DavidNguyen commited on
Commit
020e381
1 Parent(s): 2cb7113

17a563584f6c8f89748033d2039480af485e6221ccbb170942bb35a5eecd0531

Browse files
sft_full/smoe_cosinegating/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_full/smoe_cosinegating/config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/cm/archive/namnv78/checkpoints/phi3mini-clip/pft",
3
+ "architectures": [
4
+ "LlavaPhiForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
10
+ "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
11
+ },
12
+ "balance_loss_coef": 0.1,
13
+ "bos_token_id": 1,
14
+ "clip_smoe": true,
15
+ "dropout": false,
16
+ "embd_pdrop": 0.0,
17
+ "eos_token_id": 32000,
18
+ "freeze_mm_mlp_adapter": false,
19
+ "hidden_act": "silu",
20
+ "hidden_size": 3072,
21
+ "image_aspect_ratio": "pad",
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 8192,
24
+ "local_rank": 0,
25
+ "max_position_embeddings": 4096,
26
+ "mlp_smoe": true,
27
+ "mm_hidden_size": 1024,
28
+ "mm_patch_merge_type": "flat",
29
+ "mm_projector_lr": null,
30
+ "mm_projector_type": "moe",
31
+ "mm_use_im_patch_token": false,
32
+ "mm_use_im_start_end": false,
33
+ "mm_vision_select_feature": "patch",
34
+ "mm_vision_select_layer": -2,
35
+ "mm_vision_tower": "openai/clip-vit-large-patch14-336",
36
+ "model_type": "llava_phi",
37
+ "moe_name": "smoe_cosinegating",
38
+ "num_attention_heads": 32,
39
+ "num_experts": 4,
40
+ "num_hidden_layers": 32,
41
+ "num_key_value_heads": 32,
42
+ "num_layers": 3,
43
+ "num_selected": 2,
44
+ "original_max_position_embeddings": 4096,
45
+ "pad_token_id": 32000,
46
+ "resid_pdrop": 0.0,
47
+ "rms_norm_eps": 1e-05,
48
+ "rope_scaling": null,
49
+ "rope_theta": 10000.0,
50
+ "router_z_loss_coef": 0.01,
51
+ "scales": [
52
+ 1,
53
+ 3
54
+ ],
55
+ "sliding_window": 2047,
56
+ "tie_word_embeddings": false,
57
+ "tokenizer_model_max_length": 2048,
58
+ "tokenizer_padding_side": "right",
59
+ "torch_dtype": "bfloat16",
60
+ "training": true,
61
+ "transformers_version": "4.43.0",
62
+ "tune_mm_mlp_adapter": false,
63
+ "use_cache": true,
64
+ "use_mm_proj": true,
65
+ "vocab_size": 32064
66
+ }
sft_full/smoe_cosinegating/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
+ 32000,
7
+ 32001,
8
+ 32007
9
+ ],
10
+ "pad_token_id": 32000,
11
+ "transformers_version": "4.41.2"
12
+ }
sft_full/smoe_cosinegating/model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
sft_full/smoe_cosinegating/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_full/smoe_cosinegating/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
sft_full/smoe_cosinegating/tokenizer_config.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
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": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
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_full/smoe_cosinegating/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
sft_full/smoe_cosinegating/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de6ac1af5861513343a671f52eab01b29a1a3108099f1adf4e8da88eb078174d
3
+ size 8056