Choiszt commited on
Commit
98513c7
·
verified ·
1 Parent(s): 7f9360d

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<image>": 151646,
3
+ "<|endoftext|>": 151643,
4
+ "<|im_end|>": 151645,
5
+ "<|im_start|>": 151644
6
+ }
config.json ADDED
@@ -0,0 +1,216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pretrained/models--lmms-lab--llava-onevision-qwen2-7b-ov/snapshots/llava-onevision-qwen2-7b-ov",
3
+ "architectures": [
4
+ "MVLlavaQwenForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "ignore_index": -100,
12
+ "image_aspect_ratio": "anyres_max_9",
13
+ "image_crop_resolution": null,
14
+ "image_grid_pinpoints": [
15
+ [
16
+ 384,
17
+ 384
18
+ ],
19
+ [
20
+ 384,
21
+ 768
22
+ ],
23
+ [
24
+ 384,
25
+ 1152
26
+ ],
27
+ [
28
+ 384,
29
+ 1536
30
+ ],
31
+ [
32
+ 384,
33
+ 1920
34
+ ],
35
+ [
36
+ 384,
37
+ 2304
38
+ ],
39
+ [
40
+ 768,
41
+ 384
42
+ ],
43
+ [
44
+ 768,
45
+ 768
46
+ ],
47
+ [
48
+ 768,
49
+ 1152
50
+ ],
51
+ [
52
+ 768,
53
+ 1536
54
+ ],
55
+ [
56
+ 768,
57
+ 1920
58
+ ],
59
+ [
60
+ 768,
61
+ 2304
62
+ ],
63
+ [
64
+ 1152,
65
+ 384
66
+ ],
67
+ [
68
+ 1152,
69
+ 768
70
+ ],
71
+ [
72
+ 1152,
73
+ 1152
74
+ ],
75
+ [
76
+ 1152,
77
+ 1536
78
+ ],
79
+ [
80
+ 1152,
81
+ 1920
82
+ ],
83
+ [
84
+ 1152,
85
+ 2304
86
+ ],
87
+ [
88
+ 1536,
89
+ 384
90
+ ],
91
+ [
92
+ 1536,
93
+ 768
94
+ ],
95
+ [
96
+ 1536,
97
+ 1152
98
+ ],
99
+ [
100
+ 1536,
101
+ 1536
102
+ ],
103
+ [
104
+ 1536,
105
+ 1920
106
+ ],
107
+ [
108
+ 1536,
109
+ 2304
110
+ ],
111
+ [
112
+ 1920,
113
+ 384
114
+ ],
115
+ [
116
+ 1920,
117
+ 768
118
+ ],
119
+ [
120
+ 1920,
121
+ 1152
122
+ ],
123
+ [
124
+ 1920,
125
+ 1536
126
+ ],
127
+ [
128
+ 1920,
129
+ 1920
130
+ ],
131
+ [
132
+ 1920,
133
+ 2304
134
+ ],
135
+ [
136
+ 2304,
137
+ 384
138
+ ],
139
+ [
140
+ 2304,
141
+ 768
142
+ ],
143
+ [
144
+ 2304,
145
+ 1152
146
+ ],
147
+ [
148
+ 2304,
149
+ 1536
150
+ ],
151
+ [
152
+ 2304,
153
+ 1920
154
+ ],
155
+ [
156
+ 2304,
157
+ 2304
158
+ ]
159
+ ],
160
+ "image_split_resolution": null,
161
+ "image_token_index": 151646,
162
+ "initializer_range": 0.02,
163
+ "intermediate_size": 18944,
164
+ "max_position_embeddings": 32768,
165
+ "max_window_layers": 28,
166
+ "mm_hidden_size": 1152,
167
+ "mm_newline_position": "one_token",
168
+ "mm_patch_merge_type": "spatial_unpad",
169
+ "mm_projector_lr": null,
170
+ "mm_projector_type": "mlp2x_gelu",
171
+ "mm_resampler_type": null,
172
+ "mm_spatial_pool_mode": "bilinear",
173
+ "mm_tunable_parts": "mm_vision_tower,mm_motion_tower",
174
+ "mm_use_im_patch_token": false,
175
+ "mm_use_im_start_end": false,
176
+ "mm_vision_select_feature": "patch",
177
+ "mm_vision_select_layer": -2,
178
+ "mm_vision_tower": "google/siglip-so400m-patch14-384",
179
+ "mm_vision_tower_lr": 2e-06,
180
+ "model_type": "llava",
181
+ "num_attention_heads": 28,
182
+ "num_hidden_layers": 28,
183
+ "num_key_value_heads": 4,
184
+ "pos_skipping_range": 4096,
185
+ "projector_hidden_act": "gelu",
186
+ "rms_norm_eps": 1e-06,
187
+ "rope_scaling": null,
188
+ "rope_theta": 1000000.0,
189
