scutcyr commited on
Commit
efea058
1 Parent(s): 253f9cd

update model json

Browse files
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "scutcyr/BianQue-2.0",
3
+ "architectures": [
4
+ "ChatGLMForConditionalGeneration"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_chatglm.ChatGLMConfig",
8
+ "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
9
+ "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration"
10
+ },
11
+ "bos_token_id": 130004,
12
+ "eos_token_id": 130005,
13
+ "gmask_token_id": 130001,
14
+ "hidden_size": 4096,
15
+ "inner_hidden_size": 16384,
16
+ "layernorm_epsilon": 1e-05,
17
+ "mask_token_id": 130000,
18
+ "max_sequence_length": 2048,
19
+ "model_type": "chatglm",
20
+ "num_attention_heads": 32,
21
+ "num_layers": 28,
22
+ "pad_token_id": 3,
23
+ "position_encoding_2d": true,
24
+ "pre_seq_len": null,
25
+ "prefix_projection": false,
26
+ "quantization_bit": 0,
27
+ "torch_dtype": "float16",
28
+ "transformers_version": "4.29.0.dev0",
29
+ "use_cache": true,
30
+ "vocab_size": 130528
31
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 130004,
4
+ "eos_token_id": 130005,
5
+ "pad_token_id": 3,
6
+ "transformers_version": "4.29.0.dev0"
7
+ }
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,375 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13415859968
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
+ "transformer.final_layernorm.bias": "pytorch_model-00003-of-00003.bin",
8
+ "transformer.final_layernorm.weight": "pytorch_model-00003-of-00003.bin",
9
+ "transformer.layers.0.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
10
+ "transformer.layers.0.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
11
+ "transformer.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
12
+ "transformer.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
13
+ "transformer.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
14
+ "transformer.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
15
+ "transformer.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
16
+ "transformer.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
17
+ "transformer.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
18
+ "transformer.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
19
+ "transformer.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
20
+ "transformer.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
21
+ "transformer.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
22
+ "transformer.layers.1.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
23
+ "transformer.layers.1.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
24
+ "transformer.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
25
+ "transformer.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
26
+ "transformer.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
27
+ "transformer.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
28
+ "transformer.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
29
+ "transformer.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
30
+ "transformer.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
31
+ "transformer.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
32
+ "transformer.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
33
+ "transformer.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
34
+ "transformer.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
35
+ "transformer.layers.10.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
36
+ "transformer.layers.10.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
37
+ "transformer.layers.10.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
38
+ "transformer.layers.10.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
39
+ "transformer.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
40
+ "transformer.layers.10.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
41
+ "transformer.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
42
+ "transformer.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
43
+ "transformer.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
44
+ "transformer.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
45
+ "transformer.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
46
+ "transformer.layers.10.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
47
+ "transformer.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
48
+ "transformer.layers.11.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
49
+ "transformer.layers.11.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
50
+ "transformer.layers.11.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
51
+ "transformer.layers.11.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
52
+ "transformer.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
53
+ "transformer.layers.11.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
54
+ "transformer.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
55
+ "transformer.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
56
+ "transformer.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
57
+ "transformer.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
58
+ "transformer.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
59
+ "transformer.layers.11.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
60
+ "transformer.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
61
+ "transformer.layers.12.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
62
+ "transformer.layers.12.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
63
+ "transformer.layers.12.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
64
+ "transformer.layers.12.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
65
+ "transformer.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
66
+ "transformer.layers.12.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
67
+ "transformer.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
68
+ "transformer.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
69
+ "transformer.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
70
+ "transformer.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
71
+ "transformer.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
72
+ "transformer.layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
73
+ "transformer.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
74
+ "transformer.layers.13.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
75
+ "transformer.layers.13.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
76
+ "transformer.layers.13.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
77
+ "transformer.layers.13.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
78
+ "transformer.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
79
+ "transformer.layers.13.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
80
+ "transformer.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
81
+ "transformer.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
82
+ "transformer.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
83
+ "transformer.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
84
+ "transformer.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
85
+ "transformer.layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
86
+ "transformer.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
87
+ "transformer.layers.14.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
88
+ "transformer.layers.14.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
89
+ "transformer.layers.14.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
90
+ "transformer.layers.14.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
91
+ "transformer.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
92
+ "transformer.layers.14.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
93
+ "transformer.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
94
+ "transformer.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
95
+ "transformer.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
96
+ "transformer.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
97
+ "transformer.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
98
+ "transformer.layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
99
+ "transformer.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
100
+ "transformer.layers.15.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
101
+ "transformer.layers.15.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
102
+ "transformer.layers.15.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
103
+ "transformer.layers.15.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
104
+ "transformer.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
105
+ "transformer.layers.15.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
106
+ "transformer.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
107
+ "transformer.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
108
+ "transformer.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
109
+ "transformer.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
110
+ "transformer.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
111
+ "transformer.layers.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
112
+ "transformer.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
113
+ "transformer.layers.16.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
114
+ "transformer.layers.16.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
115
+ "transformer.layers.16.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
116
+ "transformer.layers.16.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
117
+ "transformer.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
118
+ "transformer.layers.16.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
119
+ "transformer.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
120
+ "transformer.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
