tf

config.json

@@ -1,22 +1,30 @@
 {
+  "_name_or_path": "/data/yechen/bert/question-answering-chinese",
   "architectures": [
     "BertForQuestionAnswering"
-  ], 
-  "attention_probs_dropout_prob": 0.1, 
-  "directionality": "bidi", 
-  "hidden_act": "gelu", 
-  "hidden_dropout_prob": 0.1, 
-  "hidden_size": 1024, 
-  "initializer_range": 0.02, 
-  "intermediate_size": 4096, 
-  "max_position_embeddings": 512, 
-  "model_type": "bert", 
-  "num_attention_heads": 16, 
-  "num_hidden_layers": 24, 
-  "pooler_fc_size": 768, 
-  "pooler_num_attention_heads": 12, 
-  "pooler_num_fc_layers": 3, 
-  "pooler_size_per_head": 128, 
-  "pooler_type": "first_token_transform", 
-  "type_vocab_size": 2, 
-  "vocab_size": 21128}
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.3.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f94f423967e740dea972c1f86698ff87fc348450f08b49365fbd7c244f8f1f15
-size 3897896992
+oid sha256:7910bf077f1f0e5134111ddee832010bf9f6558130ebefce8630a7e465f8a075
+size 1298449192