Hugging Face's logo

WHJ1998
/
cpm-bee-10b-shard-1GB

Feature Extraction
Transformers
PyTorch
cpmbee
custom_code
Model card Files Community
WHJ1998 commited on
Commit
db1239d
·
1 Parent(s): 04e7224

Upload CpmBeeForCausalLM

Browse files
Files changed (23) hide show
  1. config.json +224 -0
  2. generation_config.json +11 -0
  3. pytorch_model-00001-of-00020.bin +3 -0
  4. pytorch_model-00002-of-00020.bin +3 -0
  5. pytorch_model-00003-of-00020.bin +3 -0
  6. pytorch_model-00004-of-00020.bin +3 -0
  7. pytorch_model-00005-of-00020.bin +3 -0
  8. pytorch_model-00006-of-00020.bin +3 -0
  9. pytorch_model-00007-of-00020.bin +3 -0
  10. pytorch_model-00008-of-00020.bin +3 -0
  11. pytorch_model-00009-of-00020.bin +3 -0
  12. pytorch_model-00010-of-00020.bin +3 -0
  13. pytorch_model-00011-of-00020.bin +3 -0
  14. pytorch_model-00012-of-00020.bin +3 -0
  15. pytorch_model-00013-of-00020.bin +3 -0
  16. pytorch_model-00014-of-00020.bin +3 -0
  17. pytorch_model-00015-of-00020.bin +3 -0
  18. pytorch_model-00016-of-00020.bin +3 -0
  19. pytorch_model-00017-of-00020.bin +3 -0
  20. pytorch_model-00018-of-00020.bin +3 -0
  21. pytorch_model-00019-of-00020.bin +3 -0
  22. pytorch_model-00020-of-00020.bin +3 -0
  23. pytorch_model.bin.index.json +443 -0
config.json ADDED
@@ -0,0 +1,224 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "_name_or_path": "openbmb/cpm-bee-10b",
4
+ "architectures": [
5
+ "CpmBeeForCausalLM"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "openbmb/cpm-bee-10b--configuration_cpmbee.CpmBeeConfig",
9
+ "AutoModel": "openbmb/cpm-bee-10b--modeling_cpmbee.CpmBeeForCausalLM",
10
+ "AutoModelForCausalLM": "openbmb/cpm-bee-10b--modeling_cpmbee.CpmBeeForCausalLM"
11
+ },
12
+ "dim_ff": 10240,
13
+ "dim_head": 128,
14
+ "distance_scale": 16,
15
+ "dropout_p": 0.0,
16
+ "eps": 1e-06,
17
+ "half": true,
18
+ "hidden_size": 4096,
19
+ "init_std": 1.0,
20
+ "mask_modules": [
21
+ [
22
+ false,
23
+ false
24
+ ],
25
+ [
26
+ false,
27
+ false
28
+ ],
29
+ [
30
+ false,
31
+ false
32
+ ],
33
+ [
34
+ false,
35
+ false
36
+ ],
37
+ [
38
+ false,
39
+ false
40
+ ],
41
+ [
42
+ false,
43
+ false
44
+ ],
45
+ [
46
+ false,
47
+ false
48
+ ],
49
+ [
50
+ false,
51
+ false
52
+ ],
53
+ [
54
+ false,
55
+ false
56
+ ],
57
+ [
58
+ false,
59
+ false
60
+ ],
61
+ [
62
+ false,
63
+ false
64
+ ],
65
+ [
66
+ false,
67
+ false
68
+ ],
69
+ [
70
+ false,
71
+ false
72
+ ],
73
+ [
74
+ false,
75
+ false
76
+ ],
77
+ [
78
+ false,
79
+ false
80
+ ],
81
+ [
82
+ false,
83
+ false
84
+ ],
85
+ [
86
+ false,
87
+ false
88
+ ],
89
+ [
90
+ false,
91
+ false
92
+ ],
93
+ [
94
+ false,
95
+ false
96
+ ],
97
+ [
98
+ false,
99
+ false
100
+ ],
101
+ [
102
+ false,
103
+ false
104
+ ],
105
+ [
106
+ false,
107
+ false
108
+ ],
109
+ [
110
+ false,
111
+ false
112
+ ],
113
+ [
114
+ false,
115
+ false
116
+ ],
117
+ [
118
+ false,
119
+ false
120
+ ],
121
+ [
122
+ false,
123
+ false
124
+ ],
125
+ [
126
+ false,
127
+ false
128
+ ],
129
+ [
130
+ false,
131
+ false
132
+ ],
133
+ [
134
+ false,
135
+ false
136
+ ],
137
+ [
138
+ false,
139
+ false
140
+ ],
141
+ [
142
+ false,
143
+ false
144
+ ],
145
+ [
146
+ false,
147
+ false
148
+ ],
149
+ [
150
+ false,
151
+ false
152
+ ],
153
+ [
154
+ false,
155
+ false
156
+ ],
157
+ [
158
+ false,
159
+ false
160
+ ],
161
+ [
162
+ false,
163
+ false
164
+ ],
165
