Hugging Face's logo

Heisen0928
/
value_function

TensorBoard
Safetensors
Model card Files
xet
 Metrics Community
Heisen0928 commited on
Commit
0cc7bea
·
verified ·
1 Parent(s): c4071cf

Upload folder using huggingface_hub

Browse files
Files changed (42) hide show
  1. pi06_style/45000/added_tokens.json +225 -0
  2. pi06_style/45000/chat_template.jinja +7 -0
  3. pi06_style/45000/config.json +140 -0
  4. pi06_style/45000/generation_config.json +11 -0
  5. pi06_style/45000/global_step45003/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  6. pi06_style/45000/global_step45003/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  7. pi06_style/45000/global_step45003/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  8. pi06_style/45000/global_step45003/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  9. pi06_style/45000/global_step45003/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
  10. pi06_style/45000/global_step45003/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
  11. pi06_style/45000/global_step45003/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
  12. pi06_style/45000/global_step45003/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
  13. pi06_style/45000/global_step45003/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  14. pi06_style/45000/global_step45003/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  15. pi06_style/45000/global_step45003/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
  16. pi06_style/45000/global_step45003/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
  17. pi06_style/45000/global_step45003/zero_pp_rank_4_mp_rank_00_model_states.pt +3 -0
  18. pi06_style/45000/global_step45003/zero_pp_rank_5_mp_rank_00_model_states.pt +3 -0
  19. pi06_style/45000/global_step45003/zero_pp_rank_6_mp_rank_00_model_states.pt +3 -0
  20. pi06_style/45000/global_step45003/zero_pp_rank_7_mp_rank_00_model_states.pt +3 -0
  21. pi06_style/45000/latest +1 -0
  22. pi06_style/45000/merges.txt +0 -0
  23. pi06_style/45000/model-00001-of-00002.safetensors +3 -0
  24. pi06_style/45000/model-00002-of-00002.safetensors +3 -0
  25. pi06_style/45000/model.safetensors.index.json +832 -0
  26. pi06_style/45000/preprocessor_config.json +39 -0
  27. pi06_style/45000/rng_state_0.pth +3 -0
  28. pi06_style/45000/rng_state_1.pth +3 -0
  29. pi06_style/45000/rng_state_2.pth +3 -0
  30. pi06_style/45000/rng_state_3.pth +3 -0
  31. pi06_style/45000/rng_state_4.pth +3 -0
  32. pi06_style/45000/rng_state_5.pth +3 -0
  33. pi06_style/45000/rng_state_6.pth +3 -0
  34. pi06_style/45000/rng_state_7.pth +3 -0
  35. pi06_style/45000/scheduler.pt +3 -0
  36. pi06_style/45000/special_tokens_map.json +31 -0
  37. pi06_style/45000/tokenizer_config.json +1817 -0
  38. pi06_style/45000/trainer_state.json +0 -0
  39. pi06_style/45000/training_args.bin +3 -0
  40. pi06_style/45000/video_preprocessor_config.json +43 -0
  41. pi06_style/45000/vocab.json +0 -0
  42. pi06_style/45000/zero_to_fp32.py +760 -0
pi06_style/45000/added_tokens.json ADDED
@@ -0,0 +1,225 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<extra_id_0>": 151665,
4
+ "<extra_id_100>": 151765,
5
+ "<extra_id_101>": 151766,
6
+ "<extra_id_102>": 151767,
7
+ "<extra_id_103>": 151768,
8
+ "<extra_id_104>": 151769,
9
+ "<extra_id_105>": 151770,
10
+ "<extra_id_106>": 151771,
11
+ "<extra_id_107>": 151772,
12
+ "<extra_id_108>": 151773,
13
+ "<extra_id_109>": 151774,
14
+ "<extra_id_10>": 151675,
15
+ "<extra_id_110>": 151775,
16
+ "<extra_id_111>": 151776,
17
+ "<extra_id_112>": 151777,
18
+ "<extra_id_113>": 151778,
19
+ "<extra_id_114>": 151779,
20
+ "<extra_id_115>": 151780,
21
+ "<extra_id_116>": 151781,
22
+ "<extra_id_117>": 151782,
23
+ "<extra_id_118>": 151783,
24
+ "<extra_id_119>": 151784,
25
+ "<extra_id_11>": 151676,
26
+ "<extra_id_120>": 151785,
27
+ "<extra_id_121>": 151786,
28
+ "<extra_id_122>": 151787,
29
+ "<extra_id_123>": 151788,
30
+ "<extra_id_124>": 151789,
31
+ "<extra_id_125>": 151790,
32
+ "<extra_id_126>": 151791,
33
+ "<extra_id_127>": 151792,
34
+ "<extra_id_128>": 151793,
35
+ "<extra_id_129>": 151794,
36
+ "<extra_id_12>": 151677,
37
+ "<extra_id_130>": 151795,
38
+ "<extra_id_131>": 151796,
39
+ "<extra_id_132>": 151797,
40
+ "<extra_id_133>": 151798,
41
+ "<extra_id_134>": 151799,
42
+ "<extra_id_135>": 151800,
43
+ "<extra_id_136>": 151801,
44
+ "<extra_id_137>": 151802,
45
+ "<extra_id_138>": 151803,
46
+ "<extra_id_139>": 151804,
47
+ "<extra_id_13>": 151678,
48
+ "<extra_id_140>": 151805,
49
+ "<extra_id_141>": 151806,
50
+ "<extra_id_142>": 151807,
51
+ "<extra_id_143>": 151808,
52
+ "<extra_id_144>": 151809,
53
+ "<extra_id_145>": 151810,
54
+ "<extra_id_146>": 151811,
55
+ "<extra_id_147>": 151812,
56
+ "<extra_id_148>": 151813,
57
+ "<extra_id_149>": 151814,
58
+ "<extra_id_14>": 151679,
59
+ "<extra_id_150>": 151815,
60
+ "<extra_id_151>": 151816,
61
+ "<extra_id_152>": 151817,
62
+ "<extra_id_153>": 151818,
63
+ "<extra_id_154>": 151819,
64
+ "<extra_id_155>": 151820,
65
+ "<extra_id_156>": 151821,
66
+ "<extra_id_157>": 151822,
67
+ "<extra_id_158>": 151823,
68
+ "<extra_id_159>": 151824,
69
+ "<extra_id_15>": 151680,
70
+ "<extra_id_160>": 151825,
71
+ "<extra_id_161>": 151826,
72
+ "<extra_id_162>": 151827,
73
+ "<extra_id_163>": 151828,
74
+ "<extra_id_164>": 151829,
75
+ "<extra_id_165>": 151830,
76
+ "<extra_id_166>": 151831,
77
+ "<extra_id_167>": 151832,
78
+ "<extra_id_168>": 151833,
79
+ "<extra_id_169>": 151834,
80
+ "<extra_id_16>": 151681,
81
+ "<extra_id_170>": 151835,
82
+ "<extra_id_171>": 151836,
83
+ "<extra_id_172>": 151837,
84
+ "<extra_id_173>": 151838,
85
+ "<extra_id_174>": 151839,
86
+ "<extra_id_175>": 151840,
87
+ "<extra_id_176>": 151841,
88
+ "<extra_id_177>": 151842,
89
+ "<extra_id_178>": 151843,
90
+ "<extra_id_179>": 151844,
91
+ "<extra_id_17>": 151682,
92
+ "<extra_id_180>": 151845,
93
+ "<extra_id_181>": 151846,
94
+ "<extra_id_182>": 151847,
95
+ "<extra_id_183>": 151848,
96
+ "<extra_id_184>": 151849,
97
+ "<extra_id_185>": 151850,
98
+ "<extra_id_186>": 151851,
99
+ "<extra_id_187>": 151852,
100
+ "<extra_id_188>": 151853,
101
+ "<extra_id_189>": 151854,
102
+ "<extra_id_18>": 151683,
103
+ "<extra_id_190>": 151855,
104
+ "<extra_id_191>": 151856,
105
+ "<extra_id_192>": 151857,
106
+ "<extra_id_193>": 151858,
107
+ "<extra_id_194>": 151859,
108
+ "<extra_id_195>": 151860,
109
+ "<extra_id_196>": 151861,
110
+ "<extra_id_197>": 151862,
111
+ "<extra_id_198>": 151863,
112
+ "<extra_id_199>": 151864,
113
+ "<extra_id_19>": 151684,
114
+ "<extra_id_1>": 151666,
115
+ "<extra_id_200>": 151865,
116
+ "<extra_id_20>": 151685,
117
+ "<extra_id_21>": 151686,
118
+ "<extra_id_22>": 151687,
119
+ "<extra_id_23>": 151688,
120
+ "<extra_id_24>": 151689,
121
+ "<extra_id_25>": 151690,
122
+ "<extra_id_26>": 151691,
123
+ "<extra_id_27>": 151692,
124
+ "<extra_id_28>": 151693,
125
+ "<extra_id_29>": 151694,
126
+ "<extra_id_2>": 151667,
127
+ "<extra_id_30>": 151695,
128
+ "<extra_id_31>": 151696,
129
+ "<extra_id_32>": 151697,
130
+ "<extra_id_33>": 151698,
131
+ "<extra_id_34>": 151699,
132
+ "<extra_id_35>": 151700,
133
+ "<extra_id_36>": 151701,
134
+ "<extra_id_37>": 151702,
135
+ "<extra_id_38>": 151703,
136
+ "<extra_id_39>": 151704,
137
+ "<extra_id_3>": 151668,
138
+ "<extra_id_40>": 151705,
139
+ "<extra_id_41>": 151706,
140
+ "<extra_id_42>": 151707,
141
+ "<extra_id_43>": 151708,
142
+ "<extra_id_44>": 151709,
143
+ "<extra_id_45>": 151710,
144
+ "<extra_id_46>": 151711,
145
+ "<extra_id_47>": 151712,
146
+ "<extra_id_48>": 151713,
147
+ "<extra_id_49>": 151714,
148
+ "<extra_id_4>": 151669,
149
+ "<extra_id_50>": 151715,
150
+ "<extra_id_51>": 151716,
151
+ "<extra_id_52>": 151717,
152
+ "<extra_id_53>": 151718,
153
+ "<extra_id_54>": 151719,
154
+ "<extra_id_55>": 151720,
155
+ "<extra_id_56>": 151721,
156
+ "<extra_id_57>": 151722,
157
+ "<extra_id_58>": 151723,
158
+ "<extra_id_59>": 151724,
159
+ "<extra_id_5>": 151670,
160
+ "<extra_id_60>": 151725,
161
+ "<extra_id_61>": 151726,
162
+ "<extra_id_62>": 151727,
163
+ "<extra_id_63>": 151728,
164
+ "<extra_id_64>": 151729,
165
+ "<extra_id_65>": 151730,
166
+ "<extra_id_66>": 151731,
167
+ "<extra_id_67>": 151732,
168
+ "<extra_id_68>": 151733,
169
+ "<extra_id_69>": 151734,
170
+ "<extra_id_6>": 151671,
171
+ "<extra_id_70>": 151735,
172
+ "<extra_id_71>": 151736,
173
+ "<extra_id_72>": 151737,
174
+ "<extra_id_73>": 151738,
175
+ "<extra_id_74>": 151739,
176
+ "<extra_id_75>": 151740,
177
+ "<extra_id_76>": 151741,
178
+ "<extra_id_77>": 151742,
179
+ "<extra_id_78>": 151743,
180
+ "<extra_id_79>": 151744,
181
+ "<extra_id_7>": 151672,
182
+ "<extra_id_80>": 151745,
183
+ "<extra_id_81>": 151746,
184
+ "<extra_id_82>": 151747,
185
+ "<extra_id_83>": 151748,
186
+ "<extra_id_84>": 151749,
187
+ "<extra_id_85>": 151750,
188
+ "<extra_id_86>": 151751,
189
+ "<extra_id_87>": 151752,
190
+ "<extra_id_88>": 151753,
191
+ "<extra_id_89>": 151754,
192
+ "<extra_id_8>": 151673,
193
+ "<extra_id_90>": 151755,
194
+ "<extra_id_91>": 151756,
195
+ "<extra_id_92>": 151757,
196
+ "<extra_id_93>": 151758,
197
+ "<extra_id_94>": 151759,
198
+ "<extra_id_95>": 151760,
199
+ "<extra_id_96>": 151761,
200
+ "<extra_id_97>": 151762,
201
+ "<extra_id_98>": 151763,
202
+ "<extra_id_99>": 151764,
203
+ "<extra_id_9>": 151674,
204
+ "<tool_call>": 151657,
205
+ "<|box_end|>": 151649,
206
+ "<|box_start|>": 151648,
207
+ "<|endoftext|>": 151643,
208
+ "<|file_sep|>": 151664,
209
+ "<|fim_middle|>": 151660,
210
+ "<|fim_pad|>": 151662,
211
+ "<|fim_prefix|>": 151659,
212
+ "<|fim_suffix|>": 151661,
213
+ "<|im_end|>": 151645,
214
+ "<|im_start|>": 151644,
215
+ "<|image_pad|>": 151655,
216
+ "<|object_ref_end|>": 151647,
217
+ "<|object_ref_start|>": 151646,
218
+ "<|quad_end|>": 151651,
219
+ "<|quad_start|>": 151650,
220
+ "<|repo_name|>": 151663,
221
+ "<|video_pad|>": 151656,
222
+ "<|vision_end|>": 151653,
223
+ "<|vision_pad|>": 151654,
224
+ "<|vision_start|>": 151652
225
+ }
pi06_style/45000/chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% 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
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% 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|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
pi06_style/45000/config.json ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 2048,
11
+ "image_token_id": 151655,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 128000,
15
+ "max_window_layers": 70,
16
+ "model_type": "qwen2_5_vl",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 36,
19
+ "num_key_value_heads": 2,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": {
22
+ "mrope_section": [
23
+ 16,
24
+ 24,
25
+ 24
26
+ ],
27
+ "rope_type": "default",
28
+ "type": "default"
29
+ },
30
+ "rope_theta": 1000000.0,
31
+ "sliding_window": 32768,
32
+ "text_config": {
33
+ "_name_or_path": "/mnt/bn/ic-vlm/zhufangqi/code/value_function/qwen-vl-finetune/tools/checkpoints/Qwen2.5-VL-3B-Instruct-resize",
34
+ "architectures": [
35
+ "Qwen2_5_VLForConditionalGeneration"
36
+ ],
37
+ "attention_dropout": 0.0,
38
+ "dtype": "bfloat16",
39
+ "eos_token_id": 151645,
40
+ "hidden_act": "silu",
41
+ "hidden_size": 2048,
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 11008,
44
+ "layer_types": [
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention",
78
+ "full_attention",
79
+ "full_attention",
80
+ "full_attention"
81
+ ],
82
+ "max_position_embeddings": 128000,
83
+ "max_window_layers": 70,
84
+ "model_type": "qwen2_5_vl_text",
85
+ "num_attention_heads": 16,
86
+ "num_hidden_layers": 36,
87
+ "num_key_value_heads": 2,
88
+ "pad_token_id": 151643,
89
+ "rms_norm_eps": 1e-06,
90
+ "rope_scaling": {
91
+ "mrope_section": [
92
+ 16,
93
+ 24,
94
+ 24
95
+ ],
96
+ "rope_type": "default",
97
+ "type": "default"
98
+ },
99
+ "rope_theta": 1000000.0,
100
+ "sliding_window": null,
101
+ "tie_word_embeddings": true,
102
+ "use_cache": false,
103
+ "use_sliding_window": false,
104
+ "vision_token_id": 151654,
105
+ "vocab_size": 151866
106
+ },
107
+ "transformers_version": "4.57.0",
108
+ "use_cache": true,
109
+ "use_sliding_window": false,
110
+ "video_token_id": 151656,
111
+ "vision_config": {
112
+ "depth": 32,
113
+ "dtype": "bfloat16",
114
+ "fullatt_block_indexes": [
115
+ 7,
116
+ 15,
117
+ 23,
118
+ 31
119
+ ],
120
+ "hidden_act": "silu",
121
+ "hidden_size": 1280,
122
+ "in_channels": 3,
123
+ "in_chans": 3,
124
+ "initializer_range": 0.02,
125
+ "intermediate_size": 3420,
126
+ "model_type": "qwen2_5_vl",
127
+ "num_heads": 16,
128
+ "out_hidden_size": 2048,
129
+ "patch_size": 14,
130
+ "spatial_merge_size": 2,
131
+ "spatial_patch_size": 14,
132
+ "temporal_patch_size": 2,
133
+ "tokens_per_second": 2,
134
+ "window_size": 112
135
+ },
136
+ "vision_end_token_id": 151653,
137
+ "vision_start_token_id": 151652,
138
+ "vision_token_id": 151654,
139
+ "vocab_size": 151936
140
+ }
pi06_style/45000/generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151643
