law-llm commited on
Commit
f602500
1 Parent(s): b0ce0a4

Upload GLMForConditionalGeneration

Browse files
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/users/dzhu/outputs/law_qa/tmp/checkpoint-8400",
3
+ "architectures": [
4
+ "GLMForConditionalGeneration"
5
+ ],
6
+ "attention_dropout_prob": 0.1,
7
+ "attention_scale": 1.0,
8
+ "auto_map": {
9
+ "AutoConfig": "THUDM/glm-10b-chinese--configuration_glm.GLMConfig",
10
+ "AutoModel": "THUDM/glm-10b-chinese--modeling_glm.GLMModel",
11
+ "AutoModelForSeq2SeqLM": "THUDM/glm-10b-chinese--modeling_glm.GLMForConditionalGeneration",
12
+ "AutoModelForSequenceClassification": "THUDM/glm-10b-chinese--modeling_glm.GLMForSequenceClassification"
13
+ },
14
+ "bad_words_id": [
15
+ 50009
16
+ ],
17
+ "block_position_encoding": true,
18
+ "checkpoint_activations": false,
19
+ "checkpoint_num_layers": 1,
20
+ "embedding_dropout_prob": 0.1,
21
+ "hidden_size": 4096,
22
+ "initializer_range": 0.02,
23
+ "max_sequence_length": 1024,
24
+ "model_type": "glm",
25
+ "num_attention_heads": 64,
26
+ "num_layers": 48,
27
+ "output_dropout_prob": 0.1,
28
+ "output_predict": true,
29
+ "parallel_output": true,
30
+ "pool_token": "cls",
31
+ "relative_encoding": false,
32
+ "spell_func": "lstm",
33
+ "spell_length": null,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.29.2",
36
+ "vocab_size": 50048
37
+ }
generation_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "transformers_version": "4.29.2"
3
+ }
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85048323ee80af7e2646e497d501a5d33d46edd8b0f598e0ac7ab962b666307f
3
+ size 9982903548
pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdcea1e513448628c87a10986fb6e01664136e6238708fe8c7e353bf84b3834b
3
+ size 9934784925
pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b53c950ed0ab16efc48c6fd46db6bc03460a3af94e60e99566a6409e0a153a
3
+ size 9934769255
pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a043dd733e9fd105fea3bd465fafb94554934961474edcf3afd662214780a190
3
+ size 9666283119
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,588 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 39518535680
4
+ },
5
+ "weight_map": {
6
+ "glm.transformer.block_position_embeddings.weight": "pytorch_model-00001-of-00004.bin",
7
+ "glm.transformer.final_layernorm.bias": "pytorch_model-00004-of-00004.bin",
8
+ "glm.transformer.final_layernorm.weight": "pytorch_model-00004-of-00004.bin",
9
+ "glm.transformer.layers.0.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
10
+ "glm.transformer.layers.0.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
11
+ "glm.transformer.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
12
+ "glm.transformer.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
13
+ "glm.transformer.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
14
+ "glm.transformer.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
15
+ "glm.transformer.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
16
+ "glm.transformer.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
17
+ "glm.transformer.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
18
+ "glm.transformer.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
19
+ "glm.transformer.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
20
+ "glm.transformer.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
21
+ "glm.transformer.layers.1.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
22
+ "glm.transformer.layers.1.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
23
+ "glm.transformer.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
24
+ "glm.transformer.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
25
+ "glm.transformer.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
26
+ "glm.transformer.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
27
+ "glm.transformer.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
28
+ "glm.transformer.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
29
+ "glm.transformer.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
30
+ "glm.transformer.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
31
+ "glm.transformer.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
32
+ "glm.transformer.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
33
+ "glm.transformer.layers.10.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
34
+ "glm.transformer.layers.10.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
35
+ "glm.transformer.layers.10.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
36
+ "glm.transformer.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
37
+ "glm.transformer.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
38
+ "glm.transformer.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
39
+ "glm.transformer.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
40
+ "glm.transformer.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
41
+ "glm.transformer.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
42
+ "glm.transformer.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
43
+ "glm.transformer.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
44
+ "glm.transformer.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
45
+ "glm.transformer.layers.11.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
46
+ "glm.transformer.layers.11.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
47
+ "glm.transformer.layers.11.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
48
+ "glm.transformer.layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
49
+ "glm.transformer.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
50
+ "glm.transformer.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
51
+ "glm.transformer.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
52
+ "glm.transformer.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
53
+ "glm.transformer.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
54
+ "glm.transformer.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
55
+ "glm.transformer.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
56
+ "glm.transformer.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
57
+ "glm.transformer.layers.12.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
58
+ "glm.transformer.layers.12.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
59
+ "glm.transformer.layers.12.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
60
+ "glm.transformer.layers.12.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
61
+ "glm.transformer.layers.12.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
62
+ "glm.transformer.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
63
+ "glm.transformer.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
64
+ "glm.transformer.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
65
+ "glm.transformer.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
66
+ "glm.transformer.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
67
+ "glm.transformer.layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
68
+ "glm.transformer.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
69