+ [
166
+ false,
167
+ false
168
+ ],
169
+ [
170
+ false,
171
+ false
172
+ ],
173
+ [
174
+ false,
175
+ false
176
+ ],
177
+ [
178
+ false,
179
+ false
180
+ ],
181
+ [
182
+ false,
183
+ false
184
+ ],
185
+ [
186
+ false,
187
+ false
188
+ ],
189
+ [
190
+ false,
191
+ false
192
+ ],
193
+ [
194
+ false,
195
+ false
196
+ ],
197
+ [
198
+ false,
199
+ false
200
+ ],
201
+ [
202
+ false,
203
+ false
204
+ ],
205
+ [
206
+ false,
207
+ false
208
+ ],
209
+ [
210
+ false,
211
+ false
212
+ ]
213
+ ],
214
+ "model_type": "cpmbee",
215
+ "num_attention_heads": 32,
216
+ "num_hidden_layers": 48,
217
+ "position_bias_max_distance": 2048,
218
+ "position_bias_num_buckets": 256,
219
+ "position_bias_num_segment_buckets": 256,
220
+ "torch_dtype": "float16",
221
+ "transformers_version": "4.30.2",
222
+ "use_cache": true,
223
+ "vocab_size": 86583
224
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 6,
3
+ "eos_token_id": 7,
4
+ "is_constraint_gen_mode": false,
5
+ "is_contrastive_search_gen_mode": false,
6
+ "max_new_tokens": 100,
7
+ "num_beams": 3,
8
+ "pad_token_id": 0,
9
+ "transformers_version": "4.30.2",
10
+ "vocab_size": 86583
11
+ }
pytorch_model-00001-of-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18daf2a511a5b6c4199625c9b8e23cc5164a7f431584bfc9023d672ea255dc56
3
+ size 989913873
pytorch_model-00002-of-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5430783b0815b6e845437988126026bf936822ace34a36f0f2ab0ff660f0a390
3
+ size 973127387
pytorch_model-00003-of-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f20bb1d250fb9f00f877883eab587907410fb6e843c1e541f99fded75846f15
3
+ size 956350573
pytorch_model-00004-of-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:154e226bdbf7c5dfd1077592334629f514037de26ca1f99302aac38eb0c8d2c7
3
+ size 973127387
pytorch_model-00005-of-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3b966b94b47b797051643f9d85306fa51ebe26732cbf86ebb47874142630320
3
+ size 956350573
pytorch_model-00006-of-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23a678dcbe7a722720ebf3902937ff8f99acbe5dccdda5f9474b36f1ea4047ac
3
+ size 973127451
pytorch_model-00007-of-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f26ed5158376a2bcc2d23292abb6786dae04bcab0df948f818754c9df69e80b
3
+ size 956350573
pytorch_model-00008-of-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dd4d9f201cc05e0c1dce20cf7cf91fa1f8385b162743ced195ba1d5651e6841
3
+ size 973127451
pytorch_model-00009-of-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4127b865f63ddf20b03fdf6be02e8f91ac5ac4a64173c1fe0563130199585e55
3
+ size 956350573
pytorch_model-00010-of-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9228b387e17a5eef200ab4e4672a74b1572c437161af5f283002693d05bb5cd
3
+ size 973127451
pytorch_model-00011-of-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4137a09b4e4106914b631b5b65fce8e9934198a5a68f8ea5316a8066a3ee74e2
3
+ size 956350573
pytorch_model-00012-of-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed78a582ab399f625b2400414d382e73c4fa6876849db4d93845ce226ff0e0d0
3
+ size 973127451
pytorch_model-00013-of-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a05dd6d411b00be8074e0c57230112cbf91f96da3ed8d63fae4c37f71eb1648
3
+ size 956350573
pytorch_model-00014-of-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ba88658f3b588810d142c52bd134e4eddce9371b8fe83e685f8105fa9afce03