6
+ ],
7
+ "pad_token_id": 151643,
8
+ "repetition_penalty": 1.05,
9
+ "temperature": 1e-06,
10
+ "transformers_version": "4.57.0"
11
+ }
pi06_style/45000/global_step45003/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68f05a1e3b2e76be483844da259411c64506af444d304fc4e7c9300fa36d7560
3
+ size 4683761116
pi06_style/45000/global_step45003/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c8cdc7c784d02149b4d3bf8433794c6bbf64f2cab38cc371ae0705a10568438
3
+ size 4683761116
pi06_style/45000/global_step45003/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b386ac6a9e6b8030bf7d7ca67cd31b2835e3c914a85b50f4356316ec3b3a2915
3
+ size 4683761116
pi06_style/45000/global_step45003/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af5ffbdbc87055cdf0b362a99dd63e438cb6f49c6d020fe6d8f4f19b826f4693
3
+ size 4683761116
pi06_style/45000/global_step45003/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f7d80194e81a1b3b1245d56dbda0b762a2cbf3221553ab94833120df9b81c23
3
+ size 4683761116
pi06_style/45000/global_step45003/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaa0da333ff6a686931cdd8f374b39c631b090b59c1dcd398faab77090f416fd
3
+ size 4683761116
pi06_style/45000/global_step45003/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82b053d11e7a10a8c4ae6453e617b1594f73655a54ddf6b4f89d0fc4f698182d
3
+ size 4683761116
pi06_style/45000/global_step45003/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5bbbbafb070f3ac256bc33ca46a686ab5cfac735d59ca007f659ada64dd5bad
3
+ size 4683761116
pi06_style/45000/global_step45003/zero_pp_rank_0_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c5735785668ae8c336bbb7fe0fb9e3102214c1bb3b7342489b5db856c5be9dc
3
+ size 158533684
pi06_style/45000/global_step45003/zero_pp_rank_1_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b1972707586c74370274ee04e4485fa7fa057b3483c1303131abeb2bd2a0166
3
+ size 158533620
pi06_style/45000/global_step45003/zero_pp_rank_2_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acb0ab8d866cd460dd93be07bb2128e56c355d7976ae03d322d2f860a4a7a833
3
+ size 158533620
pi06_style/45000/global_step45003/zero_pp_rank_3_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a907ccbc864f5e3dd536bbf0d5dd66c15a78e6bf85062d5acbf416053b20fc8e
3
+ size 158533620
pi06_style/45000/global_step45003/zero_pp_rank_4_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0af64a38bef892ada418f75ca7d51d9cbae3d313b04b5e6b45c3cafc30606d8c
3
+ size 158533620
pi06_style/45000/global_step45003/zero_pp_rank_5_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a8798cd0b30ee128d1cb81c356ff765541abec46ee9b928712bbdeb2ee01567
3
+ size 158533620
pi06_style/45000/global_step45003/zero_pp_rank_6_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1645fd219ccd5ffa378ecab9f5b55b0fc735c473287c0eb8dc3e02454871018f
3
+ size 158533620
pi06_style/45000/global_step45003/zero_pp_rank_7_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91a5f76e68d82c52c82832391a83c43d2dfed8ebf99a8ab90b056b9401df4a2b
3
+ size 158533620
pi06_style/45000/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step45003
pi06_style/45000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pi06_style/45000/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3398d6635d64612ffb19e55c2c7ef1a9b40aa37ff180593d18b72f203c8db79e
3
+ size 4997464040
pi06_style/45000/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e48f8132b45813359cadcdf3c301a9ac0c506472620c24a846ac6274fe5d6a7
3
+ size 2511587184
pi06_style/45000/model.safetensors.index.json ADDED
@@ -0,0 +1,832 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 755712,
4
+ "total_size": 7508959232
5
+ },
6
+ "weight_map": {
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
262
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
263
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
264
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
265
+ "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
266
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
267
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
268
+ "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
269
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
270
+ "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
271
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
272
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
273
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
277
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
278
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
279
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
280
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
281
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
282
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
283
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
284
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
290
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
293
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
295
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
296
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
298
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
299
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
300
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
301
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
302
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
304
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
305
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
306
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
307
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
308
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
309
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
310
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
312
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
313
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
315
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
316
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
318
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
320
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
322
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
323
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
324
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
325
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
326
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
328
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
329
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
330
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
331
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
332
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
334
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
337
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
338
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
339
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
340
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
341
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
342
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
343
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
344
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
345
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
346
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
347
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
348
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
349
+ "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
350
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
351
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
352
+ "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
353
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
354
+ "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
355
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
356
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
357
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
358
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
359
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
360
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
361
+ "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
362
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
364
+ "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
365
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
366
+ "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
367
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
368
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
369
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
370
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
373
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
374
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
376
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
377
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
378
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
379
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
380
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
382
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
385
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
386
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
388
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
389
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
390
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
391
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
392
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
394
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
396
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
397
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
398
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
400
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
401
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
402
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
403
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
404
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
405
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
406
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
408
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
409
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
410
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
411
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
412
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
413
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
414
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
415
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
416
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
417
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
418
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
420
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
421
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
422
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
424
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
425
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
426
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
427
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
428
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
430
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
432
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
433
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
434
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
435
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
436
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
437
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
438
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
439
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
440
+ "model.norm.weight": "model-00002-of-00002.safetensors",
441
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
442
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
443
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
444
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
445
+ "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
446
+ "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
447
+ "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
448
+ "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
449
+ "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
450
+ "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
451
+ "visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
452
+ "visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
453
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
454
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
455
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
456
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
457
+ "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
458
+ "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
