Ghaser commited on
Commit
3bee97b
·
verified ·
1 Parent(s): a981973

Add files using upload-large-folder tool

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,257 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GrinQwen2VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "audio_end_token_id": 151666,
7
+ "audio_start_token_id": 151665,
8
+ "audio_token_id": 151667,
9
+ "avg_hidden_states_last": false,
10
+ "bos_token_id": 151643,
11
+ "capacity_factor": 3.0,
12
+ "drop_policy": "probs",
13
+ "drop_token_num_print": true,
14
+ "dynamic_intermediate_size": 18944,
15
+ "enable_expert_tensor_parallelism": false,
16
+ "eos_token_id": 151645,
17
+ "ep_size": 1,
18
+ "fixed_ep_size": 1,
19
+ "fp32_gate": true,
20
+ "hidden_act": "silu",
21
+ "hidden_size": 3584,
22
+ "ignore_differentiable_router": false,
23
+ "image_grid_pinpoints": [
24
+ [
25
+ 384,
26
+ 384
27
+ ],
28
+ [
29
+ 384,
30
+ 768
31
+ ],
32
+ [
33
+ 384,
34
+ 1152
35
+ ],
36
+ [
37
+ 384,
38
+ 1536
39
+ ],
40
+ [
41
+ 768,
42
+ 384
43
+ ],
44
+ [
45
+ 768,
46
+ 768
47
+ ],
48
+ [
49
+ 768,
50
+ 1152
51
+ ],
52
+ [
53
+ 768,
54
+ 1536
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
+ 1536,
74
+ 384
75
+ ],
76
+ [
77
+ 1536,
78
+ 768
79
+ ],
80
+ [
81
+ 1536,
82
+ 1152
83
+ ],
84
+ [
85
+ 1536,
86
+ 1536
87
+ ]
88
+ ],
89
+ "image_token_id": 151655,
90
+ "initializer_range": 0.02,
91
+ "input_jitter_noise": 0.01,
92
+ "intermediate_size": 18944,
93
+ "l_aux_weight": 0.025,
94
+ "l_aux_weight_decay_steps": 100000,
95
+ "layer_types": [
96
+ "sliding_attention",
97
+ "sliding_attention",
98
+ "sliding_attention",
99
+ "sliding_attention",
100
+ "sliding_attention",
101
+ "sliding_attention",
102
+ "sliding_attention",
103
+ "sliding_attention",
104
+ "sliding_attention",
105
+ "sliding_attention",
106
+ "sliding_attention",
107
+ "sliding_attention",
108
+ "sliding_attention",
109
+ "sliding_attention",
110
+ "sliding_attention",
111
+ "sliding_attention",
112
+ "sliding_attention",
113
+ "sliding_attention",
114
+ "sliding_attention",
115
+ "sliding_attention",
116
+ "sliding_attention",
117
+ "sliding_attention",
118
+ "sliding_attention",
119
+ "sliding_attention",
120
+ "sliding_attention",
121
+ "sliding_attention",
122
+ "sliding_attention",
123
+ "sliding_attention"
124
+ ],
125
+ "max_position_embeddings": 128000,
126
+ "max_window_layers": 28,
127
+ "min_capacity": 6,
128
+ "min_l_aux_weight": 0.025,
129
+ "mlp_dynamic_expert_num": 4,
130
+ "mlp_dynamic_null_expert_num": 1,
131
+ "mlp_dynamic_top_k": 2,
132
+ "mlp_dynamic_top_p": 0.7,
133
+ "mlp_fixed_expert_num": 2,
134
+ "mm_hidden_size": 1152,
135
+ "model_type": "grin_qwen2_vl",
136
+ "num_attention_heads": 28,
137
+ "num_hidden_layers": 28,
138
+ "num_key_value_heads": 4,
139
+ "rms_norm_eps": 1e-06,
140
+ "rope_scaling": {
141
+ "mrope_section": [
142
+ 16,
143
+ 24,
144
+ 24
145
+ ],
146
+ "rope_type": "default",
147
+ "type": "default"
148
+ },
149
+ "rope_theta": 1000000.0,
150
+ "router_jitter_noise": 0.01,
151
+ "shared_intermediate_size": 2368,
152
+ "sliding_window": 32768,
153
+ "speech_end_token_id": 151669,
154
+ "speech_prompt_token_id": 151670,
155
+ "speech_split_token_id": 151671,
156
+ "speech_start_token_id": 151668,
157
+ "tie_word_embeddings": false,
158
+ "token_drop": false,
159
+ "torch_dtype": "bfloat16",
160
+ "transformers_version": "4.45.1",
161
+ "tune_image_generator": true,
162
+ "tune_speech_generator": false,
163
+ "tune_speech_generator_only": false,
164
+ "use_cache": true,
165
+ "use_sliding_window": false,
166