3
+ size 973127451
pytorch_model-00015-of-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75089e67028dfb4533bb81ea48676a2e72f796d48e6fbbcf454ddb964a89993c
3
+ size 956350573
pytorch_model-00016-of-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9512b1fcb4bcf1b956c2ee707793928d8935a7097806386692ad24175818d4ad
3
+ size 973127451
pytorch_model-00017-of-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b27b4d013be2d85b7b16dc7dafe92ad9fea4fe17f1ee455899c31505e4148e85
3
+ size 956350573
pytorch_model-00018-of-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a435dfcca23d97ad77af72e2a54798659004aade474aefddfb89bd65833831fd
3
+ size 973127451
pytorch_model-00019-of-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa3ca32728af63c38d6bc47761f7cc4aaa275de0bea076008e9ea102c6beec19
3
+ size 956350573
pytorch_model-00020-of-00020.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b0b1263af86d9b0fc02dd8dd881c020a68b167dea29fccf28ec7ff6adc7d92a
3
+ size 877103342
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,443 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 19232161792
4
+ },
5
+ "weight_map": {
6
+ "cpmbee.encoder.layers.0.ffn.ffn.w_in.w_0.weight": "pytorch_model-00001-of-00020.bin",
7
+ "cpmbee.encoder.layers.0.ffn.ffn.w_in.w_1.weight": "pytorch_model-00001-of-00020.bin",
8
+ "cpmbee.encoder.layers.0.ffn.ffn.w_out.weight": "pytorch_model-00001-of-00020.bin",
9
+ "cpmbee.encoder.layers.0.ffn.layernorm_before_ffn.weight": "pytorch_model-00001-of-00020.bin",
10
+ "cpmbee.encoder.layers.0.self_att.layernorm_before_attention.weight": "pytorch_model-00001-of-00020.bin",
11
+ "cpmbee.encoder.layers.0.self_att.self_attention.attention_out.weight": "pytorch_model-00001-of-00020.bin",
12
+ "cpmbee.encoder.layers.0.self_att.self_attention.project_k.weight": "pytorch_model-00001-of-00020.bin",
13
+ "cpmbee.encoder.layers.0.self_att.self_attention.project_q.weight": "pytorch_model-00001-of-00020.bin",
14
+ "cpmbee.encoder.layers.0.self_att.self_attention.project_v.weight": "pytorch_model-00001-of-00020.bin",
15
+ "cpmbee.encoder.layers.1.ffn.ffn.w_in.w_0.weight": "pytorch_model-00001-of-00020.bin",
16
+ "cpmbee.encoder.layers.1.ffn.ffn.w_in.w_1.weight": "pytorch_model-00001-of-00020.bin",
17
+ "cpmbee.encoder.layers.1.ffn.ffn.w_out.weight": "pytorch_model-00001-of-00020.bin",
18
+ "cpmbee.encoder.layers.1.ffn.layernorm_before_ffn.weight": "pytorch_model-00001-of-00020.bin",
19
+ "cpmbee.encoder.layers.1.self_att.layernorm_before_attention.weight": "pytorch_model-00001-of-00020.bin",
20
+ "cpmbee.encoder.layers.1.self_att.self_attention.attention_out.weight": "pytorch_model-00001-of-00020.bin",
21
+ "cpmbee.encoder.layers.1.self_att.self_attention.project_k.weight": "pytorch_model-00001-of-00020.bin",
22
+ "cpmbee.encoder.layers.1.self_att.self_attention.project_q.weight": "pytorch_model-00001-of-00020.bin",
23
+ "cpmbee.encoder.layers.1.self_att.self_attention.project_v.weight": "pytorch_model-00001-of-00020.bin",
24
+ "cpmbee.encoder.layers.10.ffn.ffn.w_in.w_0.weight": "pytorch_model-00005-of-00020.bin",
25
+ "cpmbee.encoder.layers.10.ffn.ffn.w_in.w_1.weight": "pytorch_model-00005-of-00020.bin",
26
+ "cpmbee.encoder.layers.10.ffn.ffn.w_out.weight": "pytorch_model-00005-of-00020.bin",
27
+ "cpmbee.encoder.layers.10.ffn.layernorm_before_ffn.weight": "pytorch_model-00005-of-00020.bin",