459
+ "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
460
+ "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
461
+ "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
462
+ "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
463
+ "visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
464
+ "visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
465
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
466
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
467
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
468
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
469
+ "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
470
+ "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
471
+ "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
472
+ "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
473
+ "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
474
+ "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
475
+ "visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
476
+ "visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
477
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
478
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
479
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
480
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
481
+ "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
482
+ "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
483
+ "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
484
+ "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
485
+ "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
486
+ "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
487
+ "visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
488
+ "visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
489
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
490
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
491
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
492
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
493
+ "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
494
+ "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
495
+ "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
496
+ "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
497
+ "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
498
+ "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
499
+ "visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
500
+ "visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
501
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
502
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
503
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
504
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
505
+ "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
506
+ "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
507
+ "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
508
+ "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
509
+ "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
510
+ "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
511
+ "visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
512
+ "visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
513
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
514
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
515
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
516
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
517
+ "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
518
+ "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
519
+ "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
520
+ "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
521
+ "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
522
+ "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
523
+ "visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
524
+ "visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
525
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
526
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
527
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
528
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
529
+ "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
530
+ "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
531
+ "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
532
+ "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
533
+ "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
534
+ "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
535
+ "visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
536
+ "visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
537
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
538
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
539
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
540
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
541
+ "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
542
+ "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
543
+ "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
544
+ "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
545
+ "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
546
+ "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
547
+ "visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
548
+ "visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
549
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
550
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
551
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
552
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
553
+ "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
554
+ "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
555
+ "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
556
+ "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
557
+ "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
558
+ "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
559
+ "visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
560
+ "visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
561
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
562
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
563
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
564
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
565
+ "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
566
+ "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
567
+ "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
568
+ "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
569
+ "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
570
+ "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
571
+ "visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
572
+ "visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
573
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
574
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
575
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
576
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
577
+ "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
578
+ "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
579
+ "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
580
+ "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
581
+ "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
582
+ "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
583
+ "visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
584
+ "visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
585
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
586
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
587
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
588
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
589
+ "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
590
+ "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
591
+ "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
592
+ "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
593
+ "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
594
+ "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
595
+ "visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
596
+ "visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
597
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
598
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
599
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
600
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
601
+ "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
602
+ "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
603
+ "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
604
+ "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
605
+ "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
606
+ "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
607
+ "visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
608
+ "visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
609
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
610
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
611
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
612
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
613
+ "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
614
+ "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
615
+ "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
616
+ "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
617
+ "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
618
+ "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
619
+ "visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
620
+ "visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
621
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
622
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
623
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
624
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
625
+ "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
626
+ "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
627
+ "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
628
+ "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
629
+ "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
630
+ "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
631
+ "visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
632
+ "visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
633
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
634
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
635
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
636
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
637
+ "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
638
+ "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
639
+ "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
640
+ "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
641
+ "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
642
+ "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
643
+ "visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
644
+ "visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
645
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
646
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
647
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
648
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
649
+ "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
650
+ "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
651
+ "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
652
+ "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
653
+ "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
654
+ "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
655
+ "visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
656
+ "visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
657
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
658
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
659
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
660
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
661
+ "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
662
+ "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
663
+ "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
664
+ "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
665
+ "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
666
+ "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
667
+ "visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
668
+ "visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
669
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
670
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
671
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
672
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
673