+ "glm.transformer.layers.13.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
70
+ "glm.transformer.layers.13.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
71
+ "glm.transformer.layers.13.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
72
+ "glm.transformer.layers.13.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
73
+ "glm.transformer.layers.13.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
74
+ "glm.transformer.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
75
+ "glm.transformer.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
76
+ "glm.transformer.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
77
+ "glm.transformer.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
78
+ "glm.transformer.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
79
+ "glm.transformer.layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
80
+ "glm.transformer.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
81
+ "glm.transformer.layers.14.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
82
+ "glm.transformer.layers.14.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
83
+ "glm.transformer.layers.14.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
84
+ "glm.transformer.layers.14.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
85
+ "glm.transformer.layers.14.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
86
+ "glm.transformer.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
87
+ "glm.transformer.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
88
+ "glm.transformer.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
89
+ "glm.transformer.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
90
+ "glm.transformer.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
91
+ "glm.transformer.layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
92
+ "glm.transformer.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
93
+ "glm.transformer.layers.15.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
94
+ "glm.transformer.layers.15.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
95
+ "glm.transformer.layers.15.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
96
+ "glm.transformer.layers.15.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
97
+ "glm.transformer.layers.15.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
98
+ "glm.transformer.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
99
+ "glm.transformer.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
100
+ "glm.transformer.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
101
+ "glm.transformer.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
102
+ "glm.transformer.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
103
+ "glm.transformer.layers.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
104
+ "glm.transformer.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
105
+ "glm.transformer.layers.16.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
106
+ "glm.transformer.layers.16.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
107
+ "glm.transformer.layers.16.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
108
+ "glm.transformer.layers.16.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
109
+ "glm.transformer.layers.16.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
110
+ "glm.transformer.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
111
+ "glm.transformer.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
112
+ "glm.transformer.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
113
+ "glm.transformer.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
114
+ "glm.transformer.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
115
+ "glm.transformer.layers.16.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
116
+ "glm.transformer.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
117
+ "glm.transformer.layers.17.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
118
+ "glm.transformer.layers.17.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
119
+ "glm.transformer.layers.17.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
120
+ "glm.transformer.layers.17.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
121
+ "glm.transformer.layers.17.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
122
+ "glm.transformer.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
123
+ "glm.transformer.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
124
+ "glm.transformer.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
125
+ "glm.transformer.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
126
+ "glm.transformer.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
127
+ "glm.transformer.layers.17.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
128
+ "glm.transformer.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
129
+ "glm.transformer.layers.18.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
130
+ "glm.transformer.layers.18.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
131
+ "glm.transformer.layers.18.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
132
+ "glm.transformer.layers.18.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
133
+ "glm.transformer.layers.18.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
134
+ "glm.transformer.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
135
+ "glm.transformer.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
136
+ "glm.transformer.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
137
+ "glm.transformer.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
138
+ "glm.transformer.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
139
+ "glm.transformer.layers.18.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
140
+ "glm.transformer.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
141
+ "glm.transformer.layers.19.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
142
+ "glm.transformer.layers.19.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
143
+ "glm.transformer.layers.19.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
144
+ "glm.transformer.layers.19.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
145
+ "glm.transformer.layers.19.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
146
+ "glm.transformer.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
147
+ "glm.transformer.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
148
+ "glm.transformer.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
149
+ "glm.transformer.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
150
+ "glm.transformer.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
151
+ "glm.transformer.layers.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
152
+ "glm.transformer.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
153
+ "glm.transformer.layers.2.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
154
+ "glm.transformer.layers.2.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
155
+ "glm.transformer.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
156
+ "glm.transformer.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