+ "video_token_id": 151656,
167
+ "vision_config": {
168
+ "hidden_size": 1152,
169
+ "image_size": 384,
170
+ "intermediate_size": 4304,
171
+ "model_type": "siglip_vision_model",
172
+ "num_attention_heads": 16,
173
+ "num_hidden_layers": 27,
174
+ "patch_size": 14
175
+ },
176
+ "audio_config": {
177
+ "activation_dropout": 0.0,
178
+ "activation_function": "gelu",
179
+ "apply_spec_augment": false,
180
+ "architectures": [
181
+ "WhisperForConditionalGeneration"
182
+ ],
183
+ "attention_dropout": 0.0,
184
+ "begin_suppress_tokens": [
185
+ 220,
186
+ 50257
187
+ ],
188
+ "bos_token_id": 50257,
189
+ "classifier_proj_size": 256,
190
+ "d_model": 1280,
191
+ "decoder_attention_heads": 20,
192
+ "decoder_ffn_dim": 5120,
193
+ "decoder_layerdrop": 0.0,
194
+ "decoder_layers": 32,
195
+ "decoder_start_token_id": 50258,
196
+ "dropout": 0.0,
197
+ "encoder_attention_heads": 20,
198
+ "encoder_ffn_dim": 5120,
199
+ "encoder_layerdrop": 0.0,
200
+ "encoder_layers": 32,
201
+ "eos_token_id": 50257,
202
+ "init_std": 0.02,
203
+ "is_encoder_decoder": true,
204
+ "mask_feature_length": 10,
205
+ "mask_feature_min_masks": 0,
206
+ "mask_feature_prob": 0.0,
207
+ "mask_time_length": 10,
208
+ "mask_time_min_masks": 2,
209
+ "mask_time_prob": 0.05,
210
+ "max_length": 448,
211
+ "max_source_positions": 1500,
212
+ "max_target_positions": 448,
213
+ "median_filter_width": 7,
214
+ "model_type": "whisper",
215
+ "num_hidden_layers": 32,
216
+ "num_mel_bins": 128,
217
+ "pad_token_id": 50256,
218
+ "scale_embedding": false,
219
+ "torch_dtype": "float16",
220
+ "transformers_version": "4.36.0.dev0",
221
+ "use_cache": true,
222
+ "use_weighted_layer_sum": false,
223
+ "vocab_size": 51866
224
+ },
225
+ "vision_end_token_id": 151653,
226
+ "vision_hidden_size": 1152,
227
+ "vision_spatial_pool_stride": 12,
228
+ "vision_start_token_id": 151652,
229
+ "vision_token_id": 151654,
230
+ "vision_tower_pretrained": null,
231
+ "vision_vision_select_layer": -2,
232
+ "visual_aligner_type": "linear",
233
+ "vocab_size": 152064,
234
+ "whisper_hidden_size": 1280,
235
+ "whisper_projector_type": "linear",
236
+ "whisper_query_tokens_size": 200,
237
+ "idim": 2048,
238
+ "odim": 4096,
239
+ "encoder_pre_norm_type": "ln",
240
+ "encoder_drop_rate": 0.1,
241
+ "encoder_criterion": "ce",
242
+ "encoder_upsample_rate": 9,
243
+ "transformer_attention_dim": 896,
244
+ "transformer_linear_units": 4864,
245
+ "transformer_num_blocks": 24,
246
+ "transformer_attention_heads": 14,
247
+ "transformer_kv_heads": 2,
248
+ "transformer_dropout_rate": 0.1,
249
+ "encoder_output_dim": 896,
250
+ "do_cross_attention": true,
251
+ "cross_attention_layer_num": 6,
252
+ "llm_vocab_size": 151936,
253
+ "whisper_audio_time": 20,
254
+ "frames_upbound": 64,
255
+ "video_fps": 1.0,
256
+ "video_pixel_upbound": 384
257
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.45.1"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e57e7c182bb246cf305cf51e79c237d3a431a8a2b15f7836943d5c58b6dc98a
3
+ size 5303177376
model-00002-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35719fb8e982cb8488e0b550df50c1fd2d994d08aafe247e419803cab543d262
3
+ size 5295839904
model-00003-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb6d970b27dd7857188740457facbad5546ef3aa74e058228f2d48289aac134f
3
+ size 5295839904
model-00004-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a29b9454ef2a51274a2bb42f5f02c9288b367386a83c4174d3cd63b07f807fc
3
+ size 5295839920
model-00005-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36a892af2b986106cfe14cd6c713fda799b7f7f8dbed9849fc31df3b57270355