28
+ "cpmbee.encoder.layers.10.self_att.layernorm_before_attention.weight": "pytorch_model-00004-of-00020.bin",
29
+ "cpmbee.encoder.layers.10.self_att.self_attention.attention_out.weight": "pytorch_model-00005-of-00020.bin",
30
+ "cpmbee.encoder.layers.10.self_att.self_attention.project_k.weight": "pytorch_model-00005-of-00020.bin",
31
+ "cpmbee.encoder.layers.10.self_att.self_attention.project_q.weight": "pytorch_model-00004-of-00020.bin",
32
+ "cpmbee.encoder.layers.10.self_att.self_attention.project_v.weight": "pytorch_model-00005-of-00020.bin",
33
+ "cpmbee.encoder.layers.11.ffn.ffn.w_in.w_0.weight": "pytorch_model-00005-of-00020.bin",
34
+ "cpmbee.encoder.layers.11.ffn.ffn.w_in.w_1.weight": "pytorch_model-00005-of-00020.bin",
35
+ "cpmbee.encoder.layers.11.ffn.ffn.w_out.weight": "pytorch_model-00005-of-00020.bin",
36
+ "cpmbee.encoder.layers.11.ffn.layernorm_before_ffn.weight": "pytorch_model-00005-of-00020.bin",
37
+ "cpmbee.encoder.layers.11.self_att.layernorm_before_attention.weight": "pytorch_model-00005-of-00020.bin",
38
+ "cpmbee.encoder.layers.11.self_att.self_attention.attention_out.weight": "pytorch_model-00005-of-00020.bin",
39
+ "cpmbee.encoder.layers.11.self_att.self_attention.project_k.weight": "pytorch_model-00005-of-00020.bin",
40
+ "cpmbee.encoder.layers.11.self_att.self_attention.project_q.weight": "pytorch_model-00005-of-00020.bin",
41
+ "cpmbee.encoder.layers.11.self_att.self_attention.project_v.weight": "pytorch_model-00005-of-00020.bin",
42
+ "cpmbee.encoder.layers.12.ffn.ffn.w_in.w_0.weight": "pytorch_model-00005-of-00020.bin",
43
+ "cpmbee.encoder.layers.12.ffn.ffn.w_in.w_1.weight": "pytorch_model-00006-of-00020.bin",
44
+ "cpmbee.encoder.layers.12.ffn.ffn.w_out.weight": "pytorch_model-00006-of-00020.bin",
45
+ "cpmbee.encoder.layers.12.ffn.layernorm_before_ffn.weight": "pytorch_model-00005-of-00020.bin",
46
+ "cpmbee.encoder.layers.12.self_att.layernorm_before_attention.weight": "pytorch_model-00005-of-00020.bin",
47
+ "cpmbee.encoder.layers.12.self_att.self_attention.attention_out.weight": "pytorch_model-00005-of-00020.bin",
48
+ "cpmbee.encoder.layers.12.self_att.self_attention.project_k.weight": "pytorch_model-00005-of-00020.bin",
49
+ "cpmbee.encoder.layers.12.self_att.self_attention.project_q.weight": "pytorch_model-00005-of-00020.bin",
50
+ "cpmbee.encoder.layers.12.self_att.self_attention.project_v.weight": "pytorch_model-00005-of-00020.bin",
51
+ "cpmbee.encoder.layers.13.ffn.ffn.w_in.w_0.weight": "pytorch_model-00006-of-00020.bin",
52
+ "cpmbee.encoder.layers.13.ffn.ffn.w_in.w_1.weight": "pytorch_model-00006-of-00020.bin",
53
+ "cpmbee.encoder.layers.13.ffn.ffn.w_out.weight": "pytorch_model-00006-of-00020.bin",
54
+ "cpmbee.encoder.layers.13.ffn.layernorm_before_ffn.weight": "pytorch_model-00006-of-00020.bin",
55
+ "cpmbee.encoder.layers.13.self_att.layernorm_before_attention.weight": "pytorch_model-00006-of-00020.bin",
56
+ "cpmbee.encoder.layers.13.self_att.self_attention.attention_out.weight": "pytorch_model-00006-of-00020.bin",
57
+ "cpmbee.encoder.layers.13.self_att.self_attention.project_k.weight": "pytorch_model-00006-of-00020.bin",
58
+ "cpmbee.encoder.layers.13.self_att.self_attention.project_q.weight": "pytorch_model-00006-of-00020.bin",
59
+ "cpmbee.encoder.layers.13.self_att.self_attention.project_v.weight": "pytorch_model-00006-of-00020.bin",