157
+ "glm.transformer.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
158
+ "glm.transformer.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
159
+ "glm.transformer.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
160
+ "glm.transformer.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
161
+ "glm.transformer.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
162
+ "glm.transformer.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
163
+ "glm.transformer.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
164
+ "glm.transformer.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
165
+ "glm.transformer.layers.20.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
166
+ "glm.transformer.layers.20.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
167
+ "glm.transformer.layers.20.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
168
+ "glm.transformer.layers.20.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
169
+ "glm.transformer.layers.20.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
170
+ "glm.transformer.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
171
+ "glm.transformer.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
172
+ "glm.transformer.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
173
+ "glm.transformer.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
174
+ "glm.transformer.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
175
+ "glm.transformer.layers.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
176
+ "glm.transformer.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
177
+ "glm.transformer.layers.21.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
178
+ "glm.transformer.layers.21.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
179
+ "glm.transformer.layers.21.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
180
+ "glm.transformer.layers.21.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
181
+ "glm.transformer.layers.21.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
182
+ "glm.transformer.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
183
+ "glm.transformer.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
184
+ "glm.transformer.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
185
+ "glm.transformer.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
186
+ "glm.transformer.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
187
+ "glm.transformer.layers.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
188
+ "glm.transformer.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
189
+ "glm.transformer.layers.22.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
190
+ "glm.transformer.layers.22.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
191
+ "glm.transformer.layers.22.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
192
+ "glm.transformer.layers.22.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
193
+ "glm.transformer.layers.22.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
194
+ "glm.transformer.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
195
+ "glm.transformer.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
196
+ "glm.transformer.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
197
+ "glm.transformer.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
198
+ "glm.transformer.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
199
+ "glm.transformer.layers.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
200
+ "glm.transformer.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
201
+ "glm.transformer.layers.23.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
202
+ "glm.transformer.layers.23.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
203
+ "glm.transformer.layers.23.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
204
+ "glm.transformer.layers.23.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
205
+ "glm.transformer.layers.23.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
206
+ "glm.transformer.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
207
+ "glm.transformer.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
208
+ "glm.transformer.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
209
+ "glm.transformer.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
210
+ "glm.transformer.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
211
+ "glm.transformer.layers.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
212
+ "glm.transformer.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
213
+ "glm.transformer.layers.24.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
214
+ "glm.transformer.layers.24.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
215
+ "glm.transformer.layers.24.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
216
+ "glm.transformer.layers.24.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
217
+ "glm.transformer.layers.24.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
218
+ "glm.transformer.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
219
+ "glm.transformer.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
220
+ "glm.transformer.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
221
+ "glm.transformer.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
222
+ "glm.transformer.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
223
+ "glm.transformer.layers.24.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
224
+ "glm.transformer.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
225
+ "glm.transformer.layers.25.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
226
+ "glm.transformer.layers.25.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
227
+ "glm.transformer.layers.25.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
228
+ "glm.transformer.layers.25.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
229
+ "glm.transformer.layers.25.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
230
+ "glm.transformer.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
231
+ "glm.transformer.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
232
+ "glm.transformer.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
233
+ "glm.transformer.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
234
+ "glm.transformer.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
235
+ "glm.transformer.layers.25.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
236
+ "glm.transformer.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
237
+ "glm.transformer.layers.26.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
238
+ "glm.transformer.layers.26.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
239
+ "glm.transformer.layers.26.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
240
+ "glm.transformer.layers.26.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
241
+ "glm.transformer.layers.26.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
242
+ "glm.transformer.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
243
+ "glm.transformer.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
244
+ "glm.transformer.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