3
+ size 5295839944
model-00006-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5596901e33dfb78437db85f368d6e2a051109ebb0003985ab0d6be306c8c0128
3
+ size 5295839944
model-00007-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b3e01accbd7ad1f7cde9067f7386b42b2c03632a84dd7bd462d5ae9637d0d74
3
+ size 5295839944
model-00008-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c13c25ca0af8e6e72593dfed1da70856a5d668c348e0b185b2d46bcb19815a8
3
+ size 5295839944
model-00009-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f345a6457fe02ad4354d9e8f5fea5027cfa5fb5a17078e3a15a9731899e713a4
3
+ size 5295839944
model-00010-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da1840242b2452596effdaa3d651b399c3369066e471e1e1c0e95149ac426492
3
+ size 5354516912
model-00011-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb4486c08cbf86c0472557f42e1bbeeab6b4f31a59a645b1bf49c19e2e3cf310
3
+ size 5367350952
model-00012-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:302dc8e8dbae95f3418c007d7f06a1f88ea6dc8a876c017ff4a7ad594bd84fe7
3
+ size 3291789036
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 384,
4
+ "width": 384
5
+ },
6
+ "data_format": "channels_first",
7
+ "image_mean": [
8
+ 0.5,
9
+ 0.5,
10
+ 0.5
11
+ ],
12
+ "image_processor_type": "SigLipImageProcessor",
13
+ "image_std": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "processor_class": "Qwen2VLProcessor",
19
+ "resample": 3,
20
+ "rescale_factor": 0.00392156862745098,
21
+ "size": [
22
+ 384,
23
+ 384
24
+ ]
25
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>",
16
+ "<|audio_start|>",
17
+ "<|audio_end|>",
18
+ "<|audio_pad|>",
19
+ "<|speech_start|>",
20
+ "<|speech_end|>",
21
+ "<|speech_prompt|>",
22
+ "<|speech_split|>"
23
+ ],
24
+ "eos_token": {
25
+ "content": "<|im_end|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "pad_token": {
32
+ "content": "<|endoftext|>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ }
38
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:527d446ac3ab7ef41e79df7448810f627715a6a74d62ced4c983390a63757923
3
+ size 11429669
tokenizer_config.json ADDED
@@ -0,0 +1,551 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "151657": {
117
+ "content": "<tool_call>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "151658": {
125
+ "content": "</tool_call>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "151659": {
133
+ "content": "<|fim_prefix|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "151660": {
141
+ "content": "<|fim_middle|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "151661": {
149
+ "content": "<|fim_suffix|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "151662": {
157
+ "content": "<|fim_pad|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "151663": {
165
+ "content": "<|repo_name|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "151664": {
173
+ "content": "<|file_sep|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "151665": {
181
+ "content": "<|audio_start|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "151666": {
189
+ "content": "<|audio_end|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "151667": {
197
+ "content": "<|audio_pad|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "151668": {
205
+ "content": "<|speech_start|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "151669": {
213
+ "content": "<|speech_end|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "151670": {
221
+ "content": "<|speech_prompt|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "151671": {
