LysandreJik
commited on
Commit
•
a497d82
1
Parent(s):
c8c3811
v2 update
Browse files- .gitattributes +1 -0
- added_tokens.json +1 -0
- config.json +2 -2
- entity_vocab.json +3 -0
- merges.txt +0 -0
- pytorch_model.bin +2 -2
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -15,3 +15,4 @@
|
|
15 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
16 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
17 |
*tfevents* 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 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
18 |
+
entity_vocab.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"<ent>": 50265, "<ent2>": 50266}
|
config.json
CHANGED
@@ -16,8 +16,8 @@
|
|
16 |
"num_attention_heads": 4,
|
17 |
"num_hidden_layers": 5,
|
18 |
"pad_token_id": 1,
|
19 |
-
"transformers_version": "4.
|
20 |
"type_vocab_size": 16,
|
21 |
"use_entity_aware_attention": true,
|
22 |
-
"vocab_size":
|
23 |
}
|
16 |
"num_attention_heads": 4,
|
17 |
"num_hidden_layers": 5,
|
18 |
"pad_token_id": 1,
|
19 |
+
"transformers_version": "4.11.0.dev0",
|
20 |
"type_vocab_size": 16,
|
21 |
"use_entity_aware_attention": true,
|
22 |
+
"vocab_size": 50267
|
23 |
}
|
entity_vocab.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:733272d6ac7eb97e72817261fd6914fc30a83cd3f896aaf07eb87839188a3466
|
3 |
+
size 15161135
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2099f51f4c233392eb3ac8b3e6c4339b51586766e1bfbe377e640e4e14fecbda
|
3 |
+
size 6811851
|
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"}, "task": null, "max_entity_length": 32, "max_mention_length": 30, "entity_token_1": "<ent>", "entity_token_2": "<ent2>", "model_max_length": 512, "name_or_path": "studio-ousia/luke-base", "special_tokens_map_file": "/home/lysandre/.cache/huggingface/transformers/e2adf9c43ab82e2db47210f87bb53aa544055afc59e35389ffff22cd8fbd5d94.0ead83d1c22a0d79f17fc2eb3b32bd99fd9a262049166681d9713840ae868c2a", "tokenizer_file": null, "additional_special_tokens": [{"content": "<ent>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, {"content": "<ent2>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}], "tokenizer_class": "LukeTokenizer"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|