245
+ "glm.transformer.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
246
+ "glm.transformer.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
247
+ "glm.transformer.layers.26.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
248
+ "glm.transformer.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
249
+ "glm.transformer.layers.27.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
250
+ "glm.transformer.layers.27.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
251
+ "glm.transformer.layers.27.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
252
+ "glm.transformer.layers.27.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
253
+ "glm.transformer.layers.27.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
254
+ "glm.transformer.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
255
+ "glm.transformer.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
256
+ "glm.transformer.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
257
+ "glm.transformer.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
258
+ "glm.transformer.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
259
+ "glm.transformer.layers.27.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
260
+ "glm.transformer.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
261
+ "glm.transformer.layers.28.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
262
+ "glm.transformer.layers.28.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
263
+ "glm.transformer.layers.28.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
264
+ "glm.transformer.layers.28.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
265
+ "glm.transformer.layers.28.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
266
+ "glm.transformer.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
267
+ "glm.transformer.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
268
+ "glm.transformer.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
269
+ "glm.transformer.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
270
+ "glm.transformer.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
271
+ "glm.transformer.layers.28.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
272
+ "glm.transformer.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
273
+ "glm.transformer.layers.29.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
274
+ "glm.transformer.layers.29.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
275
+ "glm.transformer.layers.29.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
276
+ "glm.transformer.layers.29.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
277
+ "glm.transformer.layers.29.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
278
+ "glm.transformer.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
279
+ "glm.transformer.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
280
+ "glm.transformer.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
281
+ "glm.transformer.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
282
+ "glm.transformer.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
283
+ "glm.transformer.layers.29.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
284
+ "glm.transformer.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
285
+ "glm.transformer.layers.3.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
286
+ "glm.transformer.layers.3.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
287
+ "glm.transformer.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
288
+ "glm.transformer.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
289
+ "glm.transformer.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
290
+ "glm.transformer.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
291
+ "glm.transformer.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
292
+ "glm.transformer.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
293
+ "glm.transformer.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
294
+ "glm.transformer.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
295
+ "glm.transformer.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
296
+ "glm.transformer.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
297
+ "glm.transformer.layers.30.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
298
+ "glm.transformer.layers.30.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
299
+ "glm.transformer.layers.30.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
300
+ "glm.transformer.layers.30.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
301
+ "glm.transformer.layers.30.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
302
+ "glm.transformer.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
303
+ "glm.transformer.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
304
+ "glm.transformer.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
305
+ "glm.transformer.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
306
+ "glm.transformer.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
307
+ "glm.transformer.layers.30.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
308
+ "glm.transformer.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
309
+ "glm.transformer.layers.31.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
310
+ "glm.transformer.layers.31.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
311
+ "glm.transformer.layers.31.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
312
+ "glm.transformer.layers.31.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
313
+ "glm.transformer.layers.31.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
314
+ "glm.transformer.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
315
+ "glm.transformer.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
316
+ "glm.transformer.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
317
+ "glm.transformer.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
318
+ "glm.transformer.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
319
+ "glm.transformer.layers.31.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
320
+ "glm.transformer.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
321
+ "glm.transformer.layers.32.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
322
+ "glm.transformer.layers.32.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
323
+ "glm.transformer.layers.32.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
324
+ "glm.transformer.layers.32.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
325
+ "glm.transformer.layers.32.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
326
+ "glm.transformer.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
327
+ "glm.transformer.layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
328
+ "glm.transformer.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
329
+ "glm.transformer.layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
330
+ "glm.transformer.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
331
+ "glm.transformer.layers.32.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
332