+ "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
674
+ "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
675
+ "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
676
+ "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
677
+ "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
678
+ "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
679
+ "visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
680
+ "visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
681
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
682
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
683
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
684
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
685
+ "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
686
+ "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
687
+ "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
688
+ "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
689
+ "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
690
+ "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
691
+ "visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
692
+ "visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
693
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
694
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
695
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
696
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
697
+ "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
698
+ "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
699
+ "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
700
+ "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
701
+ "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
702
+ "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
703
+ "visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
704
+ "visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
705
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
706
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
707
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
708
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
709
+ "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
710
+ "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
711
+ "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
712
+ "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
713
+ "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
714
+ "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
715
+ "visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
716
+ "visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
717
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
718
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
719
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
720
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
721
+ "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
722
+ "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
723
+ "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
724
+ "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
725
+ "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
726
+ "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
727
+ "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
728
+ "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
729
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
730
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
731
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
732
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
733
+ "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
734
+ "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
735
+ "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
736
+ "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
737
+ "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
738
+ "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
739
+ "visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
740
+ "visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
741
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
742
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
743
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
744
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
745
+ "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
746
+ "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
747
+ "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
748
+ "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
749
+ "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
750
+ "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
751
+ "visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
752
+ "visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
753
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
754
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
755
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
756
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
757
+ "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
758
+ "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
759
+ "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
760
+ "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
761
+ "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
762
+ "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
763
+ "visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
764
+ "visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
765
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
766
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
767
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
768
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
769
+ "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
770
+ "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
771
+ "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
772
+ "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
773
+ "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
774
+ "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
775
+ "visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
776
+ "visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
777
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
778
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
779
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
780
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
781
+ "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
782
+ "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
783
+ "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
784
+ "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
785
+ "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
786
+ "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
787
+ "visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
788
+ "visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
789
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
790
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
791
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
792
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
793
+ "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
794
+ "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
795
+ "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
796
+ "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
797
+ "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
798
+ "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
799
+ "visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
800
+ "visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
801
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
802
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
803
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
804
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
805
+ "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
806
+ "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
807
+ "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
808
+ "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
809
+ "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
810
+ "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
811
+ "visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
812
+ "visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
813
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
814
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
815
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
816
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
817
+ "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
818
+ "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
819
+ "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
820
+ "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
821
+ "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
822
+ "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
823
+ "visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
824
+ "visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
825
+ "visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
826
+ "visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
827
+ "visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
828
+ "visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
829
+ "visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
830
+ "visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
831
+ }
832
+ }
pi06_style/45000/preprocessor_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_pad": null,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_processor_type": "Qwen2VLImageProcessorFast",
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "max_pixels": 451584,
26
+ "merge_size": 2,
27
+ "min_pixels": 12544,
28
+ "pad_size": null,
29
+ "patch_size": 14,
30
+ "processor_class": "Qwen2_5_VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_tensors": null,
34
+ "size": {
35
+ "longest_edge": 451584,
36
+ "shortest_edge": 12544
37
+ },
38
+ "temporal_patch_size": 2
39
+ }
pi06_style/45000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da661aad2e9ab98676885cda2d296e7d5781572d0062fef9c91ad25c971522e1
3
+ size 15920
pi06_style/45000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df342004a4d8e3626bf2a9f689fde7c8bfd6d995e14931f5496eda1f456cb6f2
3
+ size 15984
pi06_style/45000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f02096eb4e8850b91490e80e4a042e2e60f71bd2abc6a269d62c271649cb77d2
3
+ size 15984
pi06_style/45000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:326c778d3d0e7e3d5665fa0a9ecd92986609c430da08b41611d6c05dc19815a8
3
+ size 15984
pi06_style/45000/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d978dcb0c34e022ee6750e9d86814b8c82e4965d7e07662f35f06eeac12938f3
3
+ size 15984
pi06_style/45000/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01e83399aed1d9d173c3e07b2efa8530c956b62b2b68394c2ed0d43bd8bba9d1
3
+ size 15984
pi06_style/45000/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:606ab3ca92e3d20c327c69fdcce7f7e39bec2f2c3538b036088b255f917e3ba4
3
+ size 15984
pi06_style/45000/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1276a987dd22c9093fec58921ba19f340a28f18bff635cc01324e09a3c37ac3a
3
+ size 15984
pi06_style/45000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e745605ba3d2d082555ddc9f460c4b0b439907a995a8fe1c9256fa9b00bba790
3
+ size 1064
pi06_style/45000/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
pi06_style/45000/tokenizer_config.json ADDED
@@ -0,0 +1,1817 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<extra_id_0>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "<extra_id_1>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "151667": {
198
+ "content": "<extra_id_2>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "151668": {
206
+ "content": "<extra_id_3>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "151669": {
214
+ "content": "<extra_id_4>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<extra_id_5>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "<extra_id_6>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "<extra_id_7>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "<extra_id_8>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151674": {
254
+ "content": "<extra_id_9>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "151675": {
262
+ "content": "<extra_id_10>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "151676": {
270
+ "content": "<extra_id_11>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "151677": {
278
+ "content": "<extra_id_12>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "151678": {
286
+ "content": "<extra_id_13>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "151679": {
294
+ "content": "<extra_id_14>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "151680": {
302
