tokenizer: add initial version

config.json

@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "./",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.12.5",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82efdcf8269b58d3514960199a3de1b5db94e9e74b09528022c0bf08da93fe83
+size 169764963

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a52dc1b775a3fd49ab0076da661c4e00b04dd2bea8469fa95e31eba28904c3
+size 235445072

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "max_len": 512, "init_inputs": [], "strip_accents":false}