+ "glm.transformer.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
333
+ "glm.transformer.layers.33.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
334
+ "glm.transformer.layers.33.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
335
+ "glm.transformer.layers.33.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
336
+ "glm.transformer.layers.33.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
337
+ "glm.transformer.layers.33.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
338
+ "glm.transformer.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
339
+ "glm.transformer.layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
340
+ "glm.transformer.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
341
+ "glm.transformer.layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
342
+ "glm.transformer.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
343
+ "glm.transformer.layers.33.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
344
+ "glm.transformer.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
345
+ "glm.transformer.layers.34.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
346
+ "glm.transformer.layers.34.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
347
+ "glm.transformer.layers.34.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
348
+ "glm.transformer.layers.34.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
349
+ "glm.transformer.layers.34.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
350
+ "glm.transformer.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
351
+ "glm.transformer.layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
352
+ "glm.transformer.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
353
+ "glm.transformer.layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
354
+ "glm.transformer.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
355
+ "glm.transformer.layers.34.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
356
+ "glm.transformer.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
357
+ "glm.transformer.layers.35.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
358
+ "glm.transformer.layers.35.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
359
+ "glm.transformer.layers.35.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
360
+ "glm.transformer.layers.35.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
361
+ "glm.transformer.layers.35.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
362
+ "glm.transformer.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
363
+ "glm.transformer.layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
364
+ "glm.transformer.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
365
+ "glm.transformer.layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
366
+ "glm.transformer.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
367
+ "glm.transformer.layers.35.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
368
+ "glm.transformer.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
369
+ "glm.transformer.layers.36.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
370
+ "glm.transformer.layers.36.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
371
+ "glm.transformer.layers.36.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
372
+ "glm.transformer.layers.36.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
373
+ "glm.transformer.layers.36.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
374
+ "glm.transformer.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
375
+ "glm.transformer.layers.36.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
376
+ "glm.transformer.layers.36.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
377
+ "glm.transformer.layers.36.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
378
+ "glm.transformer.layers.36.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
379
+ "glm.transformer.layers.36.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
380
+ "glm.transformer.layers.36.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
381
+ "glm.transformer.layers.37.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
382
+ "glm.transformer.layers.37.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
383
+ "glm.transformer.layers.37.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
384
+ "glm.transformer.layers.37.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
385
+ "glm.transformer.layers.37.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
386
+ "glm.transformer.layers.37.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
387
+ "glm.transformer.layers.37.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
388
+ "glm.transformer.layers.37.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
389
+ "glm.transformer.layers.37.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
390
+ "glm.transformer.layers.37.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
391
+ "glm.transformer.layers.37.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
392
+ "glm.transformer.layers.37.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
393
+ "glm.transformer.layers.38.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
394
+ "glm.transformer.layers.38.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
395
+ "glm.transformer.layers.38.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
396
+ "glm.transformer.layers.38.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
397
+ "glm.transformer.layers.38.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
398
+ "glm.transformer.layers.38.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
399
+ "glm.transformer.layers.38.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
400
+ "glm.transformer.layers.38.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
401
+ "glm.transformer.layers.38.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
402
+ "glm.transformer.layers.38.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
403
+ "glm.transformer.layers.38.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
404
+ "glm.transformer.layers.38.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
405
+ "glm.transformer.layers.39.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
406
+ "glm.transformer.layers.39.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
407
+ "glm.transformer.layers.39.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
408
+ "glm.transformer.layers.39.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
409
+ "glm.transformer.layers.39.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
410
+ "glm.transformer.layers.39.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
411
+ "glm.transformer.layers.39.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
412
+ "glm.transformer.layers.39.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
413
+ "glm.transformer.layers.39.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
414
+ "glm.transformer.layers.39.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
415
+ "glm.transformer.layers.39.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
416
