DavidNguyen commited on
Commit
13e0c40
·
verified ·
1 Parent(s): f0e286a

Upload folder using huggingface_hub

Browse files
CompeteSMoE/competesmoe_versions/competesmoev28/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
+ }
CompeteSMoE/competesmoe_versions/competesmoev28/config.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "balance_loss_coef": 0.01,
13
+ "bos_token_id": 1,
14
+ "clip_smoe": true,
15
+ "diversity_loss_coef": 0.005,
16
+ "dropout": false,
17
+ "e_loss_coef": 0.001,
18
+ "embd_pdrop": 0.0,
19
+ "entropy_advance_loss": false,
20
+ "eos_token_id": 32000,
21
+ "freeze_backbone": false,
22
+ "freeze_mm_mlp_adapter": false,
23
+ "hidden_act": "silu",
24
+ "hidden_size": 3072,
25
+ "image_aspect_ratio": "pad",
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 8192,
28
+ "local_rank": 0,
29
+ "loss1": "balanceloss",
30
+ "loss2": "zloss",
31
+ "luna": false,
32
+ "max_position_embeddings": 131072,
33
+ "mlp_smoe": true,
34
+ "mm_hidden_size": 1152,
35
+ "mm_patch_merge_type": "flat",
36
+ "mm_projector_lr": null,
37
+ "mm_projector_type": "moe",
38
+ "mm_use_im_patch_token": false,
39
+ "mm_use_im_start_end": false,
40
+ "mm_vision_select_feature": "patch",
41
+ "mm_vision_select_layer": -2,
42
+ "mm_vision_tower": "google/siglip-so400m-patch14-224",
43
+ "model_name_or_path": "/cm/archive/namnv78/checkpoints/phi35-siglip224/pft",
44
+ "model_type": "llava_phi",
45
+ "moe_name": "competesmoev28",
46
+ "normalization": true,
47
+ "num_attention_heads": 32,
48
+ "num_experts": 4,
49
+ "num_hidden_layers": 32,
50
+ "num_key_value_heads": 32,
51
+ "num_layers": 3,
52
+ "num_selected": 2,
53
+ "number_of_previous_tokens": 2,
54
+ "original_max_position_embeddings": 4096,
55
+ "pad_token_id": 32000,
56
+ "pretrain_mm_mlp_adapter": "/cm/archive/namnv78/checkpoints/phi35-siglip224/pft/mm_projector.bin",
57
+ "rate_compete": 0.2,
58
+ "rate_flip": 0.07,
59
+ "resid_pdrop": 0.0,
60
+ "rms_norm_eps": 1e-05,
61
+ "rope_scaling": {
62
+ "long_factor": [
63
+ 1.0800000429153442,
64
+ 1.1100000143051147,
65
+ 1.1399999856948853,
66
+ 1.340000033378601,
67
+ 1.5899999141693115,
68
+ 1.600000023841858,
69
+ 1.6200000047683716,
70
+ 2.620000123977661,
71
+ 3.2300000190734863,
72
+ 3.2300000190734863,
73
+ 4.789999961853027,
74
+ 7.400000095367432,
75
+ 7.700000286102295,
76
+ 9.09000015258789,
77
+ 12.199999809265137,
78
+ 17.670000076293945,
79
+ 24.46000099182129,
80
+ 28.57000160217285,
81
+ 30.420001983642578,
82
+ 30.840002059936523,
83
+ 32.590003967285156,
84
+ 32.93000411987305,
85
+ 42.320003509521484,
86
+ 44.96000289916992,
87
+ 50.340003967285156,
88
+ 50.45000457763672,
89
+ 57.55000305175781,
90
+ 57.93000411987305,
91
+ 58.21000289916992,
92
+ 60.1400032043457,
93
+ 62.61000442504883,
94
+ 62.62000274658203,
95
+ 62.71000289916992,
96
+ 63.1400032043457,
97
+ 63.1400032043457,
98
+ 63.77000427246094,
99
+ 63.93000411987305,
100
+ 63.96000289916992,
101
+ 63.970001220703125,
102
+ 64.02999877929688,
103
+ 64.06999969482422,
104
+ 64.08000183105469,
105
+ 64.12000274658203,
106
+ 64.41000366210938,
107
+ 64.4800033569336,
108
+ 64.51000213623047,
109
+ 64.52999877929688,
110
+ 64.83999633789062
111
+ ],
112
+ "short_factor": [
113
+ 1.0,
114
+ 1.0199999809265137,
115
+ 1.0299999713897705,
116
+ 1.0299999713897705,
117
+ 1.0499999523162842,
118
+ 1.0499999523162842,
119