+ "content": "<extra_id_15>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "151681": {
310
+ "content": "<extra_id_16>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "151682": {
318
+ "content": "<extra_id_17>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "151683": {
326
+ "content": "<extra_id_18>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "151684": {
334
+ "content": "<extra_id_19>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "151685": {
342
+ "content": "<extra_id_20>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "151686": {
350
+ "content": "<extra_id_21>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "151687": {
358
+ "content": "<extra_id_22>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "151688": {
366
+ "content": "<extra_id_23>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "151689": {
374
+ "content": "<extra_id_24>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "151690": {
382
+ "content": "<extra_id_25>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "151691": {
390
+ "content": "<extra_id_26>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "151692": {
398
+ "content": "<extra_id_27>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "151693": {
406
+ "content": "<extra_id_28>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "151694": {
414
+ "content": "<extra_id_29>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "151695": {
422
+ "content": "<extra_id_30>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "151696": {
430
+ "content": "<extra_id_31>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "151697": {
438
+ "content": "<extra_id_32>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "151698": {
446
+ "content": "<extra_id_33>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "151699": {
454
+ "content": "<extra_id_34>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "151700": {
462
+ "content": "<extra_id_35>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "151701": {
470
+ "content": "<extra_id_36>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "151702": {
478
+ "content": "<extra_id_37>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "151703": {
486
+ "content": "<extra_id_38>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "151704": {
494
+ "content": "<extra_id_39>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": true
500
+ },
501
+ "151705": {
502
+ "content": "<extra_id_40>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": true
508
+ },
509
+ "151706": {
510
+ "content": "<extra_id_41>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": true
516
+ },
517
+ "151707": {
518
+ "content": "<extra_id_42>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": true
524
+ },
525
+ "151708": {
526
+ "content": "<extra_id_43>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": true
532
+ },
533
+ "151709": {
534
+ "content": "<extra_id_44>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": true
540
+ },
541
+ "151710": {
542
+ "content": "<extra_id_45>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": true
548
+ },
549
+ "151711": {
550
+ "content": "<extra_id_46>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": true
556
+ },
557
+ "151712": {
558
+ "content": "<extra_id_47>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": true
564
+ },
565
+ "151713": {
566
+ "content": "<extra_id_48>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": true
572
+ },
573
+ "151714": {
574
+ "content": "<extra_id_49>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": true
580
+ },
581
+ "151715": {
582
+ "content": "<extra_id_50>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": true
588
+ },
589
+ "151716": {
590
+ "content": "<extra_id_51>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": true
596
+ },
597
+ "151717": {
598
+ "content": "<extra_id_52>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": true
604
+ },
605
+ "151718": {
606
+ "content": "<extra_id_53>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": true
612
+ },
613
+ "151719": {
614
+ "content": "<extra_id_54>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": true
620
+ },
621
+ "151720": {
622
+ "content": "<extra_id_55>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": true
628
+ },
629
+ "151721": {
630
+ "content": "<extra_id_56>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": true
636
+ },
637
+ "151722": {
638
+ "content": "<extra_id_57>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": true
644
+ },
645
+ "151723": {
646
+ "content": "<extra_id_58>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": true
652
+ },
653
+ "151724": {
654
+ "content": "<extra_id_59>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": true
660
+ },
661
+ "151725": {
662
+ "content": "<extra_id_60>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": true
668
+ },
669
+ "151726": {
670
+ "content": "<extra_id_61>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": true
676
+ },
677
+ "151727": {
678
+ "content": "<extra_id_62>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": true
684
+ },
685
+ "151728": {
686
+ "content": "<extra_id_63>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": true
692
+ },
693
+ "151729": {
694
+ "content": "<extra_id_64>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": true
700
+ },
701
+ "151730": {
702
+ "content": "<extra_id_65>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": true
708
+ },
709
+ "151731": {
710
+ "content": "<extra_id_66>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": true
716
+ },
717
+ "151732": {
718
+ "content": "<extra_id_67>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": true
724
+ },
725
+ "151733": {
726
+ "content": "<extra_id_68>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": true
732
+ },
733
+ "151734": {
734
+ "content": "<extra_id_69>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": true
740
+ },
741
+ "151735": {
742
+ "content": "<extra_id_70>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": true
748
+ },
749
+ "151736": {
750
+ "content": "<extra_id_71>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": true
756
+ },
757
+ "151737": {
758
+ "content": "<extra_id_72>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": true
764
+ },
765
+ "151738": {
766
+ "content": "<extra_id_73>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": true
772
+ },
773
+ "151739": {
774
+ "content": "<extra_id_74>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": true
780
+ },
781
+ "151740": {
782
+ "content": "<extra_id_75>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": true
788
+ },
789
+ "151741": {
790
+ "content": "<extra_id_76>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": true
796
+ },
797
+ "151742": {
798
+ "content": "<extra_id_77>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": true
804
+ },
805
+ "151743": {
806
+ "content": "<extra_id_78>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": true
812
+ },
813
+ "151744": {
814
+ "content": "<extra_id_79>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": true
820
+ },
821
+ "151745": {
822
+ "content": "<extra_id_80>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": true
828
+ },
829
+ "151746": {
830
+ "content": "<extra_id_81>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": true
836
+ },
837
+ "151747": {
838
+ "content": "<extra_id_82>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": true
844
+ },
845
+ "151748": {
846
+ "content": "<extra_id_83>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": true
852
+ },
853
+ "151749": {
854
+ "content": "<extra_id_84>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ },
861
+ "151750": {
862
+ "content": "<extra_id_85>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": true
868
+ },
869
+ "151751": {
870
+ "content": "<extra_id_86>",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": true
876
+ },
877
+ "151752": {
878
+ "content": "<extra_id_87>",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": true
884
+ },
885
+ "151753": {
886
+ "content": "<extra_id_88>",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": true
892
+ },
893
+ "151754": {
894
+ "content": "<extra_id_89>",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": true
900
+ },
901
+ "151755": {
902
+ "content": "<extra_id_90>",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": true
908
+ },
909
+ "151756": {
910
+ "content": "<extra_id_91>",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": true
916
+ },
917
+ "151757": {
918
+ "content": "<extra_id_92>",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": true
924
+ },
925
+ "151758": {
926
+ "content": "<extra_id_93>",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": true
932
+ },
933
+ "151759": {
934
+ "content": "<extra_id_94>",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": true
940
+ },
941
+ "151760": {
942
+ "content": "<extra_id_95>",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": true
948
+ },
949
+ "151761": {
950
+ "content": "<extra_id_96>",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": true
956
+ },
957
+ "151762": {
958
+ "content": "<extra_id_97>",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": true
964
+ },
965
+ "151763": {
966
+ "content": "<extra_id_98>",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": true
972
+ },
973
+ "151764": {
974
+ "content": "<extra_id_99>",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": true
980
+ },
981
+ "151765": {
982
+ "content": "<extra_id_100>",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": true
988
+ },
989
+ "151766": {
990
+ "content": "<extra_id_101>",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": true
996
+ },
997
+ "151767": {
998
+ "content": "<extra_id_102>",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": true
1004
+ },
1005
+ "151768": {
1006
+ "content": "<extra_id_103>",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": true
1012
+ },
1013
+ "151769": {
1014
+ "content": "<extra_id_104>",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": true
1020
+ },
1021
+ "151770": {
1022
+ "content": "<extra_id_105>",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": true
1028
+ },
1029
+ "151771": {
1030
+ "content": "<extra_id_106>",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": true
1036
+ },
1037
+ "151772": {
1038
+ "content": "<extra_id_107>",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": true
1044
+ },
1045
+ "151773": {
1046
+ "content": "<extra_id_108>",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": true
1052
+ },
1053
+ "151774": {
1054
+ "content": "<extra_id_109>",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": true
1060
+ },
1061
+ "151775": {
1062
+ "content": "<extra_id_110>",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": true
1068
+ },
1069
+ "151776": {
1070
+ "content": "<extra_id_111>",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": true
1076
+ },
1077
+ "151777": {
1078
+ "content": "<extra_id_112>",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": true
1084
+ },
1085
+ "151778": {
1086
+ "content": "<extra_id_113>",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": true
1092
+ },
1093
+ "151779": {
1094
+ "content": "<extra_id_114>",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": true
1100
+ },
1101
+ "151780": {
1102
+ "content": "<extra_id_115>",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": true
1108
+ },
1109
+ "151781": {
1110
+ "content": "<extra_id_116>",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": true
1116
+ },
1117
+ "151782": {
1118
+ "content": "<extra_id_117>",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": true
1124
+ },
1125
+ "151783": {
1126
+ "content": "<extra_id_118>",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": true
1132
+ },
1133
+ "151784": {
1134
+ "content": "<extra_id_119>",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": true
1140
+ },
1141
+ "151785": {
1142
+ "content": "<extra_id_120>",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": true
1148
+ },
1149
+ "151786": {
1150
+ "content": "<extra_id_121>",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": true
1156
+ },
1157
+ "151787": {
1158
+ "content": "<extra_id_122>",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": true
1164
+ },
1165
+ "151788": {
1166
+ "content": "<extra_id_123>",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": true
1172
+ },
1173
+ "151789": {
1174
+ "content": "<extra_id_124>",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": true
1180
+ },
1181
+ "151790": {
1182
+ "content": "<extra_id_125>",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": true
1188
+ },
1189
+ "151791": {
1190
+ "content": "<extra_id_126>",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": true
1196
+ },
1197
+ "151792": {
1198
+ "content": "<extra_id_127>",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": true
