0
  26. model-00022-of-00040.safetensors +3 -0
  27. model-00023-of-00040.safetensors +3 -0
  28. model-00024-of-00040.safetensors +3 -0
  29. model-00025-of-00040.safetensors +3 -0
  30. model-00026-of-00040.safetensors +3 -0
  31. model-00027-of-00040.safetensors +3 -0
  32. model-00028-of-00040.safetensors +3 -0
  33. model-00029-of-00040.safetensors +3 -0
  34. model-00030-of-00040.safetensors +3 -0
  35. model-00031-of-00040.safetensors +3 -0
  36. model-00032-of-00040.safetensors +3 -0
  37. model-00033-of-00040.safetensors +3 -0
  38. model-00034-of-00040.safetensors +3 -0
  39. model-00035-of-00040.safetensors +3 -0
  40. model-00036-of-00040.safetensors +3 -0
  41. model-00037-of-00040.safetensors +3 -0
  42. model-00038-of-00040.safetensors +3 -0
  43. model-00039-of-00040.safetensors +3 -0
  44. model-00040-of-00040.safetensors +3 -0
  45. model.safetensors.index.json +0 -0
  46. preprocessor_config.json +171 -0
  47. processor_config.json +7 -0
  48. special_tokens_map.json +46 -0
  49. tokenizer.json +0 -0
  50. tokenizer_config.json +233 -0
README.md CHANGED
@@ -1,3 +1,3 @@
1
- ---
2
- license: mit
3
- ---
 
1
+ ---
2
+ license: mit
3
+ ---
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>\n' + message['content'] + '<|end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlavaOnevisionForConditionalGeneration"
4
+ ],
5
+ "image_grid_pinpoints": [
6
+ [
7
+ 384,
8
+ 384
9
+ ],
10
+ [
11
+ 384,
12
+ 768
13
+ ],
14
+ [
15
+ 384,
16
+ 1152
17
+ ],
18
+ [
19
+ 384,
20
+ 1536
21
+ ],
22
+ [
23
+ 384,
24
+ 1920
25
+ ],
26
+ [
27
+ 384,
28
+ 2304
29
+ ],
30
+ [
31
+ 768,
32
+ 384
33
+ ],
34
+ [
35
+ 768,
36
+ 768
37
+ ],
38
+ [
39
+ 768,
40
+ 1152
41
+ ],
42
+ [
43
+ 768,
44
+ 1536
45
+ ],
46
+ [
47
+ 768,
48
+ 1920
49
+ ],
50
+ [
51
+ 768,
52
+ 2304
53
+ ],
54
+ [
55
+ 1152,
56
+ 384
57
+ ],
58
+ [
59
+ 1152,
60
+ 768
61
+ ],
62
+ [
63
+ 1152,
64
+ 1152
65
+ ],
66
+ [
67
+ 1152,
68
+ 1536
69
+ ],
70
+ [
71
+ 1152,
72
+ 1920
73
+ ],
74
+ [
75
+ 1152,
76
+ 2304
77
+ ],
78
+ [
79
+ 1536,
80
+ 384
81
+ ],
82
+ [
83
+ 1536,
84
+ 768
85
+ ],
86
+ [
87
+ 1536,
88
+ 1152
89
+ ],
90
+ [
91
+ 1536,
92
+ 1536
93
+ ],
94
+ [
95
+ 1536,
96
+ 1920
97
+ ],
98
+ [
99
+ 1536,
100
+ 2304
101
+ ],
102
+ [
103
+ 1920,
104
+ 384
105
+ ],
106
+ [
107
+ 1920,
108
+ 768
109
+ ],
110
+ [
111
+ 1920,
112
+ 1152
113
+ ],
114
+ [
115
+ 1920,
116
+ 1536
117
+ ],
118
+ [
119
+ 1920,
120
+ 1920
121
+ ],
122
+ [
123
+ 1920,
124
+ 2304
125
+ ],
126
+ [
127
+ 2304,
128
+ 384
129
+ ],
130
+ [
131
+ 2304,
132
+ 768
133
+ ],
134
+ [
135
+ 2304,
136
+ 1152
137
+ ],
138
+ [
139
+ 2304,
140
+ 1536
141
+ ],
142
+ [
143
+ 2304,
144
+ 1920
145
+ ],
146
+ [
147
+ 2304,
148
+ 2304
149
+ ]
150
+ ],
151
+ "image_token_index": 100352,
152
+ "model_type": "llava_onevision",
153
+ "multimodal_projector_bias": true,
154
+ "num_image_tokens": 6551,
155
+ "projector_hidden_act": "gelu",
156
+ "text_config": {
157
+ "_name_or_path": "stockmark/Stockmark-2-100B-Instruct-beta",
158
+ "architectures": [
159
+ "LlamaForCausalLM"
160
+ ],
161
+ "attention_bias": false,
162
+ "attention_dropout": 0.0,
163
+ "bos_token_id": 0,
164
+ "eos_token_id": 1,
165
+ "head_dim": 128,
166
+ "hidden_act": "silu",
167
+ "hidden_size": 9216,
168
+ "initializer_range": 0.02,
169
+ "intermediate_size": 32768,
170
+ "max_position_embeddings": 32768,
171
+ "mlp_bias": false,
172
+ "model_type": "llama",
173
+ "num_attention_heads": 72,
174
+ "num_hidden_layers": 86,
175
+ "num_key_value_heads": 8,
176
+ "pad_token_id": 2,
177
+ "pretraining_tp": 1,
178
+ "rms_norm_eps": 1e-05,
179
+ "rope_scaling": null,
180
+ "rope_theta": 10000.0,
181
+ "torch_dtype": "bfloat16",
182
+ "use_cache": true,
183
+ "vocab_size": 100416
184
+ },
185
+ "tie_word_embeddings": false,
186
+ "torch_dtype": "bfloat16",
187
+ "transformers_version": "4.51.3",
188
+ "use_image_newline_parameter": true,
189
+ "video_token_index": 100353,
190
+ "vision_aspect_ratio": "anyres_max_9",
191
+ "vision_config": {
192
+ "attention_dropout": 0.0,