229
+ "content": "<|speech_split|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "151672": {
237
+ "content": "[IMG0]",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "151673": {
245
+ "content": "[IMG1]",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "151674": {
253
+ "content": "[IMG2]",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "151675": {
261
+ "content": "[IMG3]",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "151676": {
269
+ "content": "[IMG4]",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "151677": {
277
+ "content": "[IMG5]",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "151678": {
285
+ "content": "[IMG6]",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "151679": {
293
+ "content": "[IMG7]",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "151680": {
301
+ "content": "[IMG8]",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "151681": {
309
+ "content": "[IMG9]",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ },
316
+ "151682": {
317
+ "content": "[IMG10]",
318
+ "lstrip": false,
319
+ "normalized": true,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": false
323
+ },
324
+ "151683": {
325
+ "content": "[IMG11]",
326
+ "lstrip": false,
327
+ "normalized": true,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": false
331
+ },
332
+ "151684": {
333
+ "content": "[IMG12]",
334
+ "lstrip": false,
335
+ "normalized": true,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": false
339
+ },
340
+ "151685": {
341
+ "content": "[IMG13]",
342
+ "lstrip": false,
343
+ "normalized": true,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": false
347
+ },
348
+ "151686": {
349
+ "content": "[IMG14]",
350
+ "lstrip": false,
351
+ "normalized": true,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": false
355
+ },
356
+ "151687": {
357
+ "content": "[IMG15]",
358
+ "lstrip": false,
359
+ "normalized": true,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": false
363
+ },
364
+ "151688": {
365
+ "content": "[IMG16]",
366
+ "lstrip": false,
367
+ "normalized": true,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": false
371
+ },
372
+ "151689": {
373
+ "content": "[IMG17]",
374
+ "lstrip": false,
375
+ "normalized": true,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": false
379
+ },
380
+ "151690": {
381
+ "content": "[IMG18]",
382
+ "lstrip": false,
383
+ "normalized": true,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": false
387
+ },
388
+ "151691": {
389
+ "content": "[IMG19]",
390
+ "lstrip": false,
391
+ "normalized": true,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": false
395
+ },
396
+ "151692": {
397
+ "content": "[IMG20]",
398
+ "lstrip": false,
399
+ "normalized": true,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": false
403
+ },
404
+ "151693": {
405
+ "content": "[IMG21]",
406
+ "lstrip": false,
407
+ "normalized": true,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": false
411
+ },
412
+ "151694": {
413
+ "content": "[IMG22]",
414
+ "lstrip": false,
415
+ "normalized": true,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": false
419
+ },
420
+ "151695": {
421
+ "content": "[IMG23]",
422
+ "lstrip": false,
423
+ "normalized": true,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": false
427
+ },
428
+ "151696": {
429
+ "content": "[IMG24]",
430
+ "lstrip": false,
431
+ "normalized": true,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": false
435
+ },
436
+ "151697": {
437