1204
+ },
1205
+ "151793": {
1206
+ "content": "<extra_id_128>",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": true
1212
+ },
1213
+ "151794": {
1214
+ "content": "<extra_id_129>",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": true
1220
+ },
1221
+ "151795": {
1222
+ "content": "<extra_id_130>",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": true
1228
+ },
1229
+ "151796": {
1230
+ "content": "<extra_id_131>",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": true
1236
+ },
1237
+ "151797": {
1238
+ "content": "<extra_id_132>",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": true
1244
+ },
1245
+ "151798": {
1246
+ "content": "<extra_id_133>",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": true
1252
+ },
1253
+ "151799": {
1254
+ "content": "<extra_id_134>",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": true
1260
+ },
1261
+ "151800": {
1262
+ "content": "<extra_id_135>",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": true
1268
+ },
1269
+ "151801": {
1270
+ "content": "<extra_id_136>",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": true
1276
+ },
1277
+ "151802": {
1278
+ "content": "<extra_id_137>",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": true
1284
+ },
1285
+ "151803": {
1286
+ "content": "<extra_id_138>",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": true
1292
+ },
1293
+ "151804": {
1294
+ "content": "<extra_id_139>",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": true
1300
+ },
1301
+ "151805": {
1302
+ "content": "<extra_id_140>",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": true
1308
+ },
1309
+ "151806": {
1310
+ "content": "<extra_id_141>",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": true
1316
+ },
1317
+ "151807": {
1318
+ "content": "<extra_id_142>",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": true
1324
+ },
1325
+ "151808": {
1326
+ "content": "<extra_id_143>",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": true
1332
+ },
1333
+ "151809": {
1334
+ "content": "<extra_id_144>",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": true
1340
+ },
1341
+ "151810": {
1342
+ "content": "<extra_id_145>",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": true
1348
+ },
1349
+ "151811": {
1350
+ "content": "<extra_id_146>",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": true
1356
+ },
1357
+ "151812": {
1358
+ "content": "<extra_id_147>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": true
1364
+ },
1365
+ "151813": {
1366
+ "content": "<extra_id_148>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": true
1372
+ },
1373
+ "151814": {
1374
+ "content": "<extra_id_149>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": true
1380
+ },
1381
+ "151815": {
1382
+ "content": "<extra_id_150>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": true
1388
+ },
1389
+ "151816": {
1390
+ "content": "<extra_id_151>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": true
1396
+ },
1397
+ "151817": {
1398
+ "content": "<extra_id_152>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": true
1404
+ },
1405
+ "151818": {
1406
+ "content": "<extra_id_153>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": true
1412
+ },
1413
+ "151819": {
1414
+ "content": "<extra_id_154>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": true
1420
+ },
1421
+ "151820": {
1422
+ "content": "<extra_id_155>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": true
1428
+ },
1429
+ "151821": {
1430
+ "content": "<extra_id_156>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": true
1436
+ },
1437
+ "151822": {
1438
+ "content": "<extra_id_157>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": true
1444
+ },
1445
+ "151823": {
1446
+ "content": "<extra_id_158>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": true
1452
+ },
1453
+ "151824": {
1454
+ "content": "<extra_id_159>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": true
1460
+ },
1461
+ "151825": {
1462
+ "content": "<extra_id_160>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": true
1468
+ },
1469
+ "151826": {
1470
+ "content": "<extra_id_161>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": true
1476
+ },
1477
+ "151827": {
1478
+ "content": "<extra_id_162>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": true
1484
+ },
1485
+ "151828": {
1486
+ "content": "<extra_id_163>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": true
1492
+ },
1493
+ "151829": {
1494
+ "content": "<extra_id_164>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": true
1500
+ },
1501
+ "151830": {
1502
+ "content": "<extra_id_165>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": true
1508
+ },
1509
+ "151831": {
1510
+ "content": "<extra_id_166>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": true
1516
+ },
1517
+ "151832": {
1518
+ "content": "<extra_id_167>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": true
1524
+ },
1525
+ "151833": {
1526
+ "content": "<extra_id_168>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": true
1532
+ },
1533
+ "151834": {
1534
+ "content": "<extra_id_169>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": true
1540
+ },
1541
+ "151835": {
1542
+ "content": "<extra_id_170>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": true
1548
+ },
1549
+ "151836": {
1550
+ "content": "<extra_id_171>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": true
1556
+ },
1557
+ "151837": {
1558
+ "content": "<extra_id_172>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": true
1564
+ },
1565
+ "151838": {
1566
+ "content": "<extra_id_173>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": true
1572
+ },
1573
+ "151839": {
1574
+ "content": "<extra_id_174>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": true
1580
+ },
1581
+ "151840": {
1582
+ "content": "<extra_id_175>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": true
1588
+ },
1589
+ "151841": {
1590
+ "content": "<extra_id_176>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": true
1596
+ },
1597
+ "151842": {
1598
+ "content": "<extra_id_177>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": true
1604
+ },
1605
+ "151843": {
1606
+ "content": "<extra_id_178>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": true
1612
+ },
1613
+ "151844": {
1614
+ "content": "<extra_id_179>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": true
1620
+ },
1621
+ "151845": {
1622
+ "content": "<extra_id_180>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": true
1628
+ },
1629
+ "151846": {
1630
+ "content": "<extra_id_181>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": true
1636
+ },
1637
+ "151847": {
1638
+ "content": "<extra_id_182>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": true
1644
+ },
1645
+ "151848": {
1646
+ "content": "<extra_id_183>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": true
1652
+ },
1653
+ "151849": {
1654
+ "content": "<extra_id_184>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": true
1660
+ },
1661
+ "151850": {
1662
+ "content": "<extra_id_185>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": true
1668
+ },
1669
+ "151851": {
1670
+ "content": "<extra_id_186>",
1671
+ "lstrip": false,
1672
+ "normalized": false,
1673
+ "rstrip": false,
1674
+ "single_word": false,
1675
+ "special": true
1676
+ },
1677
+ "151852": {
1678
+ "content": "<extra_id_187>",
1679
+ "lstrip": false,
1680
+ "normalized": false,
1681
+ "rstrip": false,
1682
+ "single_word": false,
1683
+ "special": true
1684
+ },
1685
+ "151853": {
1686
+ "content": "<extra_id_188>",
1687
+ "lstrip": false,
1688
+ "normalized": false,
1689
+ "rstrip": false,
1690
+ "single_word": false,
1691
+ "special": true
1692
+ },
1693
+ "151854": {
1694
+ "content": "<extra_id_189>",
1695
+ "lstrip": false,
1696
+ "normalized": false,
1697
+ "rstrip": false,
1698
+ "single_word": false,
1699
+ "special": true
1700
+ },
1701
+ "151855": {
1702
+ "content": "<extra_id_190>",
1703
+ "lstrip": false,
1704
+ "normalized": false,
1705
+ "rstrip": false,
1706
+ "single_word": false,
1707
+ "special": true
1708
+ },
1709
+ "151856": {
1710
+ "content": "<extra_id_191>",
1711
+ "lstrip": false,
1712
+ "normalized": false,
1713
+ "rstrip": false,
1714
+ "single_word": false,
1715
+ "special": true
1716
+ },
1717
+ "151857": {
1718
+ "content": "<extra_id_192>",
1719
+ "lstrip": false,
1720
+ "normalized": false,
1721
+ "rstrip": false,
1722
+ "single_word": false,
1723
+ "special": true
1724
+ },
1725
+ "151858": {
1726
+ "content": "<extra_id_193>",
1727
+ "lstrip": false,
1728
+ "normalized": false,
1729
+ "rstrip": false,
1730
+ "single_word": false,
1731
+ "special": true
1732
+ },
1733
+ "151859": {
1734
+ "content": "<extra_id_194>",
1735
+ "lstrip": false,
1736
+ "normalized": false,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": true
1740
+ },
1741
+ "151860": {
1742
+ "content": "<extra_id_195>",
1743
+ "lstrip": false,
1744
+ "normalized": false,
1745
+ "rstrip": false,
1746
+ "single_word": false,
1747
+ "special": true
1748
+ },
1749
+ "151861": {
1750
+ "content": "<extra_id_196>",
1751
+ "lstrip": false,
1752
+ "normalized": false,
1753
+ "rstrip": false,
1754
+ "single_word": false,
1755
+ "special": true
1756
+ },
1757
+ "151862": {
1758
+ "content": "<extra_id_197>",
1759
+ "lstrip": false,
1760
+ "normalized": false,
1761
+ "rstrip": false,
1762
+ "single_word": false,
1763
+ "special": true
1764
+ },
1765
+ "151863": {
1766
+ "content": "<extra_id_198>",
1767
+ "lstrip": false,
1768
+ "normalized": false,
1769
+ "rstrip": false,
1770
+ "single_word": false,
1771
+ "special": true
1772
+ },
1773
+ "151864": {
1774
+ "content": "<extra_id_199>",
1775
+ "lstrip": false,
1776
+ "normalized": false,
1777
+ "rstrip": false,
1778
+ "single_word": false,
1779
+ "special": true
1780
+ },
1781
+ "151865": {
1782
+ "content": "<extra_id_200>",
1783
+ "lstrip": false,
1784
+ "normalized": false,
1785
+ "rstrip": false,
1786
+ "single_word": false,
1787
+ "special": true
1788
+ }
1789
+ },
1790
+ "additional_special_tokens": [
1791
+ "<|im_start|>",
1792
+ "<|im_end|>",
1793
+ "<|object_ref_start|>",
1794
+ "<|object_ref_end|>",
1795
+ "<|box_start|>",
1796
+ "<|box_end|>",
1797
+ "<|quad_start|>",
1798
+ "<|quad_end|>",
1799
+ "<|vision_start|>",
1800
+ "<|vision_end|>",
1801
+ "<|vision_pad|>",
1802
+ "<|image_pad|>",
1803
+ "<|video_pad|>"
1804
+ ],
1805
+ "bos_token": null,
1806
+ "clean_up_tokenization_spaces": false,
1807
+ "eos_token": "<|im_end|>",
1808
+ "errors": "replace",
1809
+ "extra_special_tokens": {},
1810
+ "model_max_length": 4096,
1811
+ "pad_token": "<|endoftext|>",
1812
+ "padding_side": "right",
1813
+ "processor_class": "Qwen2_5_VLProcessor",
1814
+ "split_special_tokens": false,
1815
+ "tokenizer_class": "Qwen2Tokenizer",
1816
+ "unk_token": null
1817
+ }
pi06_style/45000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
pi06_style/45000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5ec9602e8904b9acd2699f9915bb45f3e2046c136bff9e39896cdb93dd2b06f
3
+ size 7480
pi06_style/45000/video_preprocessor_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "do_sample_frames": false,
12
+ "fps": 2,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "input_data_format": null,
24
+ "max_frames": 8,
25
+ "max_pixels": 802816,
26
+ "merge_size": 2,
27
+ "min_frames": 4,
28
+ "min_pixels": 200704,
29
+ "num_frames": null,
30
+ "pad_size": null,
31
+ "patch_size": 14,
32
+ "processor_class": "Qwen2_5_VLProcessor",
33
+ "resample": 3,
34
+ "rescale_factor": 0.00392156862745098,
35
+ "return_metadata": false,
36
+ "size": {
37
+ "longest_edge": 802816,
38
+ "shortest_edge": 200704
39
+ },
40
+ "temporal_patch_size": 2,
41
+ "video_metadata": null,
42
+ "video_processor_type": "Qwen2VLVideoProcessor"
43
+ }
pi06_style/45000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
pi06_style/45000/zero_to_fp32.py ADDED
@@ -0,0 +1,760 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+
3
+ # Copyright (c) Microsoft Corporation.
4
+ # SPDX-License-Identifier: Apache-2.0
5
+
6
+ # DeepSpeed Team
7
+
8
+ # This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
9
+ # copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
10
+ # the future. Once extracted, the weights don't require DeepSpeed and can be used in any
11
+ # application.
12
+ #
13
+ # example:
14
+ # python zero_to_fp32.py . output_dir/
15
+ # or
16
+ # python zero_to_fp32.py . output_dir/ --safe_serialization
17
+
18
+ import argparse
19
+ import torch
20
+ import glob
21
+ import math
22
+ import os
23
+ import re
24
+ import gc
25
+ import json
26
+ import numpy as np
27
+ from tqdm import tqdm
28
+ from collections import OrderedDict
29
+ from dataclasses import dataclass
30
+
31
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
32
+ # DeepSpeed data structures it has to be available in the current python environment.