121
+ "transformer.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
122
+ "transformer.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
123
+ "transformer.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
124
+ "transformer.layers.16.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
125
+ "transformer.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
126
+ "transformer.layers.17.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
127
+ "transformer.layers.17.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
128
+ "transformer.layers.17.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
129
+ "transformer.layers.17.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
130
+ "transformer.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
131
+ "transformer.layers.17.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
132
+ "transformer.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
133
+ "transformer.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
134
+ "transformer.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
135
+ "transformer.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
136
+ "transformer.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
137
+ "transformer.layers.17.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
138
+ "transformer.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
+ "transformer.layers.18.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
140
+ "transformer.layers.18.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
141
+ "transformer.layers.18.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
142
+ "transformer.layers.18.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
143
+ "transformer.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
144
+ "transformer.layers.18.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
145
+ "transformer.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
146
+ "transformer.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
147
+ "transformer.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
148
+ "transformer.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
149
+ "transformer.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
150
+ "transformer.layers.18.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
151
+ "transformer.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
152
+ "transformer.layers.19.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
153
+ "transformer.layers.19.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
154
+ "transformer.layers.19.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
155
+ "transformer.layers.19.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
156
+ "transformer.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
157
+ "transformer.layers.19.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
158
+ "transformer.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
159
+ "transformer.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
160
+ "transformer.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
161
+ "transformer.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
162
+ "transformer.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
163
+ "transformer.layers.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
164
+ "transformer.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
165
+ "transformer.layers.2.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
166
+ "transformer.layers.2.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
167
+ "transformer.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
168
+ "transformer.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
169
+ "transformer.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
170
+ "transformer.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
171
+ "transformer.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
172
+ "transformer.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
173
+ "transformer.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
174
+ "transformer.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
175
+ "transformer.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
176
+ "transformer.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
177
+ "transformer.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
178
+ "transformer.layers.20.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
179
+ "transformer.layers.20.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
180
+ "transformer.layers.20.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
181
+ "transformer.layers.20.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
182
+ "transformer.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
183
+ "transformer.layers.20.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
184
+ "transformer.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
185
+ "transformer.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
186
+ "transformer.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
187
+ "transformer.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
188
+ "transformer.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
189
+ "transformer.layers.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
190
+ "transformer.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
191
+ "transformer.layers.21.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
192
+ "transformer.layers.21.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
193
+ "transformer.layers.21.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
194
+ "transformer.layers.21.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
195
+ "transformer.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
196
+ "transformer.layers.21.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
197
+ "transformer.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
198
+ "transformer.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
199
+ "transformer.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
200
+ "transformer.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
201
+ "transformer.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
202
+ "transformer.layers.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
203
+ "transformer.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
204
+ "transformer.layers.22.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
205
+ "transformer.layers.22.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
206
+ "transformer.layers.22.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
207
+ "transformer.layers.22.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
208
+ "transformer.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
209
+ "transformer.layers.22.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
210
+ "transformer.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
211
+ "transformer.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
212
+ "transformer.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
213
+ "transformer.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
214
+ "transformer.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
215
+ "transformer.layers.22.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
216
+ "transformer.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
217
+ "transformer.layers.23.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
218
+ "transformer.layers.23.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
219
+ "transformer.layers.23.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
220
+ "transformer.layers.23.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
221
+ "transformer.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
222
+ "transformer.layers.23.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
223
+ "transformer.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
224
+ "transformer.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
225
+ "transformer.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
226
+ "transformer.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
227
+ "transformer.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
228
+ "transformer.layers.23.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
229
+ "transformer.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
230
+ "transformer.layers.24.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
231
+ "transformer.layers.24.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
232
+ "transformer.layers.24.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
233
+ "transformer.layers.24.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
234
+ "transformer.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
235
+ "transformer.layers.24.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
236
+ "transformer.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
237
+ "transformer.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
238
+ "transformer.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
239
+ "transformer.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
240
+ "transformer.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
241
+ "transformer.layers.24.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
242
+ "transformer.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
243
+ "transformer.layers.25.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
244
+ "transformer.layers.25.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
245
+ "transformer.layers.25.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
246
+ "transformer.layers.25.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
247
+ "transformer.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
248
+ "transformer.layers.25.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
249
+ "transformer.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
250
+ "transformer.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
