fransis3 commited on
Commit
b28efb7
·
verified ·
1 Parent(s): c7b7ac7

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ltg/norbert4-xlarge",
3
+ "architectures": [
4
+ "GptBertForTokenClassification"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "attn_implementation": "flash_attention_2",
8
+ "auto_map": {
9
+ "AutoConfig": "ltg/norbert4-xlarge--configuration_gptbert.GptBertConfig",
10
+ "AutoModel": "ltg/norbert4-xlarge--modeling_gptbert.GptBertModel",
11
+ "AutoModelForCausalLM": "ltg/norbert4-xlarge--modeling_gptbert.GptBertForCausalLM",
12
+ "AutoModelForMaskedLM": "ltg/norbert4-xlarge--modeling_gptbert.GptBertForMaskedLM",
13
+ "AutoModelForMultipleChoice": "ltg/norbert4-xlarge--modeling_gptbert.GptBertForMultipleChoice",
14
+ "AutoModelForQuestionAnswering": "ltg/norbert4-xlarge--modeling_gptbert.GptBertForQuestionAnswering",
15
+ "AutoModelForSequenceClassification": "ltg/norbert4-xlarge--modeling_gptbert.GptBertForSequenceClassification",
16
+ "AutoModelForTokenClassification": "ltg/norbert4-xlarge--modeling_gptbert.GptBertForTokenClassification"
17
+ },
18
+ "bos_token_id": 1,
19
+ "classifier_dropout": 0.2,
20
+ "deterministic_flash_attn": false,
21
+ "embedding_dropout": 0.1,
22
+ "eos_token_id": 2,
23
+ "global_window_length": 8192,
24
+ "hidden_dropout": 0.0,
25
+ "hidden_size": 1536,
26
+ "id2label": {
27
+ "0": "O",
28
+ "1": "B-PER",
29
+ "2": "I-PER",
30
+ "3": "B-ORG",
31
+ "4": "I-ORG",
32
+ "5": "B-LOC",
33
+ "6": "I-LOC",
34
+ "7": "B-GPE_LOC",
35
+ "8": "I-GPE_LOC",
36
+ "9": "B-GPE_ORG",
37
+ "10": "I-GPE_ORG",
38
+ "11": "B-PROD",
39
+ "12": "I-PROD",
40
+ "13": "B-EVT",
41
+ "14": "I-EVT",
42
+ "15": "B-MISC",
43
+ "16": "I-MISC",
44
+ "17": "B-DRV",
45
+ "18": "I-DRV"
46
+ },
47
+ "intermediate_size": 4096,
48
+ "label2id": {
49
+ "B-DRV": 17,
50
+ "B-EVT": 13,
51
+ "B-GPE_LOC": 7,
52
+ "B-GPE_ORG": 9,
53
+ "B-LOC": 5,
54
+ "B-MISC": 15,
55
+ "B-ORG": 3,
56
+ "B-PER": 1,
57
+ "B-PROD": 11,
58
+ "I-DRV": 18,
59
+ "I-EVT": 14,
60
+ "I-GPE_LOC": 8,
61
+ "I-GPE_ORG": 10,
62
+ "I-LOC": 6,
63
+ "I-MISC": 16,
64
+ "I-ORG": 4,
65
+ "I-PER": 2,
66
+ "I-PROD": 12,
67
+ "O": 0
68
+ },
69
+ "layer_norm_eps": 1e-07,
70
+ "local_global_ratio": 4,
71
+ "local_window_length": 256,
72
+ "mask_token_id": 4,
73
+ "max_position_embeddings": 16384,
74
+ "model": "norbert4",
75
+ "num_attention_heads": 24,
76
+ "num_layers": 32,
77
+ "pad_token_id": 3,
78
+ "query_key_head_size": 64,
79
+ "rope_theta": 160000,
80
+ "torch_dtype": "bfloat16",
81
+ "transformers_version": "4.48.0",
82
+ "unk_token_id": 0,
83
+ "use_cache": false,
84
+ "value_head_size": 64,
85
+ "vocab_size": 51200
86
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef11341997194a5d2be19c712abc079c855b64c0e676bdd6e585391d6382d997
3
+ size 1974922998
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<pad>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<special_0>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<special_1>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<special_2>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "<special_3>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "9": {
76
+ "content": "<special_4>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "10": {
84
+ "content": "<special_5>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "11": {
92
+ "content": "<special_6>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "12": {
100
+ "content": "<special_7>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "13": {
108
+ "content": "<special_8>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "14": {
116
+ "content": "<special_9>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "15": {
124
+ "content": "<special_10>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ }
131
+ },
132
+ "bos_token": "<s>",
133
+ "clean_up_tokenization_spaces": false,
134
+ "cls_token": "<s>",
135
+ "eos_token": "</s>",
136
+ "extra_special_tokens": {},
137
+ "mask_token": "<mask>",
138
+ "model_max_length": 1000000000000000019884624838656,
139
+ "pad_token": "<pad>",
140
+ "sep_token": "</s>",
141
+ "tokenizer_class": "PreTrainedTokenizerFast",
142
+ "unk_token": "<unk>"
143
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:974e4d07ba51753cb4ba8084555fbc6157b066fc53995f0a6e44ef67508a1b0d
3
+ size 5777