33
+ from deepspeed.utils import logger
34
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
35
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
36
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
37
+
38
+
39
+ @dataclass
40
+ class zero_model_state:
41
+ buffers: dict()
42
+ param_shapes: dict()
43
+ shared_params: list
44
+ ds_version: int
45
+ frozen_param_shapes: dict()
46
+ frozen_param_fragments: dict()
47
+
48
+
49
+ debug = 0
50
+
51
+ # load to cpu
52
+ device = torch.device('cpu')
53
+
54
+
55
+ def atoi(text):
56
+ return int(text) if text.isdigit() else text
57
+
58
+
59
+ def natural_keys(text):
60
+ '''
61
+ alist.sort(key=natural_keys) sorts in human order
62
+ http://nedbatchelder.com/blog/200712/human_sorting.html
63
+ (See Toothy's implementation in the comments)
64
+ '''
65
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
66
+
67
+
68
+ def get_model_state_file(checkpoint_dir, zero_stage):
69
+ if not os.path.isdir(checkpoint_dir):
70
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
71
+
72
+ # there should be only one file
73
+ if zero_stage <= 2:
74
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
75
+ elif zero_stage == 3:
76
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
77
+
78
+ if not os.path.exists(file):
79
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
80
+
81
+ return file
82
+
83
+
84
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
85
+ # XXX: need to test that this simple glob rule works for multi-node setup too
86
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
87
+
88
+ if len(ckpt_files) == 0:
89
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
90
+
91
+ return ckpt_files
92
+
93
+
94
+ def get_optim_files(checkpoint_dir):
95
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
96
+
97
+
98
+ def get_model_state_files(checkpoint_dir):
99
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
100
+
101
+
102
+ def parse_model_states(files):
103
+ zero_model_states = []
104
+ for file in files:
105
+ state_dict = torch.load(file, map_location=device, weights_only=False)
106
+
107
+ if BUFFER_NAMES not in state_dict:
108
+ raise ValueError(f"{file} is not a model state checkpoint")
109
+ buffer_names = state_dict[BUFFER_NAMES]
110
+ if debug:
111
+ print("Found buffers:", buffer_names)
112
+
113
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
114
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
115
+ param_shapes = state_dict[PARAM_SHAPES]
116
+
117
+ # collect parameters that are included in param_shapes
118
+ param_names = []
119
+ for s in param_shapes:
120
+ for name in s.keys():
121
+ param_names.append(name)
122
+
123
+ # update with frozen parameters
124
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
125
+ if frozen_param_shapes is not None:
126
+ if debug:
127
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
128
+ param_names += list(frozen_param_shapes.keys())
129
+
130
+ # handle shared params
131
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
132
+
133
+ ds_version = state_dict.get(DS_VERSION, None)
134
+
135
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
136
+
137
+ z_model_state = zero_model_state(buffers=buffers,
138
+ param_shapes=param_shapes,
139
+ shared_params=shared_params,
140
+ ds_version=ds_version,
141
+ frozen_param_shapes=frozen_param_shapes,
142
+ frozen_param_fragments=frozen_param_fragments)
143
+ zero_model_states.append(z_model_state)
144
+
145
+ return zero_model_states
146
+
147
+
148
+ def parse_optim_states(files, ds_checkpoint_dir):
149
+ total_files = len(files)
150
+ state_dicts = []
151
+ for f in tqdm(files, desc='Loading checkpoint shards'):
152
+ state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
153
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
154
+ # and also handle the case where it was already removed by another helper script
155
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
156
+ state_dicts.append(state_dict)
157
+
158
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
159
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
160
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
161
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
162
+
163
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
164
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
165
+ # use the max of the partition_count to get the dp world_size.
166
+
167
+ if type(world_size) is list:
168
+ world_size = max(world_size)
169
+
170
+ if world_size != total_files:
171
+ raise ValueError(
172
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
173
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
174
+ )
175
+
176
+ # the groups are named differently in each stage
177
+ if zero_stage <= 2:
178
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
179
+ elif zero_stage == 3:
180
+ fp32_groups_key = FP32_FLAT_GROUPS
181
+ else:
182
+ raise ValueError(f"unknown zero stage {zero_stage}")
183
+
184
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
185
+ return zero_stage, world_size, fp32_flat_groups
186
+
187
+
188
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
189
+ """
190
+ Returns fp32 state_dict reconstructed from ds checkpoint
191
+
192
+ Args:
193
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
194
+
195
+ """
196
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
197
+
198
+ optim_files = get_optim_files(ds_checkpoint_dir)
199
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
200
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
201
+
202
+ model_files = get_model_state_files(ds_checkpoint_dir)
203
+
204
+ zero_model_states = parse_model_states(model_files)
205
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
206
+
207
+ if zero_stage <= 2:
208
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
209
+ exclude_frozen_parameters)
210
+ elif zero_stage == 3:
211
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
212
+ exclude_frozen_parameters)
213
+
214
+
215
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
216
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
217
+ return
218
+
219
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
220
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
221
+
222
+ if debug:
223
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
224
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
225
+
226
+ wanted_params = len(frozen_param_shapes)
227
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
228
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
229
+ print(f'Frozen params: Have {avail_numel} numels to process.')
230
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
231
+
232
+ total_params = 0
233
+ total_numel = 0
234
+ for name, shape in frozen_param_shapes.items():
235
+ total_params += 1
236
+ unpartitioned_numel = shape.numel()
237
+ total_numel += unpartitioned_numel
238
+
239
+ state_dict[name] = frozen_param_fragments[name]
240
+
241
+ if debug:
242
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
243
+
244
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
245
+
246
+
247
+ def _has_callable(obj, fn):
248
+ attr = getattr(obj, fn, None)
249
+ return callable(attr)
250
+
251
+
252
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
253
+ param_shapes = zero_model_states[0].param_shapes
254
+
255
+ # Reconstruction protocol:
256
+ #
257
+ # XXX: document this
258
+
259
+ if debug:
260
+ for i in range(world_size):
261
+ for j in range(len(fp32_flat_groups[0])):
262
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
263
+
264
+ # XXX: memory usage doubles here (zero2)
265
+ num_param_groups = len(fp32_flat_groups[0])
266
+ merged_single_partition_of_fp32_groups = []
267
+ for i in range(num_param_groups):
268
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
269
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
270
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
271
+ avail_numel = sum(
272
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
273
+
274
+ if debug:
275
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
276
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
277
+ # not asserting if there is a mismatch due to possible padding
278
+ print(f"Have {avail_numel} numels to process.")
279
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
280
+
281
+ # params
282
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
283
+ # out-of-core computing solution
284
+ total_numel = 0
285
+ total_params = 0
286
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
287
+ offset = 0
288
+ avail_numel = full_single_fp32_vector.numel()
289
+ for name, shape in shapes.items():
290
+
291
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
292
+ total_numel += unpartitioned_numel
293
+ total_params += 1
294
+
295
+ if debug:
296
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
297
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
298
+ offset += unpartitioned_numel
299
+
300
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
301
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
302
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
303
+ # live optimizer object, so we are checking that the numbers are within the right range
304
+ align_to = 2 * world_size
305
+
306
+ def zero2_align(x):
307
+ return align_to * math.ceil(x / align_to)
308
+
309
+ if debug:
310
+ print(f"original offset={offset}, avail_numel={avail_numel}")
311
+
312
+ offset = zero2_align(offset)
313
+ avail_numel = zero2_align(avail_numel)
314
+
315
+ if debug:
316
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
317
+
318
+ # Sanity check
319
+ if offset != avail_numel:
320
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
321
+
322
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
323
+
324
+
325
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
326
+ exclude_frozen_parameters):
327
+ state_dict = OrderedDict()
328
+
329
+ # buffers
330
+ buffers = zero_model_states[0].buffers
331
+ state_dict.update(buffers)
332
+ if debug:
333
+ print(f"added {len(buffers)} buffers")
334
+
335
+ if not exclude_frozen_parameters:
336
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
337
+
338
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
339
+
340
+ # recover shared parameters
341
+ for pair in zero_model_states[0].shared_params:
342
+ if pair[1] in state_dict:
343
+ state_dict[pair[0]] = state_dict[pair[1]]
344
+
345
+ return state_dict
346
+
347
+
348
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
349
+ remainder = unpartitioned_numel % world_size
350
+ padding_numel = (world_size - remainder) if remainder else 0
351
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
352
+ return partitioned_numel, padding_numel
353
+
354
+
355
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
356
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
357
+ return
358
+
359
+ if debug:
360
+ for i in range(world_size):
361
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
362
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
363
+
364
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
365
+ wanted_params = len(frozen_param_shapes)
366
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
367
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
368
+ print(f'Frozen params: Have {avail_numel} numels to process.')
369
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
370
+
371
+ total_params = 0
372
+ total_numel = 0
373
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
374
+ total_params += 1
375
+ unpartitioned_numel = shape.numel()
376
+ total_numel += unpartitioned_numel
377
+
378
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
379
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
380
+
381
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
382
+
383
+ if debug:
384
+ print(
385
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
386
+ )
387
+
388
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
389
+
390
+
391
+ class GatheredTensor:
392
+ """
393
+ A pseudo tensor that collects partitioned weights.
394
+ It is more memory efficient when there are multiple groups.
395
+ """
396
+
397
+ def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
398
+ self.flat_groups = flat_groups
399
+ self.flat_groups_offset = flat_groups_offset
400
+ self.offset = offset
401
+ self.partitioned_numel = partitioned_numel
402
+ self.shape = shape
403
+ self.dtype = self.flat_groups[0][0].dtype
404
+
405
+ def contiguous(self):
406
+ """
407
+ Merge partitioned weights from flat_groups into a single tensor.
408
+ """
409
+ end_idx = self.offset + self.partitioned_numel
410
+ world_size = len(self.flat_groups)
411
+ pad_flat_param_chunks = []
412
+
413
+ for rank_i in range(world_size):
414
+ # for each rank, we need to collect weights from related group/groups
415
+ flat_groups_at_rank_i = self.flat_groups[rank_i]
416
+ start_group_id = None
417
+ end_group_id = None
418
+ for group_id in range(len(self.flat_groups_offset)):
419
+ if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
420
+ start_group_id = group_id
421
+ if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
422
+ end_group_id = group_id
423
+ break
424
+ # collect weights from related group/groups
425
+ for group_id in range(start_group_id, end_group_id + 1):
426
+ flat_tensor = flat_groups_at_rank_i[group_id]
427
+ start_offset = self.offset - self.flat_groups_offset[group_id]
428
+ end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
429
+ pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
430
+
431
+ # collect weights from all ranks
432
+ pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
433
+ param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
434
+ return param
435
+
436
+
437
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
438
+ param_shapes = zero_model_states[0].param_shapes
439
+ avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
440
+
441
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
442
+ # param, re-consolidating each param, while dealing with padding if any
443
+
444
+ # merge list of dicts, preserving order
445
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
446
+
447
+ if debug:
448
+ for i in range(world_size):
449
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
450
+
451
+ wanted_params = len(param_shapes)
452
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
453
+ # not asserting if there is a mismatch due to possible padding
454
+ avail_numel = fp32_flat_groups[0].numel() * world_size
455
+ print(f"Trainable params: Have {avail_numel} numels to process.")
