Upload folder using huggingface_hub

#182
.gitattributes CHANGED
@@ -339,3 +339,4 @@ sft/1M3/Full_smoe/checkpoint-13786/logs/0627_1209_llava...l_mme_llava_model_args
339
  sft/1M3/Full_smoe/checkpoint-13786/logs/0627_1209_llava...l_mme_llava_model_args_8d283e/mmerealworld_lite.json filter=lfs diff=lfs merge=lfs -text
340
  sft/1M3/Full_smoe/checkpoint-13786/logs/0627_1209_llava...l_mme_llava_model_args_8d283e/submissions/mmbench_en_dev_results.xlsx filter=lfs diff=lfs merge=lfs -text
341
  sft/1M3/Full_smoe/checkpoint-13786/logs/0627_1209_llava...l_mme_llava_model_args_8d283e/textvqa_val.json filter=lfs diff=lfs merge=lfs -text
 
 
339
  sft/1M3/Full_smoe/checkpoint-13786/logs/0627_1209_llava...l_mme_llava_model_args_8d283e/mmerealworld_lite.json filter=lfs diff=lfs merge=lfs -text
340
  sft/1M3/Full_smoe/checkpoint-13786/logs/0627_1209_llava...l_mme_llava_model_args_8d283e/submissions/mmbench_en_dev_results.xlsx filter=lfs diff=lfs merge=lfs -text
341
  sft/1M3/Full_smoe/checkpoint-13786/logs/0627_1209_llava...l_mme_llava_model_args_8d283e/textvqa_val.json filter=lfs diff=lfs merge=lfs -text
342
+ sft/revise_Full_smoe_perturbed/trainer_state.json filter=lfs diff=lfs merge=lfs -text
sft/revise_Full_smoe_perturbed/added_tokens.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|assistant|>": 32001,
3
+ "<|endoftext|>": 32000,
4
+ "<|end|>": 32007,
5
+ "<|placeholder1|>": 32002,
6
+ "<|placeholder2|>": 32003,
7
+ "<|placeholder3|>": 32004,
8
+ "<|placeholder4|>": 32005,
9
+ "<|placeholder5|>": 32008,
10
+ "<|placeholder6|>": 32009,
11
+ "<|system|>": 32006,
12
+ "<|user|>": 32010
13
+ }
sft/revise_Full_smoe_perturbed/config.json ADDED
@@ -0,0 +1,200 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/cm/archive/namnv78/checkpoints/phi35-siglip224/pft",
3
+ "architectures": [
4
+ "LlavaPhiForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "configuration_phi3.Phi3Config",
10
+ "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
11
+ },
12
+ "bal_comp_loss_coef": 0.01,
13
+ "balance_loss_coef": 0.01,
14
+ "bos_token_id": 1,
15
+ "clip_smoe": true,
16
+ "diversity_loss_coef": 0.01,
17
+ "dropout": false,
18
+ "e_loss_coef": 0.001,
19
+ "embd_pdrop": 0.0,
20
+ "entropy_advance_loss": false,
21
+ "eos_token_id": 32000,
22
+ "freeze_backbone": false,
23
+ "freeze_mm_mlp_adapter": false,
24
+ "hidden_act": "silu",
25
+ "hidden_size": 3072,
26
+ "hybrid": false,
27
+ "image_aspect_ratio": "pad",
28
+ "init_weight": true,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 8192,
31
+ "is_cosine": false,
32
+ "is_norm_weight": false,
33
+ "local_rank": 0,
34
+ "loss1": "balanceloss",
35
+ "loss2": "zloss",
36
+ "luna": false,
37
+ "max_compete_in_iter": 3,
38
+ "max_position_embeddings": 131072,
39
+ "mlp_smoe": true,
40
+ "mm_hidden_size": 1152,
41
+ "mm_patch_merge_type": "flat",
42
+ "mm_projector_lr": null,
43
+ "mm_projector_type": "moe",
44
+ "mm_use_im_patch_token": false,
45
+ "mm_use_im_start_end": false,
46
+ "mm_vision_select_feature": "patch",
47
+ "mm_vision_select_layer": -2,