+ "content": "[IMG25]",
438
+ "lstrip": false,
439
+ "normalized": true,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": false
443
+ },
444
+ "151698": {
445
+ "content": "[IMG26]",
446
+ "lstrip": false,
447
+ "normalized": true,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": false
451
+ },
452
+ "151699": {
453
+ "content": "[IMG27]",
454
+ "lstrip": false,
455
+ "normalized": true,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": false
459
+ },
460
+ "151700": {
461
+ "content": "[IMG28]",
462
+ "lstrip": false,
463
+ "normalized": true,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": false
467
+ },
468
+ "151701": {
469
+ "content": "[IMG29]",
470
+ "lstrip": false,
471
+ "normalized": true,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": false
475
+ },
476
+ "151702": {
477
+ "content": "[IMG30]",
478
+ "lstrip": false,
479
+ "normalized": true,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": false
483
+ },
484
+ "151703": {
485
+ "content": "[IMG31]",
486
+ "lstrip": false,
487
+ "normalized": true,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": false
491
+ },
492
+ "151704": {
493
+ "content": "[TASK0]",
494
+ "lstrip": false,
495
+ "normalized": true,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": false
499
+ },
500
+ "151705": {
501
+ "content": "[TASK1]",
502
+ "lstrip": false,
503
+ "normalized": true,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": false
507
+ },
508
+ "151706": {
509
+ "content": "[TASK2]",
510
+ "lstrip": false,
511
+ "normalized": true,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": false
515
+ }
516
+ },
517
+ "additional_special_tokens": [
518
+ "<|im_start|>",
519
+ "<|im_end|>",
520
+ "<|object_ref_start|>",
521
+ "<|object_ref_end|>",
522
+ "<|box_start|>",
523
+ "<|box_end|>",
524
+ "<|quad_start|>",
525
+ "<|quad_end|>",
526
+ "<|vision_start|>",
527
+ "<|vision_end|>",
528
+ "<|vision_pad|>",
529
+ "<|image_pad|>",
530
+ "<|video_pad|>",
531
+ "<|audio_start|>",
532
+ "<|audio_end|>",
533
+ "<|audio_pad|>",
534
+ "<|speech_start|>",
535
+ "<|speech_end|>",
536
+ "<|speech_prompt|>",
537
+ "<|speech_split|>"
538
+ ],
539
+ "bos_token": null,
540
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
541
+ "clean_up_tokenization_spaces": false,
542
+ "eos_token": "<|im_end|>",
543
+ "errors": "replace",
544
+ "model_max_length": 15000,
545
+ "pad_token": "<|endoftext|>",
546
+ "padding_side": "left",
547
+ "processor_class": "Qwen2VLProcessor",
548
+ "split_special_tokens": false,
549
+ "tokenizer_class": "Qwen2Tokenizer",
550
+ "unk_token": null
551
+ }
visual_gen/dit/README.md ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ ---
6
+
7
+ # PixWizard Model Card
8
+
9
+ ## Paper or resources for more information:
10
+ Paper: [https://arxiv.org/abs/2409.15278](https://arxiv.org/abs/2409.15278) \
11
+ Code: [https://github.com/AFeng-x/PixWizard](https://github.com/AFeng-x/PixWizard)
12
+
13
+
14
+ ## Citations
15
+ ```
16
+ @article{lin2024pixwizard,
17
+ title={PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions},
18
+ author={Lin, Weifeng and Wei, Xinyu and Zhang, Renrui and Zhuo, Le and Zhao, Shitian and Huang, Siyuan and Xie, Junlin and Qiao, Yu and Gao, Peng and Li, Hongsheng},
19
+ journal={arXiv preprint arXiv:2409.15278},
20
+ year={2024}
21
+ }
22
+ ```
visual_gen/dit/consolidated.00-of-01.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:927ec489b43235cdbeda6cb8fac5b1db26e3b0c76eb0011d04f3a9af0170994b
3
+ size 8046201485