193
+ "hidden_act": "gelu_pytorch_tanh",
194
+ "hidden_size": 1152,
195
+ "image_size": 384,
196
+ "intermediate_size": 4304,
197
+ "layer_norm_eps": 1e-06,
198
+ "model_type": "siglip_vision_model",
199
+ "num_attention_heads": 16,
200
+ "num_channels": 3,
201
+ "num_hidden_layers": 26,
202
+ "patch_size": 14,
203
+ "vision_use_head": false
204
+ },
205
+ "vision_feature_layer": -1,
206
+ "vision_feature_select_strategy": "full"
207
+ }
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": [
5
+ 1,
6
+ 7
7
+ ],
8
+ "pad_token_id": 2,
9
+ "transformers_version": "4.51.3"
10
+ }
model-00001-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:891e0f2315292a624fb3c40e2ca7ea7b266805dbbed3a34140c7b2407928a6b0
3
+ size 4909732568
model-00002-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de805ccf245ccbdda5b8e36cca4a994a60bf10056dafd25b05e25d4f38c230ca
3
+ size 4982927952
model-00003-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:882479a9a015aa0959bd3f1b058b08785529268329582bbac53a86f76ab179d1
3
+ size 4756435944
model-00004-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9159d6e1558654118dac132721459a05f3c1f85b0e619d3499b65d2818cb6189
3
+ size 4982909416
model-00005-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bb0f335189f7b0898eabadba9a2584d3e1d8856cb36bba9e307df2c8593dc81
3
+ size 4982909416
model-00006-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3f9177d1aa072350e5b9349b652f221897e81a918da3b9dee1d31c47ecbe62a
3
+ size 4982927968
model-00007-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b28378b7a80794a2f5a750e1d4dac17b5d87d18eddef18164643f34b42e1cd6
3
+ size 4756435936
model-00008-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84d9395b0f4f89000317eae3c986ba8c15040a072db2acdba711b93d7af65f80
3
+ size 4982909416
model-00009-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcd619191f4d3c97f20a41dc3d2844da8107e1da2041a6edbfa08b3a128bbca7
3
+ size 4982909416
model-00010-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8f0514ff460b557b1475d9df1ea97cfe8d8d03b17320e8c8f437e8eb12ec731
3
+ size 4982927968
model-00011-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:232031161bc4eabe28ac92290972c8fbbec0575d9a9bbb67bde59769ab5cfac6
3
+ size 4756435944
model-00012-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aef46de1759c72fd5699cb34de08c0515f8e0cff1c137fed66e16145f11f0cdd
3
+ size 4982909408
model-00013-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93aa1a9344a46a6d60cd05b50747bd58bbba626859f26a2446b69bb958703f1c
3
+ size 4982909416
model-00014-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9a65c027111a56915db6e08acb142ff66df0e1691b13e14da1ad178cb8425a3
3
+ size 4982927968
model-00015-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:622bf8c1c2cc74f6f31bdec483ce4dea75c978015191610b7ca059fc37f60841
3
+ size 4756435944
model-00016-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9c6f41acee4bbb88be156ce825cd3768f02c7d93d550b9cee627c307316c263
3
+ size 4982909416
model-00017-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928706f132a87462be6f70c726cb3e015af4621a41fbbde0491b7c4a743c2d80
3
+ size 4982909408
model-00018-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1671591bb66fdf6b111d053fcc9e447a08b53463f9c52062cf5a3e8eb923481
3
+ size 4982927968
model-00019-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d733019084e09fefc0299d64feae97dcc6e9ccbfe96dd3370b1d823b60f847d1
3
+ size 4756435944
model-00020-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b43265dc5b3c984ec20ca9502be32a9cb2679e2a4eca6cb8906c0518c96022ac
3
+ size 4982909416
model-00021-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28caf6a4adccea0466f4e5ace43eb94896e83209d4a63131784ed9cab1711b43
3
+ size 4982909416
model-00022-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cfd810370c907c53665f11fc4f9b628df784e5446fa63abf9b834ee034ebfb7
3
+ size 4982927960
model-00023-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d902150ffbdee3f26f9ccfde9da0900758affaea2ed827b8ff26625177baf025