60
+ "cpmbee.encoder.layers.14.ffn.ffn.w_in.w_0.weight": "pytorch_model-00006-of-00020.bin",
61
+ "cpmbee.encoder.layers.14.ffn.ffn.w_in.w_1.weight": "pytorch_model-00006-of-00020.bin",
62
+ "cpmbee.encoder.layers.14.ffn.ffn.w_out.weight": "pytorch_model-00006-of-00020.bin",
63
+ "cpmbee.encoder.layers.14.ffn.layernorm_before_ffn.weight": "pytorch_model-00006-of-00020.bin",
64
+ "cpmbee.encoder.layers.14.self_att.layernorm_before_attention.weight": "pytorch_model-00006-of-00020.bin",
65
+ "cpmbee.encoder.layers.14.self_att.self_attention.attention_out.weight": "pytorch_model-00006-of-00020.bin",
66
+ "cpmbee.encoder.layers.14.self_att.self_attention.project_k.weight": "pytorch_model-00006-of-00020.bin",
67
+ "cpmbee.encoder.layers.14.self_att.self_attention.project_q.weight": "pytorch_model-00006-of-00020.bin",
68
+ "cpmbee.encoder.layers.14.self_att.self_attention.project_v.weight": "pytorch_model-00006-of-00020.bin",
69
+ "cpmbee.encoder.layers.15.ffn.ffn.w_in.w_0.weight": "pytorch_model-00007-of-00020.bin",
70
+ "cpmbee.encoder.layers.15.ffn.ffn.w_in.w_1.weight": "pytorch_model-00007-of-00020.bin",
71
+ "cpmbee.encoder.layers.15.ffn.ffn.w_out.weight": "pytorch_model-00007-of-00020.bin",
72
+ "cpmbee.encoder.layers.15.ffn.layernorm_before_ffn.weight": "pytorch_model-00007-of-00020.bin",
73
+ "cpmbee.encoder.layers.15.self_att.layernorm_before_attention.weight": "pytorch_model-00006-of-00020.bin",
74
+ "cpmbee.encoder.layers.15.self_att.self_attention.attention_out.weight": "pytorch_model-00007-of-00020.bin",
75
+ "cpmbee.encoder.layers.15.self_att.self_attention.project_k.weight": "pytorch_model-00007-of-00020.bin",
76
+ "cpmbee.encoder.layers.15.self_att.self_attention.project_q.weight": "pytorch_model-00006-of-00020.bin",
77
+ "cpmbee.encoder.layers.15.self_att.self_attention.project_v.weight": "pytorch_model-00007-of-00020.bin",
78
+ "cpmbee.encoder.layers.16.ffn.ffn.w_in.w_0.weight": "pytorch_model-00007-of-00020.bin",
79
+ "cpmbee.encoder.layers.16.ffn.ffn.w_in.w_1.weight": "pytorch_model-00007-of-00020.bin",
80
+ "cpmbee.encoder.layers.16.ffn.ffn.w_out.weight": "pytorch_model-00007-of-00020.bin",
81
+ "cpmbee.encoder.layers.16.ffn.layernorm_before_ffn.weight": "pytorch_model-00007-of-00020.bin",
82
+ "cpmbee.encoder.layers.16.self_att.layernorm_before_attention.weight": "pytorch_model-00007-of-00020.bin",
83
+ "cpmbee.encoder.layers.16.self_att.self_attention.attention_out.weight": "pytorch_model-00007-of-00020.bin",
84
+ "cpmbee.encoder.layers.16.self_att.self_attention.project_k.weight": "pytorch_model-00007-of-00020.bin",
85
+ "cpmbee.encoder.layers.16.self_att.self_attention.project_q.weight": "pytorch_model-00007-of-00020.bin",
86
+ "cpmbee.encoder.layers.16.self_att.self_attention.project_v.weight": "pytorch_model-00007-of-00020.bin",
87
+ "cpmbee.encoder.layers.17.ffn.ffn.w_in.w_0.weight": "pytorch_model-00007-of-00020.bin",
88
+ "cpmbee.encoder.layers.17.ffn.ffn.w_in.w_1.weight": "pytorch_model-00008-of-00020.bin",
89
+ "cpmbee.encoder.layers.17.ffn.ffn.w_out.weight": "pytorch_model-00008-of-00020.bin",
90
+ "cpmbee.encoder.layers.17.ffn.layernorm_before_ffn.weight": "pytorch_model-00007-of-00020.bin",
91
+ "cpmbee.encoder.layers.17.self_att.layernorm_before_attention.weight": "pytorch_model-00007-of-00020.bin",
92