+ 1.0499999523162842,
120
+ 1.0499999523162842,
121
+ 1.0499999523162842,
122
+ 1.0699999332427979,
123
+ 1.0999999046325684,
124
+ 1.1099998950958252,
125
+ 1.1599998474121094,
126
+ 1.1599998474121094,
127
+ 1.1699998378753662,
128
+ 1.2899998426437378,
129
+ 1.339999794960022,
130
+ 1.679999828338623,
131
+ 1.7899998426437378,
132
+ 1.8199998140335083,
133
+ 1.8499997854232788,
134
+ 1.8799997568130493,
135
+ 1.9099997282028198,
136
+ 1.9399996995925903,
137
+ 1.9899996519088745,
138
+ 2.0199997425079346,
139
+ 2.0199997425079346,
140
+ 2.0199997425079346,
141
+ 2.0199997425079346,
142
+ 2.0199997425079346,
143
+ 2.0199997425079346,
144
+ 2.0299997329711914,
145
+ 2.0299997329711914,
146
+ 2.0299997329711914,
147
+ 2.0299997329711914,
148
+ 2.0299997329711914,
149
+ 2.0299997329711914,
150
+ 2.0299997329711914,
151
+ 2.0299997329711914,
152
+ 2.0299997329711914,
153
+ 2.0799996852874756,
154
+ 2.0899996757507324,
155
+ 2.189999580383301,
156
+ 2.2199995517730713,
157
+ 2.5899994373321533,
158
+ 2.729999542236328,
159
+ 2.749999523162842,
160
+ 2.8399994373321533
161
+ ],
162
+ "type": "longrope"
163
+ },
164
+ "rope_theta": 10000.0,
165
+ "router_loss_coef": 0.01,
166
+ "router_z_loss_coef": 0.001,
167
+ "scales": [
168
+ 1,
169
+ 3
170
+ ],
171
+ "sliding_window": 262144,
172
+ "sparse_upcycling": true,
173
+ "strategy_train": "base",
174
+ "tie_word_embeddings": false,
175
+ "tokenizer_model_max_length": 2048,
176
+ "tokenizer_padding_side": "right",
177
+ "topk_max": 2,
178
+ "topk_min": 1,
179
+ "torch_dtype": "bfloat16",
180
+ "training": true,
181
+ "transformers_version": "4.43.0",
182
+ "tune_mm_mlp_adapter": false,
183
+ "unit_test": true,
184
+ "use_cache": true,
185
+ "use_mm_proj": true,
186
+ "use_old": false,
187
+ "version": "phi35",
188
+ "vision_tower": "google/siglip-so400m-patch14-224",
189
+ "vision_tower_dir": "/cm/archive/namnv78/checkpoints/phi35-siglip224/pft/clip.bin",
190
+ "vocab_size": 32064,
191
+ "warm_up": 0.05
192
+ }
CompeteSMoE/competesmoe_versions/competesmoev28/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
+ }
CompeteSMoE/competesmoe_versions/competesmoev28/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77e9c748e9da9061af66a6f90b1f924ea1ba57c62b6aa1697cfe711335e04cf9
3
+ size 4972489328
CompeteSMoE/competesmoe_versions/competesmoev28/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:819ce517a7ae177d62a05832d6e44f5b5c9cf49ecb4ca41b3ea094ba201bd087
3
+ size 4985754844
CompeteSMoE/competesmoe_versions/competesmoev28/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:040f5f4e5e9b1c1ae54a861281dd637f96adfba846022caaf9a6bb7dc44c06bf
3
+ size 248943552
CompeteSMoE/competesmoe_versions/competesmoev28/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
CompeteSMoE/competesmoe_versions/competesmoev28/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
+ }
CompeteSMoE/competesmoe_versions/competesmoev28/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
CompeteSMoE/competesmoe_versions/competesmoev28/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
+ }
CompeteSMoE/competesmoe_versions/competesmoev28/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
CompeteSMoE/competesmoe_versions/competesmoev28/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96c87ffc67947824737a423ab5193cf37ebe8fb7e13b4abc77c3b6096c6025b1
3
+ size 7928