Initial commit

README.md

@@ -0,0 +1,124 @@
+---
+
+language:
+- multilingual
+- af
+- am
+- ar
+- as
+- az
+- be
+- bg
+- bm
+- bn
+- br
+- bs
+- ca
+- cs
+- cy
+- da
+- de
+- el
+- en
+- eo
+- es
+- et
+- eu
+- fa
+- ff
+- fi
+- fr
+- fy
+- ga
+- gd
+- gl
+- gn
+- gu
+- ha
+- he
+- hi
+- hr
+- ht
+- hu
+- hy
+- id
+- ig
+- is
+- it
+- ja
+- jv
+- ka
+- kg
+- kk
+- km
+- kn
+- ko
+- ku
+- ky
+- la
+- lg
+- ln
+- lo
+- lt
+- lv
+- mg
+- mk
+- ml
+- mn
+- mr
+- ms
+- my
+- ne
+- nl
+- no
+- om
+- or
+- pa
+- pl
+- ps
+- pt
+- qu
+- ro
+- ru
+- sa
+- sd
+- si
+- sk
+- sl
+- so
+- sq
+- sr
+- ss
+- su
+- sv
+- sw
+- ta
+- te
+- th
+- ti
+- tl
+- tn
+- tr
+- uk
+- ur
+- uz
+- vi
+- wo
+- xh
+- yo
+- zh
+
+
+tags:
+- retrieval
+- entity-retrieval
+- named-entity-disambiguation
+- entity-disambiguation
+- named-entity-linking
+- entity-linking
+- text2text-generation
+---
+
+
+# mGENRE
+

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "facebook/mgenre-wiki",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_normalize_before": true,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "encoder_normalize_before": true,
+  "eos_token_id": 2,
+  "eos_token_ids": [
+    2
+  ],
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": 1024,
+  "max_position_embeddings": 1024,
+  "min_length": 0,
+  "model_type": "bart",
+  "normalize_embedding": false,
+  "num_beams": 5,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "student_decoder_layers": null,
+  "student_encoder_layers": null,
+  "task_specific_params": {},
+  "transformers_version": "4.19.2",
+  "use_cache": true,
+  "vocab_size": 256001
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c1a05450995f9b3b1ddb146271c77f71574833346c7fbc10322328a3719d6a2
+size 2469065849

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ee4dc054a17c18fe81f76c0b1cda00e9fc1cfd9e0f1a16cb6d77009e2076653
+size 4870365

special_tokens_map.json

@@ -0,0 +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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5368e45f810725f023451207956a99f324c0253d334f4bdaaeb2ae3dcd331f3d
+size 2469461956

titles_lang_all105_marisa_trie_with_redirect.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a35a904ee44b95e5e10d63f066fddcc5117cb5daf4e637ba5fadced92707756
+size 581590386

titles_lang_all105_trie_with_redirect.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af6069f11ec1d2f2ce1ef8f034eec761c0bee5971f663f6355442683e533935
+size 1754513408

tokenizer_config.json

@@ -0,0 +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"}