nicoladecao
commited on
Commit
•
daae92b
1
Parent(s):
5d59a3f
Initial commit
Browse files- README.md +124 -0
- config.json +52 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tf_model.h5 +3 -0
- titles_lang_all105_marisa_trie_with_redirect.pkl +3 -0
- titles_lang_all105_trie_with_redirect.pkl +3 -0
- tokenizer_config.json +1 -0
README.md
ADDED
@@ -0,0 +1,124 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
|
3 |
+
language:
|
4 |
+
- multilingual
|
5 |
+
- af
|
6 |
+
- am
|
7 |
+
- ar
|
8 |
+
- as
|
9 |
+
- az
|
10 |
+
- be
|
11 |
+
- bg
|
12 |
+
- bm
|
13 |
+
- bn
|
14 |
+
- br
|
15 |
+
- bs
|
16 |
+
- ca
|
17 |
+
- cs
|
18 |
+
- cy
|
19 |
+
- da
|
20 |
+
- de
|
21 |
+
- el
|
22 |
+
- en
|
23 |
+
- eo
|
24 |
+
- es
|
25 |
+
- et
|
26 |
+
- eu
|
27 |
+
- fa
|
28 |
+
- ff
|
29 |
+
- fi
|
30 |
+
- fr
|
31 |
+
- fy
|
32 |
+
- ga
|
33 |
+
- gd
|
34 |
+
- gl
|
35 |
+
- gn
|
36 |
+
- gu
|
37 |
+
- ha
|
38 |
+
- he
|
39 |
+
- hi
|
40 |
+
- hr
|
41 |
+
- ht
|
42 |
+
- hu
|
43 |
+
- hy
|
44 |
+
- id
|
45 |
+
- ig
|
46 |
+
- is
|
47 |
+
- it
|
48 |
+
- ja
|
49 |
+
- jv
|
50 |
+
- ka
|
51 |
+
- kg
|
52 |
+
- kk
|
53 |
+
- km
|
54 |
+
- kn
|
55 |
+
- ko
|
56 |
+
- ku
|
57 |
+
- ky
|
58 |
+
- la
|
59 |
+
- lg
|
60 |
+
- ln
|
61 |
+
- lo
|
62 |
+
- lt
|
63 |
+
- lv
|
64 |
+
- mg
|
65 |
+
- mk
|
66 |
+
- ml
|
67 |
+
- mn
|
68 |
+
- mr
|
69 |
+
- ms
|
70 |
+
- my
|
71 |
+
- ne
|
72 |
+
- nl
|
73 |
+
- no
|
74 |
+
- om
|
75 |
+
- or
|
76 |
+
- pa
|
77 |
+
- pl
|
78 |
+
- ps
|
79 |
+
- pt
|
80 |
+
- qu
|
81 |
+
- ro
|
82 |
+
- ru
|
83 |
+
- sa
|
84 |
+
- sd
|
85 |
+
- si
|
86 |
+
- sk
|
87 |
+
- sl
|
88 |
+
- so
|
89 |
+
- sq
|
90 |
+
- sr
|
91 |
+
- ss
|
92 |
+
- su
|
93 |
+
- sv
|
94 |
+
- sw
|
95 |
+
- ta
|
96 |
+
- te
|
97 |
+
- th
|
98 |
+
- ti
|
99 |
+
- tl
|
100 |
+
- tn
|
101 |
+
- tr
|
102 |
+
- uk
|
103 |
+
- ur
|
104 |
+
- uz
|
105 |
+
- vi
|
106 |
+
- wo
|
107 |
+
- xh
|
108 |
+
- yo
|
109 |
+
- zh
|
110 |
+
|
111 |
+
|
112 |
+
tags:
|
113 |
+
- retrieval
|
114 |
+
- entity-retrieval
|
115 |
+
- named-entity-disambiguation
|
116 |
+
- entity-disambiguation
|
117 |
+
- named-entity-linking
|
118 |
+
- entity-linking
|
119 |
+
- text2text-generation
|
120 |
+
---
|
121 |
+
|
122 |
+
|
123 |
+
# mGENRE
|
124 |
+
|
config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/mgenre-wiki",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.0,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 1024,
|
15 |
+
"decoder_attention_heads": 16,
|
16 |
+
"decoder_ffn_dim": 4096,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 12,
|
19 |
+
"decoder_normalize_before": true,
|
20 |
+
"decoder_start_token_id": 2,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"early_stopping": true,
|
23 |
+
"encoder_attention_heads": 16,
|
24 |
+
"encoder_ffn_dim": 4096,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 12,
|
27 |
+
"encoder_normalize_before": true,
|
28 |
+
"eos_token_id": 2,
|
29 |
+
"eos_token_ids": [
|
30 |
+
2
|
31 |
+
],
|
32 |
+
"forced_eos_token_id": 2,
|
33 |
+
"gradient_checkpointing": false,
|
34 |
+
"init_std": 0.02,
|
35 |
+
"is_encoder_decoder": true,
|
36 |
+
"max_length": 1024,
|
37 |
+
"max_position_embeddings": 1024,
|
38 |
+
"min_length": 0,
|
39 |
+
"model_type": "bart",
|
40 |
+
"normalize_embedding": false,
|
41 |
+
"num_beams": 5,
|
42 |
+
"num_hidden_layers": 12,
|
43 |
+
"pad_token_id": 1,
|
44 |
+
"scale_embedding": true,
|
45 |
+
"static_position_embeddings": false,
|
46 |
+
"student_decoder_layers": null,
|
47 |
+
"student_encoder_layers": null,
|
48 |
+
"task_specific_params": {},
|
49 |
+
"transformers_version": "4.19.2",
|
50 |
+
"use_cache": true,
|
51 |
+
"vocab_size": 256001
|
52 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c1a05450995f9b3b1ddb146271c77f71574833346c7fbc10322328a3719d6a2
|
3 |
+
size 2469065849
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ee4dc054a17c18fe81f76c0b1cda00e9fc1cfd9e0f1a16cb6d77009e2076653
|
3 |
+
size 4870365
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5368e45f810725f023451207956a99f324c0253d334f4bdaaeb2ae3dcd331f3d
|
3 |
+
size 2469461956
|
titles_lang_all105_marisa_trie_with_redirect.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a35a904ee44b95e5e10d63f066fddcc5117cb5daf4e637ba5fadced92707756
|
3 |
+
size 581590386
|
titles_lang_all105_trie_with_redirect.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9af6069f11ec1d2f2ce1ef8f034eec761c0bee5971f663f6355442683e533935
|
3 |
+
size 1754513408
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "tokenizer_class": "XLMRobertaTokenizer"}
|