Hugging Face's logo

AbstractPhil
/
bert-beatrix-2048

Safetensors
nomic_bert
symbolic
classification
text_masking
image_feature
text_feature
experimental
categorical
similarity
teacher
custom_code
Model card Files
xet
Community
AbstractPhil commited on
Commit
14cdead
·
verified ·
1 Parent(s): aa24e48

Upload 12 files

Browse files
Files changed (12) hide show
  1. added_tokens.json +54 -0
  2. config.json +61 -0
  3. configuration_hf_nomic_bert.py +56 -0
  4. model.safetensors +3 -0
  5. optimizer.pt +3 -0
  6. scheduler.pt +3 -0
  7. special_token_ids.json +114 -0
  8. special_tokens_map.json +91 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +533 -0
  11. training_state.json +16 -0
  12. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<accessory>": 30528,
3
+ "<emotion>": 30524,
4
+ "<fabric>": 30544,
5
+ "<footwear>": 30529,
6
+ "<grid>": 30536,
7
+ "<hair_length>": 30532,
8
+ "<hair_style>": 30531,
9
+ "<headwear>": 30533,
10
+ "<intent>": 30542,
11
+ "<jewelry>": 30545,
12
+ "<lighting>": 30526,
13
+ "<material>": 30527,
14
+ "<object_left>": 30539,
15
+ "<object_right>": 30540,
16
+ "<offset>": 30538,
17
+ "<pattern>": 30535,
18
+ "<pose>": 30523,
19
+ "<relation>": 30541,
20
+ "<style>": 30543,
21
+ "<subject1>": 30546,
22
+ "<subject2>": 30547,
23
+ "<subject>": 30522,
24
+ "<surface>": 30525,
25
+ "<texture>": 30534,
26
+ "<upper_body_clothing>": 30530,
27
+ "<zone>": 30537,
28
+ "[SHUNT_1000000]": 30548,
29
+ "[SHUNT_1000001]": 30549,
30
+ "[SHUNT_1000002]": 30550,
31
+ "[SHUNT_1000003]": 30551,
32
+ "[SHUNT_1000004]": 30552,
33
+ "[SHUNT_1000005]": 30553,
34
+ "[SHUNT_1000006]": 30554,
35
+ "[SHUNT_1000007]": 30555,
36
+ "[SHUNT_1000008]": 30556,
37
+ "[SHUNT_1000009]": 30557,
38
+ "[SHUNT_1000010]": 30558,
39
+ "[SHUNT_1000011]": 30559,
40
+ "[SHUNT_1000012]": 30560,
41
+ "[SHUNT_1000013]": 30561,
42
+ "[SHUNT_1000014]": 30562,
43
+ "[SHUNT_1000015]": 30563,
44
+ "[SHUNT_1000016]": 30564,
45
+ "[SHUNT_1000017]": 30565,
46
+ "[SHUNT_1000018]": 30566,
47
+ "[SHUNT_1000019]": 30567,
48
+ "[SHUNT_1000020]": 30568,
49
+ "[SHUNT_1000021]": 30569,
50
+ "[SHUNT_1000022]": 30570,
51
+ "[SHUNT_1000023]": 30571,
52
+ "[SHUNT_1000024]": 30572,
53
+ "[SHUNT_1000025]": 30573
54
+ }
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "swiglu",
3
+ "architectures": [
4
+ "NomicBertForPreTraining"
5
+ ],
6
+ "attn_pdrop": 0.2,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_hf_nomic_bert.NomicBertConfig",
9
+ "AutoModel": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertModel",
10
+ "AutoModelForMaskedLM": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForPreTraining",
11
+ "AutoModelForMultipleChoice": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForMultipleChoice",
12
+ "AutoModelForQuestionAnswering": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForQuestionAnswering",
13
+ "AutoModelForSequenceClassification": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForSequenceClassification",
14
+ "AutoModelForTokenClassification": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForTokenClassification"
15
+ },
16
+ "bos_token_id": null,
17
+ "causal": false,
18
+ "dense_seq_output": true,
19
+ "embd_pdrop": 0.2,
20
+ "eos_token_id": null,
21
+ "fused_bias_fc": true,
22
+ "fused_dropout_add_ln": true,
23
+ "initializer_range": 0.02,
24
+ "layer_norm_epsilon": 1e-12,
25
+ "max_trained_positions": 2048,
26
+ "mlp_fc1_bias": false,
27
+ "mlp_fc2_bias": false,
28
+ "model_type": "nomic_bert",
29
+ "n_embd": 768,
30
+ "n_head": 12,
31
+ "n_inner": 3072,
32
+ "n_layer": 12,
33
+ "n_positions": 2048,
34
+ "pad_vocab_size_multiple": 64,
35
+ "parallel_block": false,
36
+ "parallel_block_tied_norm": false,
37
+ "prenorm": false,
38
+ "qkv_proj_bias": false,