251
+ "transformer.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
252
+ "transformer.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
253
+ "transformer.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
254
+ "transformer.layers.25.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
255
+ "transformer.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
256
+ "transformer.layers.26.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
257
+ "transformer.layers.26.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
258
+ "transformer.layers.26.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
259
+ "transformer.layers.26.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
260
+ "transformer.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
261
+ "transformer.layers.26.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
262
+ "transformer.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
263
+ "transformer.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
264
+ "transformer.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
265
+ "transformer.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
266
+ "transformer.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
267
+ "transformer.layers.26.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
268
+ "transformer.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
269
+ "transformer.layers.27.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
270
+ "transformer.layers.27.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
271
+ "transformer.layers.27.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
272
+ "transformer.layers.27.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
273
+ "transformer.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
274
+ "transformer.layers.27.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
275
+ "transformer.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
276
+ "transformer.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
277
+ "transformer.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
278
+ "transformer.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
279
+ "transformer.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
280
+ "transformer.layers.27.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
281
+ "transformer.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
282
+ "transformer.layers.3.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
283
+ "transformer.layers.3.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
284
+ "transformer.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
285
+ "transformer.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
286
+ "transformer.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
287
+ "transformer.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
288
+ "transformer.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
289
+ "transformer.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
290
+ "transformer.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
291
+ "transformer.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
292
+ "transformer.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
293
+ "transformer.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
294
+ "transformer.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
295
+ "transformer.layers.4.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
296
+ "transformer.layers.4.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
297
+ "transformer.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
298
+ "transformer.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
299
+ "transformer.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
300
+ "transformer.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
301
+ "transformer.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
302
+ "transformer.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
303
+ "transformer.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
304
+ "transformer.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
305
+ "transformer.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
306
+ "transformer.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
307
+ "transformer.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
308
+ "transformer.layers.5.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
309
+ "transformer.layers.5.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
310
+ "transformer.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
311
+ "transformer.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
312
+ "transformer.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
313
+ "transformer.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
314
+ "transformer.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
315
+ "transformer.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
316
+ "transformer.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
317
+ "transformer.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
318
+ "transformer.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
319
+ "transformer.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
320
+ "transformer.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
321
+ "transformer.layers.6.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
322
+ "transformer.layers.6.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
323
+ "transformer.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
324
+ "transformer.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
325
+ "transformer.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
326
+ "transformer.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
327
+ "transformer.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
328
+ "transformer.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
329
+ "transformer.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
330
+ "transformer.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
331
+ "transformer.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
332
+ "transformer.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
333
+ "transformer.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
334
+ "transformer.layers.7.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
335
+ "transformer.layers.7.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
336
+ "transformer.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
337
+ "transformer.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
338
+ "transformer.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
339
+ "transformer.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
340
+ "transformer.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
341
+ "transformer.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
342
+ "transformer.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
343
+ "transformer.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
344
+ "transformer.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
345
+ "transformer.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
346
+ "transformer.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
347
+ "transformer.layers.8.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
348
+ "transformer.layers.8.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
349
+ "transformer.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
350
+ "transformer.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
351
+ "transformer.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
352
+ "transformer.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
353
+ "transformer.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
354
+ "transformer.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
355
+ "transformer.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
356
+ "transformer.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
357
+ "transformer.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
358
+ "transformer.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
359
+ "transformer.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
360
+ "transformer.layers.9.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
361
+ "transformer.layers.9.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
362
+ "transformer.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
363
+ "transformer.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
364
+ "transformer.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
365
+ "transformer.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
366
+ "transformer.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
367
+ "transformer.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
368
+ "transformer.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
369
+ "transformer.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
370
+ "transformer.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
371
+ "transformer.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
372
+ "transformer.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
373
+ "transformer.word_embeddings.weight": "pytorch_model-00001-of-00003.bin"
374
+ }
375
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<sop>",
3
+ "eos_token": "<eop>",
4
+ "mask_token": "[MASK]",
5
+ "pad_token": "<pad>",
6
+ "unk_token": "<unk>"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_map": {
3
+ "AutoTokenizer": [
4
+ "tokenization_chatglm.ChatGLMTokenizer",
5
+ null
6
+ ]
7
+ },
8
+ "bos_token": "<sop>",
9
+ "clean_up_tokenization_spaces": true,
10
+ "do_lower_case": false,
11
+ "end_token": "</s>",
12
+ "eos_token": "<eop>",
13
+ "gmask_token": "[gMASK]",
14
+ "mask_token": "[MASK]",
15
+ "model_max_length": 1000000000000000019884624838656,
16
+ "num_image_tokens": 0,
17
+ "pad_token": "<pad>",
18
+ "padding_side": "left",
19
+ "remove_space": false,
20
+ "tokenizer_class": "ChatGLMTokenizer",
21
+ "unk_token": "<unk>"
22
+ }