initial commit

.gitattributes

@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+entity_vocab.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,34 @@
+---
+language: multilingual
+thumbnail: https://github.com/studio-ousia/luke/raw/master/resources/luke_logo.png
+tags:
+  - luke
+  - named entity recognition
+  - relation classification
+  - question answering
+license: apache-2.0
+---
+
+## mLUKE
+
+**mLUKE** (multilingual LUKE) is a multilingual extension of LUKE.
+
+Please check the [official repository](https://github.com/studio-ousia/luke) for
+more details and updates.
+
+This is the mLUKE base model with 12 hidden layers, 768 hidden size. The total number
+of parameters in this model is 585M (278M for the word embeddings and encoder, 307M for the entity embeddings).
+The model was initialized with the weights of XLM-RoBERTa(base) and trained using December 2020 version of Wikipedia in 24 languages.
+
+### Citation
+
+If you find mLUKE useful for your work, please cite the following paper:
+
+```latex
+@inproceedings{ri2021mluke,
+  title={mLUKE: The Power of Entity Representations in Multilingual Pretrained Language Models},
+  author={Ryokan Ri, Ikuya Yamada, Yoshimasa Tsuruoka},
+  booktitle={arXiv},
+  year={2021}
+}
+```

added_tokens.json

@@ -0,0 +1 @@
+{"<ent>": 250002, "<ent2>": 250003}

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "LukeForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bert_model_name": "xlm-roberta-base",
+  "bos_token_id": 0,
+  "cls_entity_prediction": false,
+  "deepspeed_transformer_layer_args": {},
+  "entity_emb_size": 256,
+  "entity_vocab_size": 1200001,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "luke",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "use_deepspeed_transformer_layer": false,
+  "use_entity_aware_attention": true,
+  "vocab_size": 250004
+}

entity_vocab.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc661ccd50c8856fec1c1937275801ac148dadea1835bd15ba37037853b73cc5
+size 438520875

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56588c40f41cff82e5174f1cd790bf59151f82c434407fd103d6ede9addeee5a
+size 2437467971

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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}, "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

@@ -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": {}, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/Users/linghan/.cache/huggingface/transformers/daeda8d936162ca65fe6dd158ecce1d8cb56c17d89b78ab86be1558eaef1d76a.a984cf52fc87644bd4a2165f1e07e0ac880272c1e82d648b4674907056912bd7", "name_or_path": "xlm-roberta-base", "tokenizer_class": "MLukeTokenizer"}