39
+ "reorder_and_upcast_attn": false,
40
+ "resid_pdrop": 0.2,
41
+ "rotary_emb_base": 1000,
42
+ "rotary_emb_fraction": 1.0,
43
+ "rotary_emb_interleaved": false,
44
+ "rotary_emb_scale_base": null,
45
+ "rotary_scaling_factor": null,
46
+ "scale_attn_by_inverse_layer_idx": false,
47
+ "scale_attn_weights": true,
48
+ "summary_activation": null,
49
+ "summary_first_dropout": 0.2,
50
+ "summary_proj_to_labels": true,
51
+ "summary_type": "cls_index",
52
+ "summary_use_proj": true,
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.52.2",
55
+ "type_vocab_size": 2,
56
+ "use_cache": true,
57
+ "use_flash_attn": true,
58
+ "use_rms_norm": false,
59
+ "use_xentropy": true,
60
+ "vocab_size": 30592
61
+ }
configuration_hf_nomic_bert.py ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from transformers import GPT2Config
2
+
3
+
4
+ class NomicBertConfig(GPT2Config):
5
+ model_type = "nomic_bert"
6
+
7
+ def __init__(
8
+ self,
9
+ prenorm=False,
10
+ parallel_block=False,
11
+ parallel_block_tied_norm=False,
12
+ rotary_emb_fraction=0.0,
13
+ fused_dropout_add_ln=False,
14
+ fused_bias_fc=False,
15
+ use_flash_attn=False,
16
+ use_xentropy=False,
17
+ qkv_proj_bias=True,
18
+ rotary_emb_base=10_000,
19
+ rotary_emb_scale_base=None,
20
+ rotary_emb_interleaved=False,
21
+ mlp_fc1_bias=True,
22
+ mlp_fc2_bias=True,
23
+ use_rms_norm=False,
24
+ causal=False,
25
+ type_vocab_size=2,
26
+ dense_seq_output=True,
27
+ pad_vocab_size_multiple=1,
28
+ tie_word_embeddings=True,
29
+ rotary_scaling_factor=None,
30
+ max_trained_positions=2048,
31
+ **kwargs,
32
+ ):
33
+ self.prenorm = prenorm
34
+ self.parallel_block = parallel_block
35
+ self.parallel_block_tied_norm = parallel_block_tied_norm
36
+ self.rotary_emb_fraction = rotary_emb_fraction
37
+ self.tie_word_embeddings = tie_word_embeddings
38
+ self.fused_dropout_add_ln = fused_dropout_add_ln
39
+ self.fused_bias_fc = fused_bias_fc
40
+ self.use_flash_attn = use_flash_attn
41
+ self.use_xentropy = use_xentropy
42
+ self.qkv_proj_bias = qkv_proj_bias
43
+ self.rotary_emb_base = rotary_emb_base
44
+ self.rotary_emb_scale_base = rotary_emb_scale_base
45
+ self.rotary_emb_interleaved = rotary_emb_interleaved
46
+ self.mlp_fc1_bias = mlp_fc1_bias
47
+ self.mlp_fc2_bias = mlp_fc2_bias
48
+ self.use_rms_norm = use_rms_norm
49
+ self.causal = causal
50
+ self.type_vocab_size = type_vocab_size
51
+ self.dense_seq_output = dense_seq_output
52
+ self.pad_vocab_size_multiple = pad_vocab_size_multiple
53
+ self.rotary_scaling_factor = rotary_scaling_factor
54
+ self.max_trained_positions = max_trained_positions
55
+
56
+ super().__init__(**kwargs)
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:472f7fd9e4123cf8c171bbbfa296fad7bc1230b97e2d3522decc01a921a25098
3
+ size 549501112
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:649b5eaf2360b3c1c1bb54ec0cf3a9d80d8e315ed062a2f98401f7aa931fd936
3
+ size 1099075450
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7caa9af73ead4dcab8719bfe1807fc0bd4ca62f37a68f298abeb53456103ad34
3
+ size 1256
special_token_ids.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "symbolic_token_ids": {
3
+ "<subject>": 30522,
4
+ "<subject1>": 30546,
5
+ "<subject2>": 30547,
6
+ "<pose>": 30523,
7
+ "<emotion>": 30524,
8
+ "<surface>": 30525,
9
+ "<lighting>": 30526,
10
+ "<material>": 30527,
11
+ "<accessory>": 30528,
12
+ "<footwear>": 30529,
13
+ "<upper_body_clothing>": 30530,
14
+ "<hair_style>": 30531,
15
+ "<hair_length>": 30532,
16
+ "<headwear>": 30533,
17
+ "<texture>": 30534,
18
+ "<pattern>": 30535,
19
+ "<grid>": 30536,
20
+ "<zone>": 30537,
21
+ "<offset>": 30538,
22
+ "<object_left>": 30539,
23
+ "<object_right>": 30540,
24
+ "<relation>": 30541,
25
+ "<intent>": 30542,
26