48
+ "mm_vision_tower": "google/siglip-so400m-patch14-224",
49
+ "model_name_or_path": "/cm/archive/namnv78/checkpoints/phi35-siglip224/pft",
50
+ "model_type": "llava_phi",
51
+ "moe_name": "smoe_perturbed",
52
+ "norm_softmax": false,
53
+ "normalization": true,
54
+ "num_attention_heads": 32,
55
+ "num_experts": 4,
56
+ "num_hidden_layers": 32,
57
+ "num_key_value_heads": 32,
58
+ "num_layers": 3,
59
+ "num_selected": 2,
60
+ "number_of_previous_tokens": 2,
61
+ "original_max_position_embeddings": 4096,
62
+ "pad_token_id": 32000,
63
+ "pretrain_mm_mlp_adapter": "/cm/archive/namnv78/checkpoints/phi35-siglip224/pft/mm_projector.bin",
64
+ "rate_compete": 0.2,
65
+ "rate_flip": 0.05,
66
+ "resid_pdrop": 0.0,
67
+ "rms_norm_eps": 1e-05,
68
+ "rope_scaling": {
69
+ "long_factor": [
70
+ 1.0800000429153442,
71
+ 1.1100000143051147,
72
+ 1.1399999856948853,
73
+ 1.340000033378601,
74
+ 1.5899999141693115,
75
+ 1.600000023841858,
76
+ 1.6200000047683716,
77
+ 2.620000123977661,
78
+ 3.2300000190734863,
79
+ 3.2300000190734863,
80
+ 4.789999961853027,
81
+ 7.400000095367432,
82
+ 7.700000286102295,
83
+ 9.09000015258789,
84
+ 12.199999809265137,
85
+ 17.670000076293945,
86
+ 24.46000099182129,
87
+ 28.57000160217285,
88
+ 30.420001983642578,
89
+ 30.840002059936523,
90
+ 32.590003967285156,
91
+ 32.93000411987305,
92
+ 42.320003509521484,
93
+ 44.96000289916992,
94
+ 50.340003967285156,
95
+ 50.45000457763672,
96
+ 57.55000305175781,
97
+ 57.93000411987305,
98
+ 58.21000289916992,
99
+ 60.1400032043457,
100
+ 62.61000442504883,
101
+ 62.62000274658203,
102
+ 62.71000289916992,
103
+ 63.1400032043457,
104
+ 63.1400032043457,
105
+ 63.77000427246094,
106
+ 63.93000411987305,
107
+ 63.96000289916992,
108
+ 63.970001220703125,
109
+ 64.02999877929688,
110
+ 64.06999969482422,
111
+ 64.08000183105469,
112
+ 64.12000274658203,
113
+ 64.41000366210938,
114
+ 64.4800033569336,
115
+ 64.51000213623047,
116
+ 64.52999877929688,
117
+ 64.83999633789062
118
+ ],
119
+ "short_factor": [
120
+ 1.0,
121
+ 1.0199999809265137,
122
+ 1.0299999713897705,
123
+ 1.0299999713897705,
124
+ 1.0499999523162842,
125
+ 1.0499999523162842,
126
+ 1.0499999523162842,
127
+ 1.0499999523162842,
128
+ 1.0499999523162842,
129
+ 1.0699999332427979,
130
+ 1.0999999046325684,
131
+ 1.1099998950958252,
132
+ 1.1599998474121094,
133
+ 1.1599998474121094,
134
+ 1.1699998378753662,
135
+ 1.2899998426437378,
136
+ 1.339999794960022,
137
+ 1.679999828338623,
138
+ 1.7899998426437378,
139
+ 1.8199998140335083,
140
+ 1.8499997854232788,
141
+ 1.8799997568130493,
142
+ 1.9099997282028198,
143
+ 1.9399996995925903,
144
+ 1.9899996519088745,
145
+ 2.0199997425079346,
146
+ 2.0199997425079346,
147
+ 2.0199997425079346,
148
+ 2.0199997425079346,
149
+ 2.0199997425079346,
150
+ 2.0199997425079346,
151
+ 2.0299997329711914,
152
+ 2.0299997329711914,
153
+ 2.0299997329711914,
154
+ 2.0299997329711914,
155
+ 2.0299997329711914,
156
+ 2.0299997329711914,
157
+ 2.0299997329711914,
158
+ 2.0299997329711914,
159
