[BERT/Paddle] BERT Paddle initial release

Author: Wong4j

PaddlePaddle/LanguageModeling/BERT/Dockerfile

@@ -0,0 +1,15 @@
+ARG FROM_IMAGE_NAME=nvcr.io/nvidia/paddlepaddle:22.08-py3
+
+FROM ${FROM_IMAGE_NAME}
+
+RUN apt-get update && apt-get install -y pbzip2 pv bzip2 cabextract
+
+ENV BERT_PREP_WORKING_DIR /workspace/bert/data
+ADD requirements.txt /workspace/
+WORKDIR /workspace/
+RUN pip install --no-cache-dir -r requirements.txt
+RUN git clone https://github.com/attardi/wikiextractor.git && cd wikiextractor && git checkout 6408a430fc504a38b04d37ce5e7fc740191dee16 && cd ..
+RUN git clone https://github.com/soskek/bookcorpus.git
+
+ADD . /workspace/bert
+WORKDIR /workspace/bert

PaddlePaddle/LanguageModeling/BERT/README.md

@@ -0,0 +1,13 @@
+# Copyright (c) 2022 NVIDIA Corporation.  All rights reserved.
+#
+# 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.

PaddlePaddle/LanguageModeling/BERT/__init__.py

@@ -0,0 +1,13 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 512,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "type_vocab_size": 2,
+  "vocab_size": 28996
+}

PaddlePaddle/LanguageModeling/BERT/bert_configs/bert-base-cased.json

@@ -0,0 +1,13 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 512,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

PaddlePaddle/LanguageModeling/BERT/bert_configs/bert-base-uncased.json

@@ -0,0 +1,13 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "max_position_embeddings": 512,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "type_vocab_size": 2,
+  "vocab_size": 28996
+}

PaddlePaddle/LanguageModeling/BERT/bert_configs/bert-large-cased.json

@@ -0,0 +1,13 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "max_position_embeddings": 512,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}