+ "<style>": 30543,
27
+ "<fabric>": 30544,
28
+ "<jewelry>": 30545
29
+ },
30
+ "shunt_token_ids": {
31
+ "[SHUNT_1000000]": 30548,
32
+ "[SHUNT_1000001]": 30549,
33
+ "[SHUNT_1000002]": 30550,
34
+ "[SHUNT_1000003]": 30551,
35
+ "[SHUNT_1000004]": 30552,
36
+ "[SHUNT_1000005]": 30553,
37
+ "[SHUNT_1000006]": 30554,
38
+ "[SHUNT_1000007]": 30555,
39
+ "[SHUNT_1000008]": 30556,
40
+ "[SHUNT_1000009]": 30557,
41
+ "[SHUNT_1000010]": 30558,
42
+ "[SHUNT_1000011]": 30559,
43
+ "[SHUNT_1000012]": 30560,
44
+ "[SHUNT_1000013]": 30561,
45
+ "[SHUNT_1000014]": 30562,
46
+ "[SHUNT_1000015]": 30563,
47
+ "[SHUNT_1000016]": 30564,
48
+ "[SHUNT_1000017]": 30565,
49
+ "[SHUNT_1000018]": 30566,
50
+ "[SHUNT_1000019]": 30567,
51
+ "[SHUNT_1000020]": 30568,
52
+ "[SHUNT_1000021]": 30569,
53
+ "[SHUNT_1000022]": 30570,
54
+ "[SHUNT_1000023]": 30571,
55
+ "[SHUNT_1000024]": 30572,
56
+ "[SHUNT_1000025]": 30573
57
+ },
58
+ "symbolic_tokens": [
59
+ "<subject>",
60
+ "<subject1>",
61
+ "<subject2>",
62
+ "<pose>",
63
+ "<emotion>",
64
+ "<surface>",
65
+ "<lighting>",
66
+ "<material>",
67
+ "<accessory>",
68
+ "<footwear>",
69
+ "<upper_body_clothing>",
70
+ "<hair_style>",
71
+ "<hair_length>",
72
+ "<headwear>",
73
+ "<texture>",
74
+ "<pattern>",
75
+ "<grid>",
76
+ "<zone>",
77
+ "<offset>",
78
+ "<object_left>",
79
+ "<object_right>",
80
+ "<relation>",
81
+ "<intent>",
82
+ "<style>",
83
+ "<fabric>",
84
+ "<jewelry>"
85
+ ],
86
+ "shunt_tokens": [
87
+ "[SHUNT_1000000]",
88
+ "[SHUNT_1000001]",
89
+ "[SHUNT_1000002]",
90
+ "[SHUNT_1000003]",
91
+ "[SHUNT_1000004]",
92
+ "[SHUNT_1000005]",
93
+ "[SHUNT_1000006]",
94
+ "[SHUNT_1000007]",
95
+ "[SHUNT_1000008]",
96
+ "[SHUNT_1000009]",
97
+ "[SHUNT_1000010]",
98
+ "[SHUNT_1000011]",
99
+ "[SHUNT_1000012]",
100
+ "[SHUNT_1000013]",
101
+ "[SHUNT_1000014]",
102
+ "[SHUNT_1000015]",
103
+ "[SHUNT_1000016]",
104
+ "[SHUNT_1000017]",
105
+ "[SHUNT_1000018]",
106
+ "[SHUNT_1000019]",
107
+ "[SHUNT_1000020]",
108
+ "[SHUNT_1000021]",
109
+ "[SHUNT_1000022]",
110
+ "[SHUNT_1000023]",
111
+ "[SHUNT_1000024]",
112
+ "[SHUNT_1000025]"
113
+ ]
114
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<subject>",
4
+ "<pose>",
5
+ "<emotion>",
6
+ "<surface>",
7
+ "<lighting>",
8
+ "<material>",
9
+ "<accessory>",
10
+ "<footwear>",
11
+ "<upper_body_clothing>",
12
+ "<hair_style>",
13
+ "<hair_length>",
14
+ "<headwear>",
15
+ "<texture>",
16
+ "<pattern>",
17
+ "<grid>",
18
+ "<zone>",
19
+ "<offset>",
20
+ "<object_left>",
21
+ "<object_right>",
22
+ "<relation>",
23
+ "<intent>",
24
+ "<style>",
25
+ "<fabric>",
26
+ "<jewelry>",
27
+ "<subject1>",
28
+ "<subject2>",
29
+ "[SHUNT_1000000]",
30
+ "[SHUNT_1000001]",
31
+ "[SHUNT_1000002]",
32
+ "[SHUNT_1000003]",
33
+ "[SHUNT_1000004]",
34
+ "[SHUNT_1000005]",
35
+ "[SHUNT_1000006]",
36
+ "[SHUNT_1000007]",
37
+ "[SHUNT_1000008]",
38
+ "[SHUNT_1000009]",
39
+ "[SHUNT_1000010]",
40
+ "[SHUNT_1000011]",
41
+ "[SHUNT_1000012]",
42
+ "[SHUNT_1000013]",
43
+ "[SHUNT_1000014]",
44
+ "[SHUNT_1000015]",
45
+ "[SHUNT_1000016]",
46
+ "[SHUNT_1000017]",
47
+ "[SHUNT_1000018]",
48
+ "[SHUNT_1000019]",
49
+ "[SHUNT_1000020]",
50
+ "[SHUNT_1000021]",
51
+ "[SHUNT_1000022]",
52
+ "[SHUNT_1000023]",
53
+ "[SHUNT_1000024]",
54
+ "[SHUNT_1000025]"
55
+ ],
56
+ "cls_token": {
57
+ "content": "[CLS]",
58
+ "lstrip": false,
59
+ "normalized": false,
60
+ "rstrip": false,
61
+ "single_word": false
62
+ },
63
+ "mask_token": {
64
+ "content": "[MASK]",
65
+ "lstrip": false,
66
+ "normalized": false,
67
+ "rstrip": false,
68
+ "single_word": false
69
+ },
70
+ "pad_token": {
71
+ "content": "[PAD]",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false
76
+ },
77
+ "sep_token": {
78
+ "content": "[SEP]",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false
