add config tokenizer

config.json

@@ -0,0 +1,15 @@
+{
+    "num_layers":40,
+    "vocab_size":50176,
+    "hidden_size":3072,
+    "num_attention_heads":48,
+    "embedding_dropout_prob":0.1,
+    "attention_dropout_prob":0.1,
+    "output_dropout_prob":0.1,
+    "max_sequence_length":1024,
+    "max_memory_length":512,
+    "checkpoint_activations":false,
+    "checkpoint_num_layers":1,
+    "parallel_output":true,
+    "relative_encoding":true
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ea6f4164152bc58d23e24e48f7bf4187aad72a32e97ec4b3acc832fe183cbc2
+size 1021864