add code

__init__.py

@@ -0,0 +1,15 @@
+# coding=utf-8
+# Copyright 2018 The Google AI Language Team Authors.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+

bert_train/bert_config_beauty_128.json

@@ -0,0 +1,13 @@
+{
+  "attention_probs_dropout_prob": 0.2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.5,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "max_position_embeddings": 50,
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "type_vocab_size": 2,
+  "vocab_size": 54546
+}

bert_train/bert_config_beauty_256.json

@@ -0,0 +1,13 @@
+{
+  "attention_probs_dropout_prob": 0.2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.5,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 50,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 2,
+  "type_vocab_size": 2,
+  "vocab_size": 54546
+}

bert_train/bert_config_beauty_64.json

@@ -0,0 +1,13 @@
+{
+  "attention_probs_dropout_prob": 0.2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.5,
+  "hidden_size": 64,
+  "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "max_position_embeddings": 50,
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "type_vocab_size": 2,
+  "vocab_size": 54546
+}

bert_train/bert_config_ml-1m_128.json

@@ -0,0 +1,13 @@
+{
+  "attention_probs_dropout_prob": 0.2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.5,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "max_position_embeddings": 200,
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "type_vocab_size": 2,
+  "vocab_size": 3420
+}

bert_train/bert_config_ml-1m_256.json

@@ -0,0 +1,13 @@
+{
+  "attention_probs_dropout_prob": 0.2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.5,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "max_position_embeddings": 200,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 2,
+  "type_vocab_size": 2,
+  "vocab_size": 3420
+}

bert_train/bert_config_ml-1m_64.json

@@ -0,0 +1,13 @@
+{
+  "attention_probs_dropout_prob": 0.2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.2,
+  "hidden_size": 64,
+  "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "max_position_embeddings": 200,
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "type_vocab_size": 2,
+  "vocab_size": 3420
+}

bert_train/bert_config_ml-20m_128.json

@@ -0,0 +1,13 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "max_position_embeddings": 200,
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "type_vocab_size": 2,
+  "vocab_size": 26748
+}

bert_train/bert_config_ml-20m_256.json

@@ -0,0 +1,13 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 200,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 2,
+  "type_vocab_size": 2,
+  "vocab_size": 26748
+}

bert_train/bert_config_ml-20m_64.json

@@ -0,0 +1,13 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 64,
+  "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "max_position_embeddings": 200,
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "type_vocab_size": 2,
+  "vocab_size": 26748
+}

bert_train/bert_config_steam_128.json

@@ -0,0 +1,13 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "max_position_embeddings": 50,
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "type_vocab_size": 2,
+  "vocab_size": 13048
+}

bert_train/bert_config_steam_256.json

@@ -0,0 +1,13 @@
+{
+  "attention_probs_dropout_prob": 0.2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.2,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 50,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 2,
+  "type_vocab_size": 2,
+  "vocab_size": 13048
+}

bert_train/bert_config_steam_64.json

@@ -0,0 +1,13 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 64,
+  "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "max_position_embeddings": 50,
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "type_vocab_size": 2,
+  "vocab_size": 13048
+}