+ 2.0299997329711914,
160
+ 2.0799996852874756,
161
+ 2.0899996757507324,
162
+ 2.189999580383301,
163
+ 2.2199995517730713,
164
+ 2.5899994373321533,
165
+ 2.729999542236328,
166
+ 2.749999523162842,
167
+ 2.8399994373321533
168
+ ],
169
+ "type": "longrope"
170
+ },
171
+ "rope_theta": 10000.0,
172
+ "router_loss_coef": 0.01,
173
+ "router_theta": 0.1,
174
+ "router_z_loss_coef": 0.001,
175
+ "scales": [
176
+ 1,
177
+ 3
178
+ ],
179
+ "sliding_window": 262144,
180
+ "sparse_upcycling": true,
181
+ "strategy_train": "base",
182
+ "tie_word_embeddings": false,
183
+ "tokenizer_model_max_length": 2048,
184
+ "tokenizer_padding_side": "right",
185
+ "topk_max": 2,
186
+ "topk_min": 1,
187
+ "torch_dtype": "bfloat16",
188
+ "training": true,
189
+ "transformers_version": "4.43.0",
190
+ "tune_mm_mlp_adapter": false,
191
+ "unit_test": true,
192
+ "use_cache": true,
193
+ "use_mm_proj": true,
194
+ "use_old": false,
195
+ "version": "phi35",
196
+ "vision_tower": "google/siglip-so400m-patch14-224",
197
+ "vision_tower_dir": "/cm/archive/namnv78/checkpoints/phi35-siglip224/pft/clip.bin",
198
+ "vocab_size": 32064,
199
+ "warm_up": 0.05
200
+ }
sft/revise_Full_smoe_perturbed/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 32007,
7
+ 32001,
8
+ 32000
9
+ ],
10
+ "pad_token_id": 32000,
11
+ "transformers_version": "4.43.0"
12
+ }
sft/revise_Full_smoe_perturbed/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b7dc636565fa9baf66e44039e78b47f01cd1f5eb916a8890d7eb6cb3e6bb3f0
3
+ size 4972489328
sft/revise_Full_smoe_perturbed/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf79379bb2e091adae93ebb1ec101c723c80566c4fb494221692ea2af6adcc30
3
+ size 4985662816
sft/revise_Full_smoe_perturbed/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fc745f3b52c7c45e114fe5f43b1a7bc0c7e3f9bca54360fb25f2c26b87c20b3
3
+ size 248952888
sft/revise_Full_smoe_perturbed/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
sft/revise_Full_smoe_perturbed/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
sft/revise_Full_smoe_perturbed/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
sft/revise_Full_smoe_perturbed/tokenizer_config.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ }
118
+ },
119
+ "bos_token": "<s>",
120
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
121
+ "clean_up_tokenization_spaces": false,
122
+ "eos_token": "<|endoftext|>",
123
+ "legacy": false,
124
+ "model_max_length": 2048,
125
+ "pad_token": "<unk>",
126
+ "padding_side": "right",
127
+ "sp_model_kwargs": {},
128
+ "spaces_between_special_tokens": false,
129
+ "tokenizer_class": "LlamaTokenizer",
130
+ "unk_token": "<unk>",
131
+ "use_default_system_prompt": false
132
+ }
sft/revise_Full_smoe_perturbed/trainer_state.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd664991a8b743e1af45a3a0d372bdd36e27ef03a933e5af3ae00981d0e68613
3
+ size 10537381
sft/revise_Full_smoe_perturbed/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42138134460c59fb9d227d1f4f3ded04a4b2a23343452019b3c3f578510208e1
3
+ size 7992