3
+ size 4756435944
model-00024-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6df16678c34f4640c8f07d715d5273241b3557c13b29020c5ad0d152edeefa25
3
+ size 4982909416
model-00025-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ad41eebd912b0a75935b13ea4e3eb6545e718de0d88d035d84819dc8f7887c2
3
+ size 4982909416
model-00026-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d0bd063afc94acccce2b69c3f595ba3636acefc3b00d7adc7ab1c589925dda9
3
+ size 4982927968
model-00027-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e55ff135b490cc9ab1a0e9316d4014c4e375e8607e0f45ba86bd53282c7c640
3
+ size 4756435944
model-00028-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6853229f338366bbfc9b0618e59f9bdf278984ebbc5d98179fac621a7f0ac15a
3
+ size 4982909416
model-00029-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d823ca10fcc17d6e7c63b3813ac8bc3b714b053c18ab0186e096165e4c02804
3
+ size 4982909416
model-00030-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:802fd94a74c3b73df5de9552cfb7a7db4aac0eaba1085f2fa236aaebbf023871
3
+ size 4982927968
model-00031-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dab82b3a8beb729097207c915a5d739f57f75f11a96149a711b37a1e42cdc7c
3
+ size 4756435936
model-00032-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:019d0b58fc9f6a01d7629315e3922598443a51c0a1dbf4f2b40f90711a97616f
3
+ size 4982909416
model-00033-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0820de450b01caf4b688ed86e2a4aa7491633f3879d4827489ff14e8eee1511
3
+ size 4982909416
model-00034-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:432c327d9b250dce7d59b17ea28df56b6f0ad8dad56999727aeed2837176122a
3
+ size 4982927968
model-00035-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff34ef1cc81b63f0bfe4c7db09141b48cc401d893305381af456818af2124178
3
+ size 4756435944
model-00036-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:237079a25ee9bc571e4e0d833f24bc0754acd96613870c0cb32eb61c77df3b45
3
+ size 4982909408
model-00037-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56a33be7aed7259ee374701ab10f953b61047eb9d509ee7616bdb9bb69da2959
3
+ size 4982909416
model-00038-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35e0a398daf3e44d8bc0dba0d38bb1a4dfc01932a0cc5b515a70d95bf64eb9f9
3
+ size 4982927968
model-00039-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:270c78267cb05a40c63650f8f81bcc0d91adc73952376e13a894628b244ee0de
3
+ size 4991031976
model-00040-of-00040.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f6575921b29111726be00965999115dcf110ecffae2bbb3f50d3e86456b9361
3
+ size 752097024
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "image_grid_pinpoints": [
8
+ [
9
+ 384,
10
+ 384
11
+ ],
12
+ [
13
+ 384,
14
+ 768
15
+ ],
16
+ [
17
+ 384,
18
+ 1152
19
+ ],
20
+ [
21
+ 384,
22
+ 1536
23
+ ],
24
+ [
25
+ 384,
26
+ 1920
27
+ ],
28
+ [
29
+ 384,
30
+ 2304
31
+ ],
32
+ [
33
+ 768,
34
+ 384
35
+ ],
36
+ [
37
+ 768,
38
+ 768
39
+ ],
40
+ [
41
+ 768,
42
+ 1152
43
+ ],
44
+ [
45
+ 768,
46
+ 1536
47
+ ],
48
+ [
49
+ 768,
50
+ 1920
51
+ ],
52
+ [
53
+ 768,
54
+ 2304
55
+ ],
56
+ [
57
+ 1152,
58
+ 384
59
+ ],
60
+ [
61
+ 1152,
62
+ 768
63
+ ],
64
+ [
65
+ 1152,
66
+ 1152
67
+ ],
68
+ [
69
+ 1152,
70
+ 1536
71
+ ],
72
+ [
73
+ 1152,
74
+ 1920
75
+ ],
76
+ [
77
+ 1152,
78
+ 2304
79
+ ],
80
+ [
81
+ 1536,
82
+ 384
83
+ ],
84
+ [
85
+ 1536,
86
+ 768
87
+ ],
88
+ [
89
+ 1536,
90
+ 1152
91
+ ],
92
+ [
93
+ 1536,
94
+ 1536
95
+ ],
96
+ [
97
+ 1536,
98
+ 1920
99
+ ],
100
+ [
101
+ 1536,
102
+ 2304
103
+ ],
104
+ [
105
+ 1920,
106
+ 384
107
+ ],
108
+ [
109
+ 1920,
110
+ 768
111
+ ],
112
+ [
113
+ 1920,
114
+ 1152
115
+ ],
116
+ [
117
+ 1920,
118
+ 1536
119
+ ],
120
+ [
121
+ 1920,
122
+ 1920
123
+ ],
124
+ [
125
+ 1920,
126
+ 2304
127
+ ],
128
+ [
129
+ 2304,
130
+ 384
131
+ ],
132
+ [
133
+ 2304,
134
+ 768
135
+ ],
136
+ [
137
+ 2304,
138
+ 1152
139
+ ],
140
+ [
141
+ 2304,
142
+ 1536
143
+ ],
144
+ [
145
+ 2304,
146
+ 1920
147
+ ],
148
+ [
149
+ 2304,
150
+ 2304
151
+ ]
152
+ ],
153
+ "image_mean": [
154