visual_gen/dit/consolidated_ema.00-of-01.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85716aac6fe46893a55a80e1f6b152b94094c35f79fad240bab81f0829f9b163
3
+ size 8046205577
visual_gen/dit/gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
visual_gen/dit/model_args.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e07e0ff9a089bc12e827ff20c4653fd17596c301ae144c3d0110d34274f4da2
3
+ size 2284
visual_gen/sdxl-vae/README.md ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - stable-diffusion
5
+ - stable-diffusion-diffusers
6
+ inference: false
7
+ ---
8
+ # SDXL - VAE
9
+
10
+ #### How to use with 🧨 diffusers
11
+ You can integrate this fine-tuned VAE decoder to your existing `diffusers` workflows, by including a `vae` argument to the `StableDiffusionPipeline`
12
+ ```py
13
+ from diffusers.models import AutoencoderKL
14
+ from diffusers import StableDiffusionPipeline
15
+
16
+ model = "stabilityai/your-stable-diffusion-model"
17
+ vae = AutoencoderKL.from_pretrained("stabilityai/sdxl-vae")
18
+ pipe = StableDiffusionPipeline.from_pretrained(model, vae=vae)
19
+ ```
20
+
21
+ ## Model
22
+ [SDXL](https://huggingface.co/stabilityai/stable-diffusion-xl-base-0.9) is a [latent diffusion model](https://arxiv.org/abs/2112.10752), where the diffusion operates in a pretrained,
23
+ learned (and fixed) latent space of an autoencoder.
24
+ While the bulk of the semantic composition is done by the latent diffusion model,
25
+ we can improve _local_, high-frequency details in generated images by improving the quality of the autoencoder.
26
+ To this end, we train the same autoencoder architecture used for the original [Stable Diffusion](https://github.com/CompVis/stable-diffusion) at a larger batch-size (256 vs 9)
27
+ and additionally track the weights with an exponential moving average (EMA).
28
+ The resulting autoencoder outperforms the original model in all evaluated reconstruction metrics, see the table below.
29
+
30
+
31
+ ## Evaluation
32
+ _SDXL-VAE vs original kl-f8 VAE vs f8-ft-MSE_
33
+ ### COCO 2017 (256x256, val, 5000 images)
34
+ | Model | rFID | PSNR | SSIM | PSIM | Link | Comments
35
+ |----------|------|--------------|---------------|---------------|------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------|
36
+ | | | | | | | |
37
+ | SDXL-VAE | 4.42 | 24.7 +/- 3.9 | 0.73 +/- 0.13 | 0.88 +/- 0.27 | https://huggingface.co/stabilityai/sdxl-vae/blob/main/sdxl_vae.safetensors | as used in SDXL |
38
+ | original | 4.99 | 23.4 +/- 3.8 | 0.69 +/- 0.14 | 1.01 +/- 0.28 | https://ommer-lab.com/files/latent-diffusion/kl-f8.zip | as used in SD |
39
+ | ft-MSE | 4.70 | 24.5 +/- 3.7 | 0.71 +/- 0.13 | 0.92 +/- 0.27 | https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.ckpt | resumed with EMA from ft-EMA, emphasis on MSE (rec. loss = MSE + 0.1 * LPIPS), smoother outputs |
visual_gen/sdxl-vae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.18.0.dev0",
4
+ "_name_or_path": ".",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "in_channels": 3,
19
+ "latent_channels": 4,
20
+ "layers_per_block": 2,
21
+ "norm_num_groups": 32,
22
+ "out_channels": 3,
23
+ "sample_size": 1024,
24
+ "scaling_factor": 0.13025,
25
+ "up_block_types": [
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D"
30
+ ]
31
+ }
visual_gen/sdxl-vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1598f3d24932bcfe6634e8b618ea1e30ab1d57f5aad13a6d2de446d2199f2341
3
+ size 334643268
visual_gen/sdxl-vae/gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
vocab.json ADDED
The diff for this file is too large to render. See raw diff