initial commit
Browse files- .gitattributes +1 -0
- added_tokens.json +1 -0
- config.json +50 -0
- entity_vocab.json +3 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
.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 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"LukeForEntityClassification"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"bert_model_name": "roberta-large",
|
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": 1024,
|
15 |
+
"id2label": {
|
16 |
+
"0": "LABEL_0",
|
17 |
+
"1": "LABEL_1",
|
18 |
+
"2": "LABEL_2",
|
19 |
+
"3": "LABEL_3",
|
20 |
+
"4": "LABEL_4",
|
21 |
+
"5": "LABEL_5",
|
22 |
+
"6": "LABEL_6",
|
23 |
+
"7": "LABEL_7",
|
24 |
+
"8": "LABEL_8"
|
25 |
+
},
|
26 |
+
"initializer_range": 0.02,
|
27 |
+
"intermediate_size": 4096,
|
28 |
+
"label2id": {
|
29 |
+
"LABEL_0": 0,
|
30 |
+
"LABEL_1": 1,
|
31 |
+
"LABEL_2": 2,
|
32 |
+
"LABEL_3": 3,
|
33 |
+
"LABEL_4": 4,
|
34 |
+
"LABEL_5": 5,
|
35 |
+
"LABEL_6": 6,
|
36 |
+
"LABEL_7": 7,
|
37 |
+
"LABEL_8": 8
|
38 |
+
},
|
39 |
+
"layer_norm_eps": 1e-05,
|
40 |
+
"max_position_embeddings": 514,
|
41 |
+
"model_type": "luke",
|
42 |
+
"num_attention_heads": 16,
|
43 |
+
"num_hidden_layers": 24,
|
44 |
+
"output_past": true,
|
45 |
+
"pad_token_id": 1,
|
46 |
+
"transformers_version": "4.6.0.dev0",
|
47 |
+
"type_vocab_size": 1,
|
48 |
+
"use_entity_aware_attention": true,
|
49 |
+
"vocab_size": 50267
|
50 |
+
}
|
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 sha256:884934fc02bc6d6cdf5be8a193c78c8c4b75c00f7e5c9624f061db8513000ef4
|
3 |
+
size 2239159855
|
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, "special_tokens_map_file": null, "tokenizer_file": "/Users/ikuya/.cache/huggingface/transformers/e16a2590deb9e6d73711d6e05bf27d832fa8c1162d807222e043ca650a556964.fc9576039592f026ad76a1c231b89aee8668488c671dfbe6616bab2ed298d730", "name_or_path": "roberta-large"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|