Upload model

config.json

@@ -1,7 +1,6 @@
 {
-  "_name_or_path": "/home/yuwei/miao/GoBERT/go_bert/upload/ckpt_best",
   "architectures": [
-    "BertForPreTraining"
+    "GoBERTModel_Ex_Im"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0800fa6d2bc78a69a919d3db55ad44aa131756681df36641ce212e1f2274faff
+size 9114139152

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab6fd2aa4b71e313067354fef1c1b4ab6c29c676a04e88a6176145c579b0e31d
+size 1015118456

model.safetensors.index.json

@@ -0,0 +1,183 @@
+{
+  "metadata": {
+    "total_size": 10129236848
+  },
+  "weight_map": {
+    "bert.embeddings.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.embeddings.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.embeddings.position_embeddings.weight": "model-00002-of-00002.safetensors",
+    "bert.embeddings.token_type_embeddings.weight": "model-00002-of-00002.safetensors",
+    "bert.embeddings.word_embeddings.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.0.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.1.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.2.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.3.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.3.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.3.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.3.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.3.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.3.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.3.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.3.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.3.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.3.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.3.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.3.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.3.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.3.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.3.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.3.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.4.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.4.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.4.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.4.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.4.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.4.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.4.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.4.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.4.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.4.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.4.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.4.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.4.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.4.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.4.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.4.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.5.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.5.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.5.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.5.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.5.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.5.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.5.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.5.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.5.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.5.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.5.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.5.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.5.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.5.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.5.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.5.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.6.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.6.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.6.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.6.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.6.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.6.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.6.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.6.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.6.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.6.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.6.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.6.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.6.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.6.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.6.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.6.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.7.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.7.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.7.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.7.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.7.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.7.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.7.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.7.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.7.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.7.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.7.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.7.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.7.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.7.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.7.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.7.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.8.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.8.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.8.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.8.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.8.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.8.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.8.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.8.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.8.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.8.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.8.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.8.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.8.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.8.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.8.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.8.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.9.attention.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.9.attention.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.9.attention.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.9.attention.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.9.attention.self.key.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.9.attention.self.key.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.9.attention.self.query.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.9.attention.self.query.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.9.attention.self.value.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.9.attention.self.value.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.9.intermediate.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.9.intermediate.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.9.output.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.9.output.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.9.output.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.encoder.layer.9.output.dense.weight": "model-00002-of-00002.safetensors",
+    "bert.pooler.dense.bias": "model-00002-of-00002.safetensors",
+    "bert.pooler.dense.weight": "model-00002-of-00002.safetensors",
+    "cls.predictions.bias": "model-00002-of-00002.safetensors",
+    "cls.predictions.decoder.weight": "model-00002-of-00002.safetensors",
+    "cls.predictions.transform.LayerNorm.bias": "model-00002-of-00002.safetensors",
+    "cls.predictions.transform.LayerNorm.weight": "model-00002-of-00002.safetensors",
+    "cls.predictions.transform.dense.bias": "model-00002-of-00002.safetensors",
+    "cls.predictions.transform.dense.weight": "model-00002-of-00002.safetensors",
+    "cls.seq_relationship.bias": "model-00002-of-00002.safetensors",
+    "cls.seq_relationship.weight": "model-00002-of-00002.safetensors",
+    "ex_label_buffer": "model-00001-of-00002.safetensors"
+  }
+}