456
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
457
+
458
+ # params
459
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
460
+ # out-of-core computing solution
461
+ offset = 0
462
+ total_numel = 0
463
+ total_params = 0
464
+ flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
465
+ for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
466
+ unpartitioned_numel = shape.numel()
467
+ total_numel += unpartitioned_numel
468
+ total_params += 1
469
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
470
+
471
+ if debug:
472
+ print(
473
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
474
+ )
475
+
476
+ # memory efficient tensor
477
+ tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
478
+ state_dict[name] = tensor
479
+ offset += partitioned_numel
480
+
481
+ offset *= world_size
482
+
483
+ # Sanity check
484
+ if offset != avail_numel:
485
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
486
+
487
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
488
+
489
+
490
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
491
+ exclude_frozen_parameters):
492
+ state_dict = OrderedDict()
493
+
494
+ # buffers
495
+ buffers = zero_model_states[0].buffers
496
+ state_dict.update(buffers)
497
+ if debug:
498
+ print(f"added {len(buffers)} buffers")
499
+
500
+ if not exclude_frozen_parameters:
501
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
502
+
503
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
504
+
505
+ # recover shared parameters
506
+ for pair in zero_model_states[0].shared_params:
507
+ if pair[1] in state_dict:
508
+ state_dict[pair[0]] = state_dict[pair[1]]
509
+
510
+ return state_dict
511
+
512
+
513
+ def to_torch_tensor(state_dict, return_empty_tensor=False):
514
+ """
515
+ Convert state_dict of GatheredTensor to torch tensor
516
+ """
517
+ torch_state_dict = {}
518
+ converted_tensors = {}
519
+ for name, tensor in state_dict.items():
520
+ tensor_id = id(tensor)
521
+ if tensor_id in converted_tensors: # shared tensors
522
+ shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
523
+ torch_state_dict[name] = shared_tensor
524
+ else:
525
+ converted_tensors[tensor_id] = name
526
+ if return_empty_tensor:
527
+ torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
528
+ else:
529
+ torch_state_dict[name] = tensor.contiguous()
530
+ return torch_state_dict
531
+
532
+
533
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
534
+ tag=None,
535
+ exclude_frozen_parameters=False,
536
+ lazy_mode=False):
537
+ """
538
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
539
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
540
+ via a model hub.
541
+
542
+ Args:
543
+ - ``checkpoint_dir``: path to the desired checkpoint folder
544
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
545
+ - ``exclude_frozen_parameters``: exclude frozen parameters
546
+ - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
547
+ Convert the pesduo tensor to torch tensor by ``.contiguous()``
548
+
549
+ Returns:
550
+ - pytorch ``state_dict``
551
+
552
+ A typical usage might be ::
553
+
554
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
555
+ # do the training and checkpoint saving
556
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
557
+ model = model.cpu() # move to cpu
558
+ model.load_state_dict(state_dict)
559
+ # submit to model hub or save the model to share with others
560
+
561
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
562
+ application. i.e. you will need to re-initialize the deepspeed engine, since
563
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
564
+
565
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
566
+
567
+ Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
568
+ You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
569
+ the checkpoint. Or you can load state_dict in lazy mode ::
570
+
571
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
572
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
573
+ for name, lazy_tensor in state_dict.item():
574
+ tensor = lazy_tensor.contiguous() # to cpu
575
+ print(name, tensor)
576
+ # del tensor to release memory if it no longer in use
577
+ """
578
+ if tag is None:
579
+ latest_path = os.path.join(checkpoint_dir, 'latest')
580
+ if os.path.isfile(latest_path):
581
+ with open(latest_path, 'r') as fd:
582
+ tag = fd.read().strip()
583
+ else:
584
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
585
+
586
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
587
+
588
+ if not os.path.isdir(ds_checkpoint_dir):
589
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
590
+
591
+ state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
592
+ if lazy_mode:
593
+ return state_dict
594
+ else:
595
+ return to_torch_tensor(state_dict)
596
+
597
+
598
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
599
+ output_dir,
600
+ max_shard_size="5GB",
601
+ safe_serialization=False,
602
+ tag=None,
603
+ exclude_frozen_parameters=False):
604
+ """
605
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
606
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
607
+
608
+ Args:
609
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
610
+ - ``output_dir``: directory to the pytorch fp32 state_dict output files
611
+ - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
612
+ - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
613
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
614
+ - ``exclude_frozen_parameters``: exclude frozen parameters
615
+ """
616
+
617
+ # Dependency pre-check
618
+ if safe_serialization:
619
+ try:
620
+ from safetensors.torch import save_file
621
+ except ImportError:
622
+ print('If you want to use `safe_serialization`, please `pip install safetensors`')
623
+ raise
624
+ if max_shard_size is not None:
625
+ try:
626
+ from huggingface_hub import split_torch_state_dict_into_shards
627
+ except ImportError:
628
+ print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
629
+ raise
630
+
631
+ # Convert zero checkpoint to state_dict
632
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
633
+ tag,
634
+ exclude_frozen_parameters,
635
+ lazy_mode=True)
636
+
637
+ # Shard the model if it is too big.
638
+ weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
639
+ if max_shard_size is not None:
640
+ filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
641
+ # an memory-efficient approach for sharding
642
+ empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
643
+ state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
644
+ filename_pattern=filename_pattern,
645
+ max_shard_size=max_shard_size)
646
+ else:
647
+ from collections import namedtuple
648
+ StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
649
+ state_dict_split = StateDictSplit(is_sharded=False,
650
+ filename_to_tensors={weights_name: list(state_dict.keys())})
651
+
652
+ # Save the model by shard
653
+ os.makedirs(output_dir, exist_ok=True)
654
+ filename_to_tensors = state_dict_split.filename_to_tensors.items()
655
+ for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
656
+ shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
657
+ shard_state_dict = to_torch_tensor(shard_state_dict)
658
+ output_path = os.path.join(output_dir, shard_file)
659
+ if safe_serialization:
660
+ save_file(shard_state_dict, output_path, metadata={"format": "pt"})
661
+ else:
662
+ torch.save(shard_state_dict, output_path)
663
+ # release the memory of current shard
664
+ for tensor_name in list(shard_state_dict.keys()):
665
+ del state_dict[tensor_name]
666
+ del shard_state_dict[tensor_name]
667
+ del shard_state_dict
668
+ gc.collect()
669
+
670
+ # Save index if sharded
671
+ if state_dict_split.is_sharded:
672
+ index = {
673
+ "metadata": state_dict_split.metadata,
674
+ "weight_map": state_dict_split.tensor_to_filename,
675
+ }
676
+ save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
677
+ save_index_file = os.path.join(output_dir, save_index_file)
678
+ with open(save_index_file, "w", encoding="utf-8") as f:
679
+ content = json.dumps(index, indent=2, sort_keys=True) + "\n"
680
+ f.write(content)
681
+
682
+
683
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
684
+ """
685
+ 1. Put the provided model to cpu
686
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
687
+ 3. Load it into the provided model
688
+
689
+ Args:
690
+ - ``model``: the model object to update
691
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
692
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
693
+
694
+ Returns:
695
+ - ``model`: modified model
696
+
697
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
698
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
699
+ conveniently placed for you in the checkpoint folder.
700
+
701
+ A typical usage might be ::
702
+
703
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
704
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
705
+ # submit to model hub or save the model to share with others
706
+
707
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
708
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
709
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
710
+
711
+ """
712
+ logger.info(f"Extracting fp32 weights")
713
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
714
+
715
+ logger.info(f"Overwriting model with fp32 weights")
716
+ model = model.cpu()
717
+ model.load_state_dict(state_dict, strict=False)
718
+
719
+ return model
720
+
721
+
722
+ if __name__ == "__main__":
723
+ parser = argparse.ArgumentParser()
724
+ parser.add_argument("checkpoint_dir",
725
+ type=str,
726
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
727
+ parser.add_argument("output_dir",
728
+ type=str,
729
+ help="directory to the pytorch fp32 state_dict output files"
730
+ "(e.g. path/checkpoint-12-output/)")
731
+ parser.add_argument(
732
+ "--max_shard_size",
733
+ type=str,
734
+ default="5GB",
735
+ help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
736
+ "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
737
+ "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
738
+ "without CPU OOM issues.")
739
+ parser.add_argument(
740
+ "--safe_serialization",
741
+ default=False,
742
+ action='store_true',
743
+ help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
744
+ parser.add_argument("-t",
745
+ "--tag",
746
+ type=str,
747
+ default=None,
748
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
749
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
750
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
751
+ args = parser.parse_args()
752
+
753
+ debug = args.debug
754
+
755
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
756
+ args.output_dir,
757
+ max_shard_size=args.max_shard_size,
758
+ safe_serialization=args.safe_serialization,
759
+ tag=args.tag,
760
+ exclude_frozen_parameters=args.exclude_frozen_parameters)