From 8c7a98cbefb7fae739b9ac154ca5b22e65e494b9 Mon Sep 17 00:00:00 2001
From: pfgqbl2ej <942783126@qq.com>
Date: Mon, 8 Nov 2021 20:53:17 +0800
Subject: [PATCH] ADD file via upload

---
 examples/nlp/bert/datasets | 62 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 62 insertions(+)
 create mode 100644 examples/nlp/bert/datasets

diff --git a/examples/nlp/bert/datasets b/examples/nlp/bert/datasets
new file mode 100644
index 0000000..6707662
--- /dev/null
+++ b/examples/nlp/bert/datasets
@@ -0,0 +1,62 @@
+'''
+BERT Config:
+--------------------------------------------------------------------------------------------------'''
+class BertConfig(object):
+    """Configuration class to store the configuration of a `BertModel`.
+    """
+    def __init__(self,
+                 vocab_size,
+                 hidden_size=768,
+                 num_hidden_layers=12,
+                 num_attention_heads=12,
+                 intermediate_size=3072,
+                 hidden_act="relu",
+                 hidden_dropout_prob=0.1,
+                 attention_probs_dropout_prob=0.1,
+                 max_position_embeddings=512,
+                 type_vocab_size=2,
+                 initializer_range=0.02,
+                 output_hidden_states=False,
+                 batch_size=100,
+                 ):
+        """Constructs BertConfig.
+
+        Args:
+            vocab_size_or_config_json_file: Vocabulary size of `inputs_ids` in `BertModel`.
+            hidden_size: Size of the encoder layers and the pooler layer.
+            num_hidden_layers: Number of hidden layers in the Transformer encoder.
+            num_attention_heads: Number of attention heads for each attention layer in
+                the Transformer encoder.
+            intermediate_size: The size of the "intermediate" (i.e., feed-forward)
+                layer in the Transformer encoder.
+            hidden_act: The non-linear activation function (function or string) in the
+                encoder and pooler. If string, "gelu", "relu" and "swish" are supported.
+            hidden_dropout_prob: The dropout probabilitiy for all fully connected
+                layers in the embeddings, encoder, and pooler.
+            attention_probs_dropout_prob: The dropout ratio for the attention
+                probabilities.
+            max_position_embeddings: The maximum sequence length that this model might
+                ever be used with. Typically set this to something large just in case
+                (e.g., 512 or 1024 or 2048).
+            type_vocab_size: The vocabulary size of the `token_type_ids` passed into
+                `BertModel`.
+            initializer_range: The sttdev of the truncated_normal_initializer for
+                initializing all weight matrices.
+        """
+
+        self.vocab_size = vocab_size
+        self.hidden_size = hidden_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.hidden_act = hidden_act
+        self.intermediate_size = intermediate_size
+        self.hidden_dropout_prob = hidden_dropout_prob
+        self.attention_probs_dropout_prob = attention_probs_dropout_prob
+        self.max_position_embeddings = max_position_embeddings
+        self.type_vocab_size = type_vocab_size
+        self.initializer_range = initializer_range
+        self.output_hidden_states = output_hidden_states
+        self.batch_size = batch_size
+
+
+'''-----------------------------------------------------------------------------------------------'''