+ "sliding_window": 131072,
190
+ "text_config": {
191
+ "model_type": "llama"
192
+ },
193
+ "tie_word_embeddings": false,
194
+ "tokenizer_model_max_length": 8192,
195
+ "tokenizer_padding_side": "right",
196
+ "torch_dtype": "float32",
197
+ "transformers_version": "4.39.2",
198
+ "use_cache": true,
199
+ "use_mm_proj": true,
200
+ "use_pos_skipping": false,
201
+ "use_sliding_window": false,
202
+ "vision_config": {
203
+ "hidden_size": 1024,
204
+ "image_size": 336,
205
+ "intermediate_size": 4096,
206
+ "model_type": "clip_vision_model",
207
+ "num_attention_heads": 16,
208
+ "num_hidden_layers": 24,
209
+ "patch_size": 14,
210
+ "projection_dim": 768,
211
+ "vocab_size": 32000
212
+ },
213
+ "vision_feature_layer": -2,
214
+ "vision_feature_select_strategy": "default",
215
+ "vision_tower_pretrained": null
216
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.39.2"
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fb66c57a7db2d5490444a3969652beef893fe57663f70cb4d92c4ae709356c7
3
+ size 4976701640
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e1b3468ad6c2cec0de059de481d2cd6b70d6ec4d471cc99b818146047b6c402
3
+ size 4778622352
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a429eb945795d213647bded20cea26b910a358b200ad29602353a68199b47655
3
+ size 4932743960
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e22e6974839f25f665238822e00c22e5c3d8e9d5943daf835779083f23153b0d
3
+ size 4932743992
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e89c42b01f165eb59216ae30eabbce4674bccf73db94b518e047079e2d37c0af
3
+ size 4998852296
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3ea021c2103526b1b5277094a2be53bc005f0adb3bcc482eaa231fa06f271e3
3
+ size 4744023488
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:959e245726a2c9d0cd8c80be70ea11ba135b16a448898df89d1aaeda5239f5a4
3
+ size 2179989632
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<image>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "additional_special_tokens": [
38
+ "<|im_start|>",
39
+ "<|im_end|>"
40
+ ],
41
+ "bos_token": null,
42
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
43
+ "clean_up_tokenization_spaces": false,
44
+ "eos_token": "<|im_end|>",
45
+ "errors": "replace",
46
+ "model_max_length": 8192,
47
+ "pad_token": "<|endoftext|>",
48
+ "padding_side": "right",
49
+ "processor_class": "LlavaProcessor",
50
+ "split_special_tokens": false,
51
+ "tokenizer_class": "Qwen2Tokenizer",
52
+ "unk_token": null
53
+ }
trainer_state.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": null,
5
+ "eval_steps": 500,
6
+ "global_step": 0,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 500,
12
+ "max_steps": 0,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 0,
15
+ "save_steps": 500,
16
+ "total_flos": 0,
17
+ "train_batch_size": null,
18
+ "trial_name": null,
19
+ "trial_params": null
20
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a18cc67a721fb4310566ef84db75213c2060b9d11058d41ec0492a1547254eb9
3
+ size 6648
vocab.json ADDED
The diff for this file is too large to render. See raw diff