TheNewPing commited on
Commit
cc27725
1 Parent(s): f5f6421

Model save

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ entity_vocab.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: studio-ousia/luke-base
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: luke-base-paper-setup
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # luke-base-paper-setup
15
+
16
+ This model is a fine-tuned version of [studio-ousia/luke-base](https://huggingface.co/studio-ousia/luke-base) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 1e-05
36
+ - train_batch_size: 32
37
+ - eval_batch_size: 32
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-06
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 3
42
+
43
+ ### Framework versions
44
+
45
+ - Transformers 4.36.2
46
+ - Pytorch 2.1.0+cu121
47
+ - Datasets 2.16.1
48
+ - Tokenizers 0.15.0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<ent2>": 50266,
3
+ "<ent>": 50265
4
+ }
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "studio-ousia/luke-base",
3
+ "architectures": [
4
+ "LukeForMultipleChoice"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bert_model_name": "roberta-base",
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": null,
10
+ "entity_emb_size": 256,
11
+ "entity_vocab_size": 500000,
12
+ "eos_token_id": 2,
13
+ "gradient_checkpointing": false,
14
+ "hidden_act": "gelu",
15
+ "hidden_dropout_prob": 0.1,
16
+ "hidden_size": 768,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "layer_norm_eps": 1e-05,
20
+ "max_position_embeddings": 514,
21
+ "model_type": "luke",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "output_past": true,
25
+ "pad_token_id": 1,
26
+ "position_embedding_type": "absolute",
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.36.2",
29
+ "type_vocab_size": 1,
30
+ "use_cache": true,
31
+ "use_entity_aware_attention": true,
32
+ "vocab_size": 50267
33
+ }
entity_vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72f741e7347ec41a9f27909eb042dbe0d830be3f9c8d201d46e790ceafc07e32
3
+ size 16161138
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f88e4d5b3ffd43b98a8d197a423219956df96e4c2ddc7ba505b0f47c9a794f69
3
+ size 1098044764
special_tokens_map.json ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<ent>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<ent2>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<ent>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<ent2>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ ],
32
+ "bos_token": {
33
+ "content": "<s>",
34
+ "lstrip": false,
35
+ "normalized": true,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "cls_token": {
40
+ "content": "<s>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "eos_token": {
47
+ "content": "</s>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "mask_token": {
54
+ "content": "<mask>",
55
+ "lstrip": true,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false
59
+ },
60
+ "pad_token": {
61
+ "content": "<pad>",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ },
67
+ "sep_token": {
68
+ "content": "</s>",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false
73
+ },
74
+ "unk_token": {
75
+ "content": "<unk>",
76
+ "lstrip": false,
77
+ "normalized": true,
78
+ "rstrip": false,
79
+ "single_word": false
80
+ }
81
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "50265": {
45
+ "content": "<ent>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "50266": {
53
+ "content": "<ent2>",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ }
60
+ },
61
+ "additional_special_tokens": [
62
+ "<ent>",
63
+ "<ent2>",
64
+ "<ent>",
65
+ "<ent2>"
66
+ ],
67
+ "bos_token": "<s>",
68
+ "clean_up_tokenization_spaces": true,
69
+ "cls_token": "<s>",
70
+ "entity_mask2_token": "[MASK2]",
71
+ "entity_mask_token": "[MASK]",
72
+ "entity_pad_token": "[PAD]",
73
+ "entity_token_1": "<ent>",
74
+ "entity_token_2": "<ent2>",
75
+ "entity_unk_token": "[UNK]",
76
+ "eos_token": "</s>",
77
+ "errors": "replace",
78
+ "mask_token": "<mask>",
79
+ "max_entity_length": 32,
80
+ "max_mention_length": 30,
81
+ "model_max_length": 512,
82
+ "pad_token": "<pad>",
83
+ "sep_token": "</s>",
84
+ "task": null,
85
+ "tokenizer_class": "LukeTokenizer",
86
+ "unk_token": "<unk>"
87
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:078e9d9875da62cb6c82f431a671419537f1c0c8f29f9db74de29d5d94578dc8
3
+ size 4728
vocab.json ADDED
The diff for this file is too large to render. See raw diff