Initial commit
Browse files- added_tokens.json +1 -0
- config.json +32 -0
- entity_vocab.json +1 -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
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<ent>": 50265, "<ent2>": 50266}
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "studio-ousia/luke-base-lite",
|
3 |
+
"architectures": [
|
4 |
+
"LukeForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bert_model_name": "roberta-base",
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"entity_emb_size": 256,
|
10 |
+
"entity_vocab_size": 4,
|
11 |
+
"eos_token_id": 2,
|
12 |
+
"gradient_checkpointing": false,
|
13 |
+
"hidden_act": "gelu",
|
14 |
+
"hidden_dropout_prob": 0.1,
|
15 |
+
"hidden_size": 768,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 3072,
|
18 |
+
"layer_norm_eps": 1e-05,
|
19 |
+
"max_position_embeddings": 514,
|
20 |
+
"model_type": "luke",
|
21 |
+
"num_attention_heads": 12,
|
22 |
+
"num_hidden_layers": 12,
|
23 |
+
"output_past": true,
|
24 |
+
"pad_token_id": 1,
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.15.0",
|
28 |
+
"type_vocab_size": 1,
|
29 |
+
"use_cache": true,
|
30 |
+
"use_entity_aware_attention": true,
|
31 |
+
"vocab_size": 50267
|
32 |
+
}
|
entity_vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"[MASK]": 0, "[UNK]": 1, "[PAD]": 2, "[MASK2]": 3}
|
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 sha256:01b47daa243cba92b271d206ab443a5fc6b78e7a3bb040da8a9a175118e331b0
|
3 |
+
size 589480003
|
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>", "entity_unk_token": "[UNK]", "entity_pad_token": "[PAD]", "entity_mask_token": "[MASK]", "entity_mask2_token": "[MASK2]", "model_max_length": 512, "name_or_path": "studio-ousia/luke-base", "special_tokens_map_file": "/home/ryo0123/.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
|
|