ikuyamada commited on
Commit
4649112
1 Parent(s): 70d02d3

First version of the luke-base model and tokenizer.

Browse files
.gitattributes CHANGED
@@ -14,3 +14,4 @@
14
  *.pb filter=lfs diff=lfs merge=lfs -text
15
  *.pt filter=lfs diff=lfs merge=lfs -text
16
  *.pth filter=lfs diff=lfs merge=lfs -text
 
 
14
  *.pb filter=lfs diff=lfs merge=lfs -text
15
  *.pt filter=lfs diff=lfs merge=lfs -text
16
  *.pth filter=lfs diff=lfs merge=lfs -text
17
+ entity_vocab.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<ent>": 50265, "<ent2>": 50266}
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LukeEntityAwareAttentionModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bert_model_name": "roberta-base",
7
+ "bos_token_id": 0,
8
+ "entity_emb_size": 256,
9
+ "entity_vocab_size": 500000,
10
+ "eos_token_id": 2,
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "layer_norm_eps": 1e-05,
18
+ "max_position_embeddings": 514,
19
+ "model_type": "luke",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_layers": 12,
22
+ "output_past": true,
23
+ "pad_token_id": 1,
24
+ "position_embedding_type": "absolute",
25
+ "transformers_version": "4.4.0.dev0",
26
+ "type_vocab_size": 1,
27
+ "use_cache": true,
28
+ "vocab_size": 50267
29
+ }
entity_vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45e0508babfee0667db9a8dfa2519a6e470c769c3489b4c87c45b26f59e30947
3
+ size 15287192
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe4d39fa2b1582c3d9aadbbd926ab26c64caef16fb64c3f4658dda7e74a9c3f2
3
+ size 1098122571
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": [{"content": "<ent>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<ent2>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "name_or_path": "roberta-base"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff