Upload GLMForConditionalGeneration

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "/home/s9dazhuu/outputs/exp_outputs/law_qa/official_glm_10b_chinese_80GB/checkpoint-5400",
+  "architectures": [
+    "GLMForConditionalGeneration"
+  ],
+  "attention_dropout_prob": 0.1,
+  "attention_scale": 1.0,
+  "auto_map": {
+    "AutoConfig": "THUDM/glm-10b-chinese--configuration_glm.GLMConfig",
+    "AutoModel": "THUDM/glm-10b-chinese--modeling_glm.GLMModel",
+    "AutoModelForSeq2SeqLM": "THUDM/glm-10b-chinese--modeling_glm.GLMForConditionalGeneration",
+    "AutoModelForSequenceClassification": "THUDM/glm-10b-chinese--modeling_glm.GLMForSequenceClassification"
+  },
+  "bad_words_id": [
+    50009
+  ],
+  "block_position_encoding": true,
+  "checkpoint_activations": false,
+  "checkpoint_num_layers": 1,
+  "embedding_dropout_prob": 0.1,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "max_sequence_length": 1024,
+  "model_type": "glm",
+  "num_attention_heads": 64,
+  "num_layers": 48,
+  "output_dropout_prob": 0.1,
+  "output_predict": true,
+  "parallel_output": true,
+  "pool_token": "cls",
+  "relative_encoding": false,
+  "spell_func": "lstm",
+  "spell_length": null,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "vocab_size": 50048
+}

generation_config.json

@@ -0,0 +1,3 @@
+{
+  "transformers_version": "4.29.2"
+}

pytorch_model-00001-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baa7e860bedc34dfde9c068df3069384cb8210a7882d58b4554b22ef9fafc447
+size 9982903548

pytorch_model-00002-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c8f8270022b922159bf0dec751181a4001b72f4638ec18dc536ccde11d2106c
+size 9934784925

pytorch_model-00003-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24d1a5dd014e7b5ccfea0558d53b4db5365e84c0c6ad5e4be4d2fb69e7488255
+size 9934769255

pytorch_model-00004-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5068294f0e51f0d1f44bc1cb2f1028c717e4601b3a93649e48a5bc656a034dd5
+size 9666283119

pytorch_model.bin.index.json

@@ -0,0 +1,588 @@
+{
+  "metadata": {
+    "total_size": 39518535680
+  },
+  "weight_map": {
+    "glm.transformer.block_position_embeddings.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.final_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.final_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.0.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.0.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.1.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.1.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.10.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.10.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.10.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.11.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.11.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.11.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.12.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.12.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.12.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.12.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.12.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.13.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.13.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.13.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.13.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.13.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.14.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.14.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.14.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.14.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.14.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.15.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.15.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.15.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.15.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.15.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.16.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.16.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.16.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.16.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.16.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.16.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.17.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.17.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.17.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.17.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.17.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.17.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.18.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.18.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.18.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.18.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.18.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.18.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.19.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.19.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.19.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.19.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.19.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.2.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.2.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.20.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.20.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.20.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.20.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.20.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.21.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.21.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.21.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.21.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.21.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.22.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.22.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.22.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.22.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.22.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.23.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.23.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.23.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.23.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.23.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "glm.transformer.layers.24.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.24.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.24.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.24.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.24.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.24.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.25.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.25.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.25.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.25.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.25.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.25.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.26.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.26.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.26.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.26.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.26.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.26.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.27.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.27.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.27.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.27.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.27.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.27.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.28.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.28.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.28.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.28.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.28.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.28.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.29.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.29.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.29.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.29.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.29.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.29.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.3.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.3.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.30.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.30.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.30.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.30.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.30.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.30.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.31.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.31.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.31.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.31.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.31.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.31.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.32.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.32.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.32.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.32.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.32.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.32.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.33.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.33.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.33.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.33.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.33.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.33.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.34.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.34.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.34.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.34.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.34.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.34.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.35.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.35.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.35.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.35.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.35.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.35.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.36.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.36.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.36.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.36.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.36.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "glm.transformer.layers.36.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.36.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.36.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.36.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.36.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.36.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.37.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.37.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.37.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.37.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.37.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.37.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.37.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.37.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.37.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.37.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.37.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.37.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.38.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.38.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.38.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.38.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.38.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.38.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.38.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.38.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.38.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.38.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.38.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.38.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.39.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.39.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.39.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.39.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.39.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.39.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.39.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.39.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.39.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.39.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.39.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.39.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.4.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.4.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.40.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.40.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.40.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.40.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.40.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.40.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.40.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.40.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.40.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.40.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.40.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.40.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.41.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.41.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.41.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.41.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.41.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.41.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.41.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.41.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.41.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.41.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.41.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.41.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.42.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.42.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.42.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.42.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.42.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.42.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.42.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.42.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.42.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.42.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.42.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.42.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.43.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.43.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.43.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.43.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.43.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.43.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.43.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.43.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.43.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.43.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.43.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.43.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.44.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.44.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.44.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.44.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.44.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.44.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.44.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.44.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.44.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.44.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.44.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.44.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.45.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.45.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.45.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.45.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.45.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.45.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.45.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.45.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.45.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.45.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.45.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.45.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.46.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.46.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.46.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.46.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.46.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.46.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.46.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.46.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.46.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.46.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.46.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.46.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.47.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.47.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.47.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.47.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.47.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.47.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.47.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.47.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.47.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.47.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.47.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.47.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "glm.transformer.layers.5.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.5.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.6.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.6.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.7.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.7.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.8.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.8.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.9.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.9.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.transformer.position_embeddings.weight": "pytorch_model-00001-of-00004.bin",
+    "glm.word_embeddings.weight": "pytorch_model-00001-of-00004.bin"
+  }
+}