83
+ },
84
+ "unk_token": {
85
+ "content": "[UNK]",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false
90
+ }
91
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,533 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30522": {
44
+ "content": "<subject>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "30523": {
52
+ "content": "<pose>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "30524": {
60
+ "content": "<emotion>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "30525": {
68
+ "content": "<surface>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "30526": {
76
+ "content": "<lighting>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "30527": {
84
+ "content": "<material>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "30528": {
92
+ "content": "<accessory>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "30529": {
100
+ "content": "<footwear>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "30530": {
108
+ "content": "<upper_body_clothing>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "30531": {
116
+ "content": "<hair_style>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "30532": {
124
+ "content": "<hair_length>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "30533": {
132
+ "content": "<headwear>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "30534": {
140
+ "content": "<texture>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "30535": {
148
+ "content": "<pattern>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "30536": {
156
+ "content": "<grid>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "30537": {
164
+ "content": "<zone>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "30538": {
172
+ "content": "<offset>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "30539": {
180
+ "content": "<object_left>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "30540": {
188
+ "content": "<object_right>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "30541": {
196
+ "content": "<relation>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "30542": {
204
+ "content": "<intent>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "30543": {
212
+ "content": "<style>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "30544": {
220
+ "content": "<fabric>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "30545": {
228
+ "content": "<jewelry>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "30546": {
236
+ "content": "<subject1>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "30547": {
244
+ "content": "<subject2>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "30548": {
252
+ "content": "[SHUNT_1000000]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "30549": {
260
+ "content": "[SHUNT_1000001]",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "30550": {
268
+ "content": "[SHUNT_1000002]",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "30551": {
276
+ "content": "[SHUNT_1000003]",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "30552": {
284
+ "content": "[SHUNT_1000004]",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "30553": {
292
+ "content": "[SHUNT_1000005]",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "30554": {
300
+ "content": "[SHUNT_1000006]",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "30555": {
308
+ "content": "[SHUNT_1000007]",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "30556": {
316
+ "content": "[SHUNT_1000008]",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "30557": {
324
+ "content": "[SHUNT_1000009]",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "30558": {
332
+ "content": "[SHUNT_1000010]",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "30559": {