+ 0.5,
155
+ 0.5,
156
+ 0.5
157
+ ],
158
+ "image_processor_type": "LlavaOnevisionImageProcessor",
159
+ "image_std": [
160
+ 0.5,
161
+ 0.5,
162
+ 0.5
163
+ ],
164
+ "processor_class": "LlavaOnevisionProcessor",
165
+ "resample": 2,
166
+ "rescale_factor": 0.00392156862745098,
167
+ "size": {
168
+ "height": 384,
169
+ "width": 384
170
+ }
171
+ }
processor_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_token": "<image>",
3
+ "num_image_tokens": 729,
4
+ "processor_class": "LlavaOnevisionProcessor",
5
+ "video_token": "<video>",
6
+ "vision_feature_select_strategy": "full"
7
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<image>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<video>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": {
19
+ "content": "<s>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "</s>",
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
+ "unk_token": {
40
+ "content": "<unk>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ }
46
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<s>",
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": "<pad>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<|system|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "5": {
46
+ "content": "<|user|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "6": {
54
+ "content": "<|assistant|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "7": {
62
+ "content": "<|end|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "8": {
70
+ "content": "<|reserved_special_token_0|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "9": {
78
+ "content": "<|reserved_special_token_1|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "10": {
86
+ "content": "<|reserved_special_token_2|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "11": {
94
+ "content": "<|reserved_special_token_3|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "12": {
102
+ "content": "<|reserved_special_token_4|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "13": {
110
+ "content": "<|reserved_special_token_5|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "14": {
118
+ "content": "<|reserved_special_token_6|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "15": {
126
+ "content": "<|reserved_special_token_7|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "16": {
134
+ "content": "<|reserved_special_token_8|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "17": {
142
+ "content": "<|reserved_special_token_9|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "18": {
150
+ "content": "<|reserved_special_token_10|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "19": {
158
+ "content": "<|reserved_special_token_11|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "20": {
166
+ "content": "<|reserved_special_token_12|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "21": {
174
+ "content": "<|reserved_special_token_13|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "22": {
182
+ "content": "<|reserved_special_token_14|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "23": {
190
+ "content": "<|reserved_special_token_15|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "100352": {
198
+ "content": "<image>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "100353": {
206
+ "content": "<video>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<image>",
216
+ "<video>"
217
+ ],
218
+ "bos_token": "<s>",
219
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>\n' + message['content'] + '<|end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}",
220
+ "clean_up_tokenization_spaces": false,
221
+ "eos_token": "</s>",
222
+ "extra_special_tokens": {},
223
+ "model_input_names": [
224
+ "input_ids",
225
+ "attention_mask"
226
+ ],
227
+ "model_max_length": 1000000000000000019884624838656,
228
+ "pad_token": "<pad>",
229
+ "padding_side": "left",
230
+ "processor_class": "LlavaOnevisionProcessor",
231
+ "tokenizer_class": "PreTrainedTokenizer",
232
+ "unk_token": "<unk>"
233
+ }