initial commit

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "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": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.5.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 100002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a279364774123165dcc515e7840d5f18d6f5ecd26ade26355b4c30653c453a85
+size 652269275

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f486660afe1c3edc98c96ce69928d5dfbb0d04d3cda791687c137382e8667ce
+size 2024878

tokenizer_config.json

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