+ "glm.transformer.layers.39.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
417
+ "glm.transformer.layers.4.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
418
+ "glm.transformer.layers.4.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
419
+ "glm.transformer.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
420
+ "glm.transformer.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
421
+ "glm.transformer.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
422
+ "glm.transformer.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
423
+ "glm.transformer.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
424
+ "glm.transformer.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
425
+ "glm.transformer.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
426
+ "glm.transformer.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
427
+ "glm.transformer.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
428
+ "glm.transformer.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
429
+ "glm.transformer.layers.40.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
430
+ "glm.transformer.layers.40.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
431
+ "glm.transformer.layers.40.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
432
+ "glm.transformer.layers.40.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
433
+ "glm.transformer.layers.40.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
434
+ "glm.transformer.layers.40.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
435
+ "glm.transformer.layers.40.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
436
+ "glm.transformer.layers.40.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
437
+ "glm.transformer.layers.40.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
438
+ "glm.transformer.layers.40.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
439
+ "glm.transformer.layers.40.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
440
+ "glm.transformer.layers.40.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
441
+ "glm.transformer.layers.41.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
442
+ "glm.transformer.layers.41.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
443
+ "glm.transformer.layers.41.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
444
+ "glm.transformer.layers.41.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
445
+ "glm.transformer.layers.41.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
446
+ "glm.transformer.layers.41.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
447
+ "glm.transformer.layers.41.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
448
+ "glm.transformer.layers.41.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
449
+ "glm.transformer.layers.41.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
450
+ "glm.transformer.layers.41.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
451
+ "glm.transformer.layers.41.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
452
+ "glm.transformer.layers.41.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
453
+ "glm.transformer.layers.42.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
454
+ "glm.transformer.layers.42.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
455
+ "glm.transformer.layers.42.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
456
+ "glm.transformer.layers.42.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
457
+ "glm.transformer.layers.42.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
458
+ "glm.transformer.layers.42.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
459
+ "glm.transformer.layers.42.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
460
+ "glm.transformer.layers.42.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
461
+ "glm.transformer.layers.42.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
462
+ "glm.transformer.layers.42.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
463
+ "glm.transformer.layers.42.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
464
+ "glm.transformer.layers.42.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
465
+ "glm.transformer.layers.43.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
466
+ "glm.transformer.layers.43.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
467
+ "glm.transformer.layers.43.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
468
+ "glm.transformer.layers.43.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
469
+ "glm.transformer.layers.43.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
470
+ "glm.transformer.layers.43.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
471
+ "glm.transformer.layers.43.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
472
+ "glm.transformer.layers.43.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
473
+ "glm.transformer.layers.43.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
474
+ "glm.transformer.layers.43.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
475
+ "glm.transformer.layers.43.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
476
+ "glm.transformer.layers.43.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
477
+ "glm.transformer.layers.44.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
478
+ "glm.transformer.layers.44.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
479
+ "glm.transformer.layers.44.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
480
+ "glm.transformer.layers.44.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
481
+ "glm.transformer.layers.44.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
482
+ "glm.transformer.layers.44.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
483
+ "glm.transformer.layers.44.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
484
+ "glm.transformer.layers.44.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
485
+ "glm.transformer.layers.44.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
486
+ "glm.transformer.layers.44.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
487
+ "glm.transformer.layers.44.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
488
+ "glm.transformer.layers.44.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
489
+ "glm.transformer.layers.45.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
490
+ "glm.transformer.layers.45.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
491
+ "glm.transformer.layers.45.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
492
+ "glm.transformer.layers.45.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
493
+ "glm.transformer.layers.45.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
494
+ "glm.transformer.layers.45.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
495
+ "glm.transformer.layers.45.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
496
+ "glm.transformer.layers.45.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
497
+ "glm.transformer.layers.45.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
498
+ "glm.transformer.layers.45.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
499
+ "glm.transformer.layers.45.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