340
+ "content": "[SHUNT_1000011]",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "30560": {
348
+ "content": "[SHUNT_1000012]",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "30561": {
356
+ "content": "[SHUNT_1000013]",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "30562": {
364
+ "content": "[SHUNT_1000014]",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "30563": {
372
+ "content": "[SHUNT_1000015]",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "30564": {
380
+ "content": "[SHUNT_1000016]",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "30565": {
388
+ "content": "[SHUNT_1000017]",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "30566": {
396
+ "content": "[SHUNT_1000018]",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "30567": {
404
+ "content": "[SHUNT_1000019]",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "30568": {
412
+ "content": "[SHUNT_1000020]",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "30569": {
420
+ "content": "[SHUNT_1000021]",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "30570": {
428
+ "content": "[SHUNT_1000022]",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "30571": {
436
+ "content": "[SHUNT_1000023]",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "30572": {
444
+ "content": "[SHUNT_1000024]",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "30573": {
452
+ "content": "[SHUNT_1000025]",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ }
459
+ },
460
+ "additional_special_tokens": [
461
+ "<subject>",
462
+ "<pose>",
463
+ "<emotion>",
464
+ "<surface>",
465
+ "<lighting>",
466
+ "<material>",
467
+ "<accessory>",
468
+ "<footwear>",
469
+ "<upper_body_clothing>",
470
+ "<hair_style>",
471
+ "<hair_length>",
472
+ "<headwear>",
473
+ "<texture>",
474
+ "<pattern>",
475
+ "<grid>",
476
+ "<zone>",
477
+ "<offset>",
478
+ "<object_left>",
479
+ "<object_right>",
480
+ "<relation>",
481
+ "<intent>",
482
+ "<style>",
483
+ "<fabric>",
484
+ "<jewelry>",
485
+ "<subject1>",
486
+ "<subject2>",
487
+ "[SHUNT_1000000]",
488
+ "[SHUNT_1000001]",
489
+ "[SHUNT_1000002]",
490
+ "[SHUNT_1000003]",
491
+ "[SHUNT_1000004]",
492
+ "[SHUNT_1000005]",
493
+ "[SHUNT_1000006]",
494
+ "[SHUNT_1000007]",
495
+ "[SHUNT_1000008]",
496
+ "[SHUNT_1000009]",
497
+ "[SHUNT_1000010]",
498
+ "[SHUNT_1000011]",
499
+ "[SHUNT_1000012]",
500
+ "[SHUNT_1000013]",
501
+ "[SHUNT_1000014]",
502
+ "[SHUNT_1000015]",
503
+ "[SHUNT_1000016]",
504
+ "[SHUNT_1000017]",
505
+ "[SHUNT_1000018]",
506
+ "[SHUNT_1000019]",
507
+ "[SHUNT_1000020]",
508
+ "[SHUNT_1000021]",
509
+ "[SHUNT_1000022]",
510
+ "[SHUNT_1000023]",
511
+ "[SHUNT_1000024]",
512
+ "[SHUNT_1000025]"
513
+ ],
514
+ "clean_up_tokenization_spaces": true,
515
+ "cls_token": "[CLS]",
516
+ "do_lower_case": true,
517
+ "extra_special_tokens": {},
518
+ "mask_token": "[MASK]",
519
+ "max_length": 77,
520
+ "model_max_length": 8192,
521
+ "pad_to_multiple_of": null,
522
+ "pad_token": "[PAD]",
523
+ "pad_token_type_id": 0,
524
+ "padding_side": "right",
525
+ "sep_token": "[SEP]",
526
+ "stride": 0,
527
+ "strip_accents": null,
528
+ "tokenize_chinese_chars": true,
529
+ "tokenizer_class": "BertTokenizer",
530
+ "truncation_side": "right",
531
+ "truncation_strategy": "longest_first",
532
+ "unk_token": "[UNK]"
533
+ }
training_state.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "step": 248000,
3
+ "epoch": 13,
4
+ "vocab_size": 30574,
5
+ "model_vocab_size": 30592,
6
+ "config": {
7
+ "optimizer_type": "adamw",
8
+ "lr": 2e-05,
9
+ "weight_decay": 0.01,
10
+ "warmup_steps": 8000,
11
+ "scheduler_type": "cosine",
12
+ "scheduler_params": {
13
+ "eta_min": 1e-07
14
+ }
15
+ }
16
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff