init

README.md

@@ -1,3 +1,17 @@
----
-license: cc-by-sa-3.0
----
+---
+language: ja
+license: cc-by-sa-4.0
+datasets:
+- wikipedia
+widget:
+- text: 東北大学で[MASK]の研究をしています。
+---
+
+# What is this model?
+- 東北大学のBERT large JapaneseをRustで使える様に変換
+- [cl-tohoku/bert-large-japanese](https://huggingface.co/cl-tohoku/bert-large-japanese)
+
+## Licenses
+
+The pretrained models are distributed under the terms of the [Creative Commons Attribution-ShareAlike 3.0](https://creativecommons.org/licenses/by-sa/3.0/).
+

config.json

@@ -0,0 +1,20 @@
+{
+    "architectures": [
+        "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "layer_norm_eps": 1e-12,
+    "max_position_embeddings": 512,
+    "model_type": "bert",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "pad_token_id": 0,
+    "tokenizer_class": "BertJapaneseTokenizer",
+    "type_vocab_size": 2,
+    "vocab_size": 32768
+}

rust_model.ot

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2781ffd6e814a654770c3e6648b0a69ee17bd500a77bc36fd904544027dd6b1
+size 1488590140

tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+    "do_lower_case": false,
+    "word_tokenizer_type": "mecab",
+    "subword_tokenizer_type": "wordpiece",
+    "mecab_kwargs": {
+        "mecab_dic": "unidic_lite"
+    }
+}