Text-to-Image
Diffusers
Safetensors
ntk1507 commited on
Commit
dd355d3
·
verified ·
1 Parent(s): fb9851e

Upload folder using huggingface_hub

Browse files
MVRD/d28_lambda0.5_fullft_aug2/added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<image>": 151646,
3
+ "<|endoftext|>": 151643,
4
+ "<|im_end|>": 151645,
5
+ "<|im_start|>": 151644
6
+ }
MVRD/d28_lambda0.5_fullft_aug2/config.json ADDED
@@ -0,0 +1,225 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "lmms-lab/LLaVA-Video-7B-Qwen2",
3
+ "add_faster_video": false,
4
+ "add_time_instruction": false,
5
+ "architectures": [
6
+ "LlavaQwenForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 151643,
10
+ "distill_layer": 28,
11
+ "eos_token_id": 151645,
12
+ "faster_token_stride": 10,
13
+ "force_sample": true,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 3584,
16
+ "ignore_index": -100,
17
+ "image_aspect_ratio": "anyres_max_9",
18
+ "image_crop_resolution": null,
19
+ "image_grid_pinpoints": [
20
+ [
21
+ 384,
22
+ 384
23
+ ],
24
+ [
25
+ 384,
26
+ 768
27
+ ],
28
+ [
29
+ 384,
30
+ 1152
31
+ ],
32
+ [
33
+ 384,
34
+ 1536
35
+ ],
36
+ [
37
+ 384,
38
+ 1920
39
+ ],
40
+ [
41
+ 384,
42
+ 2304
43
+ ],
44
+ [
45
+ 768,
46
+ 384
47
+ ],
48
+ [
49
+ 768,
50
+ 768
51
+ ],
52
+ [
53
+ 768,
54
+ 1152
55
+ ],
56
+ [
57
+ 768,
58
+ 1536
59
+ ],
60
+ [
61
+ 768,
62
+ 1920
63
+ ],
64
+ [
65
+ 768,
66
+ 2304
67
+ ],
68
+ [
69
+ 1152,
70
+ 384
71
+ ],
72
+ [
73
+ 1152,
74
+ 768
75
+ ],
76
+ [
77
+ 1152,
78
+ 1152
79
+ ],
80
+ [
81
+ 1152,
82
+ 1536
83
+ ],
84
+ [
85
+ 1152,
86
+ 1920
87
+ ],
88
+ [
89
+ 1152,
90
+ 2304
91
+ ],
92
+ [
93
+ 1536,
94
+ 384
95
+ ],
96
+ [
97
+ 1536,
98
+ 768
99
+ ],
100
+ [
101
+ 1536,
102
+ 1152
103
+ ],
104
+ [
105
+ 1536,
106
+ 1536
107
+ ],
108
+ [
109
+ 1536,
110
+ 1920
111
+ ],
112
+ [
113
+ 1536,
114
+ 2304
115
+ ],
116
+ [
117
+ 1920,
118
+ 384
119
+ ],
120
+ [
121
+ 1920,
122
+ 768
123
+ ],
124
+ [
125
+ 1920,
126
+ 1152
127
+ ],
128
+ [
129
+ 1920,
130
+ 1536
131
+ ],
132
+ [
133
+ 1920,
134
+ 1920
135
+ ],
136
+ [
137
+ 1920,
138
+ 2304
139
+ ],
140
+ [
141
+ 2304,
142
+ 384
143
+ ],
144
+ [
145
+ 2304,
146
+ 768
147
+ ],
148
+ [
149
+ 2304,
150
+ 1152
151
+ ],
152
+ [
153
+ 2304,
154
+ 1536
155
+ ],
156
+ [
157
+ 2304,
158
+ 1920
159
+ ],
160
+ [
161
+ 2304,
162
+ 2304
163
+ ]
164
+ ],
165
+ "image_split_resolution": null,
166
+ "image_token_index": 151646,
167
+ "initializer_range": 0.02,
168
+ "intermediate_size": 18944,
169
+ "lambda_distill": 0.5,
170
+ "max_position_embeddings": 32768,
171
+ "max_window_layers": 28,
172
+ "mlp_out_dim": 256,
173
+ "mm_hidden_size": 1152,
174
+ "mm_newline_position": "grid",
175
+ "mm_patch_merge_type": "spatial_unpad",
176
+ "mm_projector_lr": null,
177
+ "mm_projector_type": "mlp2x_gelu",
178
+ "mm_resampler_type": null,
179
+ "mm_spatial_pool_mode": "bilinear",
180
+ "mm_spatial_pool_stride": 2,
181
+ "mm_spatial_tower": "vggt",
182
+ "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model,matching_head",
183