500
+ "glm.transformer.layers.45.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
501
+ "glm.transformer.layers.46.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
502
+ "glm.transformer.layers.46.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
503
+ "glm.transformer.layers.46.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
504
+ "glm.transformer.layers.46.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
505
+ "glm.transformer.layers.46.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
506
+ "glm.transformer.layers.46.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
507
+ "glm.transformer.layers.46.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
508
+ "glm.transformer.layers.46.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
509
+ "glm.transformer.layers.46.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
510
+ "glm.transformer.layers.46.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
511
+ "glm.transformer.layers.46.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
512
+ "glm.transformer.layers.46.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
513
+ "glm.transformer.layers.47.attention.dense.bias": "pytorch_model-00004-of-00004.bin",
514
+ "glm.transformer.layers.47.attention.dense.weight": "pytorch_model-00004-of-00004.bin",
515
+ "glm.transformer.layers.47.attention.query_key_value.bias": "pytorch_model-00004-of-00004.bin",
516
+ "glm.transformer.layers.47.attention.query_key_value.weight": "pytorch_model-00004-of-00004.bin",
517
+ "glm.transformer.layers.47.input_layernorm.bias": "pytorch_model-00004-of-00004.bin",
518
+ "glm.transformer.layers.47.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
519
+ "glm.transformer.layers.47.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
520
+ "glm.transformer.layers.47.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
521
+ "glm.transformer.layers.47.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
522
+ "glm.transformer.layers.47.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
523
+ "glm.transformer.layers.47.post_attention_layernorm.bias": "pytorch_model-00004-of-00004.bin",
524
+ "glm.transformer.layers.47.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
525
+ "glm.transformer.layers.5.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
526
+ "glm.transformer.layers.5.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
527
+ "glm.transformer.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
528
+ "glm.transformer.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
529
+ "glm.transformer.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
530
+ "glm.transformer.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
531
+ "glm.transformer.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
532
+ "glm.transformer.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
533
+ "glm.transformer.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
534
+ "glm.transformer.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
535
+ "glm.transformer.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
536
+ "glm.transformer.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
537
+ "glm.transformer.layers.6.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
538
+ "glm.transformer.layers.6.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
539
+ "glm.transformer.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
540
+ "glm.transformer.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
541
+ "glm.transformer.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
542
+ "glm.transformer.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
543
+ "glm.transformer.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
544
+ "glm.transformer.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
545
+ "glm.transformer.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
546
+ "glm.transformer.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
547
+ "glm.transformer.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
548
+ "glm.transformer.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
549
+ "glm.transformer.layers.7.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
550
+ "glm.transformer.layers.7.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
551
+ "glm.transformer.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
552
+ "glm.transformer.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
553
+ "glm.transformer.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
554
+ "glm.transformer.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
555
+ "glm.transformer.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
556
+ "glm.transformer.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
557
+ "glm.transformer.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
558
+ "glm.transformer.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
559
+ "glm.transformer.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
560
+ "glm.transformer.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
561
+ "glm.transformer.layers.8.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
562
+ "glm.transformer.layers.8.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
563
+ "glm.transformer.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
564
+ "glm.transformer.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
565
+ "glm.transformer.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
566
+ "glm.transformer.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
567
+ "glm.transformer.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
568
+ "glm.transformer.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
569
+ "glm.transformer.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
570
+ "glm.transformer.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
571
+ "glm.transformer.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
572
+ "glm.transformer.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
573
+ "glm.transformer.layers.9.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
574
+ "glm.transformer.layers.9.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
575
+ "glm.transformer.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
576
+ "glm.transformer.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
577
+ "glm.transformer.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
578
+ "glm.transformer.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
579
+ "glm.transformer.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
580
+ "glm.transformer.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
581
+ "glm.transformer.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
582
+ "glm.transformer.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
583
+ "glm.transformer.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
584
+ "glm.transformer.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
585
+ "glm.transformer.position_embeddings.weight": "pytorch_model-00001-of-00004.bin",
586
+ "glm.word_embeddings.weight": "pytorch_model-00001-of-00004.bin"
587
+ }
588
+ }