tf

config.json

@@ -1,21 +1,30 @@
 {
+  "_name_or_path": "/data/yechen/bert/bert-large-chinese",
   "architectures": [
     "BertForMaskedLM"
-  ], 
-  "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, 
-  "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 sha256:2594fba1861e40f8a19d0505aceee88c766da31ef64704f61efb0af8cc8d0c42
-size 3919167104
+oid sha256:313050cd80734a801bda2c1caf1259022873c1aae07d6e285f953bdab8ba285f
+size 1393494464