+ "mm_use_im_patch_token": false,
184
+ "mm_use_im_start_end": false,
185
+ "mm_vision_select_feature": "patch",
186
+ "mm_vision_select_layer": -2,
187
+ "mm_vision_tower": "google/siglip-so400m-patch14-384",
188
+ "mm_vision_tower_lr": 2e-06,
189
+ "model_type": "llava",
190
+ "num_attention_heads": 28,
191
+ "num_hidden_layers": 28,
192
+ "num_key_value_heads": 4,
193
+ "pos_skipping_range": 4096,
194
+ "projector_hidden_act": "gelu",
195
+ "rms_norm_eps": 1e-06,
196
+ "rope_scaling": null,
197
+ "rope_theta": 1000000.0,
198
+ "sliding_window": 131072,
199
+ "text_config": {
200
+ "model_type": "llama"
201
+ },
202
+ "tie_word_embeddings": false,
203
+ "tokenizer_model_max_length": 32768,
204
+ "tokenizer_padding_side": "right",
205
+ "torch_dtype": "bfloat16",
206
+ "transformers_version": "4.40.0.dev0",
207
+ "use_cache": true,
208
+ "use_mm_proj": true,
209
+ "use_pos_skipping": false,
210
+ "use_sliding_window": false,
211
+ "vision_config": {
212
+ "hidden_size": 1024,
213
+ "image_size": 336,
214
+ "intermediate_size": 4096,
215
+ "model_type": "clip_vision_model",
216
+ "num_attention_heads": 16,
217
+ "num_hidden_layers": 24,
218
+ "patch_size": 14,
219
+ "projection_dim": 768,
220
+ "vocab_size": 32000
221
+ },
222
+ "vision_feature_layer": -2,
223
+ "vision_feature_select_strategy": "default",
224
+ "vision_tower_pretrained": null
225
+ }
MVRD/d28_lambda0.5_fullft_aug2/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": "4.40.0.dev0"
14
+ }
MVRD/d28_lambda0.5_fullft_aug2/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
MVRD/d28_lambda0.5_fullft_aug2/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3814cefd513a88e942f363755f616dd4c0b72e78aa393bfbc53e900b9118586b
3
+ size 4877668032
MVRD/d28_lambda0.5_fullft_aug2/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1039be6be6c20f85b2dadecc62ab20a67e034c7b035ea6e579a2d948ea45fb08
3
+ size 4932751008
MVRD/d28_lambda0.5_fullft_aug2/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaeaf4da42b42daa0e65080afa758921af77638ebe24c686b608d7fe96b0732a
3
+ size 4994571904
MVRD/d28_lambda0.5_fullft_aug2/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fdbc0e2cd19e8c628fbf8a699a26e123c490dcc52c498b779ed99c5b1def250
3
+ size 3796741960
MVRD/d28_lambda0.5_fullft_aug2/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
MVRD/d28_lambda0.5_fullft_aug2/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
+ }
MVRD/d28_lambda0.5_fullft_aug2/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
MVRD/d28_lambda0.5_fullft_aug2/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": 32768,
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
+ }
MVRD/d28_lambda0.5_fullft_aug2/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
MVRD/d28_lambda0.5_fullft_aug2/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b2bf09ee7b3e1333f12ee998948a93c48dff4793c0989a52295596e1c9ecf84
3
+ size 8145
MVRD/d28_lambda0.5_fullft_aug2/vocab.json ADDED
The diff for this file is too large to render. See raw diff