+ "cpmbee.encoder.layers.17.self_att.self_attention.attention_out.weight": "pytorch_model-00007-of-00020.bin",
93
+ "cpmbee.encoder.layers.17.self_att.self_attention.project_k.weight": "pytorch_model-00007-of-00020.bin",
94
+ "cpmbee.encoder.layers.17.self_att.self_attention.project_q.weight": "pytorch_model-00007-of-00020.bin",
95
+ "cpmbee.encoder.layers.17.self_att.self_attention.project_v.weight": "pytorch_model-00007-of-00020.bin",
96
+ "cpmbee.encoder.layers.18.ffn.ffn.w_in.w_0.weight": "pytorch_model-00008-of-00020.bin",
97
+ "cpmbee.encoder.layers.18.ffn.ffn.w_in.w_1.weight": "pytorch_model-00008-of-00020.bin",
98
+ "cpmbee.encoder.layers.18.ffn.ffn.w_out.weight": "pytorch_model-00008-of-00020.bin",
99
+ "cpmbee.encoder.layers.18.ffn.layernorm_before_ffn.weight": "pytorch_model-00008-of-00020.bin",
100
+ "cpmbee.encoder.layers.18.self_att.layernorm_before_attention.weight": "pytorch_model-00008-of-00020.bin",
101
+ "cpmbee.encoder.layers.18.self_att.self_attention.attention_out.weight": "pytorch_model-00008-of-00020.bin",
102
+ "cpmbee.encoder.layers.18.self_att.self_attention.project_k.weight": "pytorch_model-00008-of-00020.bin",
103
+ "cpmbee.encoder.layers.18.self_att.self_attention.project_q.weight": "pytorch_model-00008-of-00020.bin",
104
+ "cpmbee.encoder.layers.18.self_att.self_attention.project_v.weight": "pytorch_model-00008-of-00020.bin",
105
+ "cpmbee.encoder.layers.19.ffn.ffn.w_in.w_0.weight": "pytorch_model-00008-of-00020.bin",
106
+ "cpmbee.encoder.layers.19.ffn.ffn.w_in.w_1.weight": "pytorch_model-00008-of-00020.bin",
107
+ "cpmbee.encoder.layers.19.ffn.ffn.w_out.weight": "pytorch_model-00008-of-00020.bin",
108
+ "cpmbee.encoder.layers.19.ffn.layernorm_before_ffn.weight": "pytorch_model-00008-of-00020.bin",
109
+ "cpmbee.encoder.layers.19.self_att.layernorm_before_attention.weight": "pytorch_model-00008-of-00020.bin",
110
+ "cpmbee.encoder.layers.19.self_att.self_attention.attention_out.weight": "pytorch_model-00008-of-00020.bin",
111
+ "cpmbee.encoder.layers.19.self_att.self_attention.project_k.weight": "pytorch_model-00008-of-00020.bin",
112
+ "cpmbee.encoder.layers.19.self_att.self_attention.project_q.weight": "pytorch_model-00008-of-00020.bin",
113
+ "cpmbee.encoder.layers.19.self_att.self_attention.project_v.weight": "pytorch_model-00008-of-00020.bin",
114
+ "cpmbee.encoder.layers.2.ffn.ffn.w_in.w_0.weight": "pytorch_model-00001-of-00020.bin",
115
+ "cpmbee.encoder.layers.2.ffn.ffn.w_in.w_1.weight": "pytorch_model-00002-of-00020.bin",
116
+ "cpmbee.encoder.layers.2.ffn.ffn.w_out.weight": "pytorch_model-00002-of-00020.bin",
117
+ "cpmbee.encoder.layers.2.ffn.layernorm_before_ffn.weight": "pytorch_model-00001-of-00020.bin",
118
+ "cpmbee.encoder.layers.2.self_att.layernorm_before_attention.weight": "pytorch_model-00001-of-00020.bin",
119
+ "cpmbee.encoder.layers.2.self_att.self_attention.attention_out.weight": "pytorch_model-00001-of-00020.bin",
120
+ "cpmbee.encoder.layers.2.self_att.self_attention.project_k.weight": "pytorch_model-00001-of-00020.bin",
121
+ "cpmbee.encoder.layers.2.self_att.self_attention.project_q.weight": "pytorch_model-00001-of-00020.bin",
122
+ "cpmbee.encoder.layers.2.self_att.self_attention.project_v.weight": "pytorch_model-00001-of-00020.bin",
123
+ "cpmbee.encoder.layers.20.ffn.ffn.w_in.w_0.weight": "pytorch_model-00009-of-00020.bin",
124
+ "cpmbee.encoder.layers.20.ffn.ffn.w_in.w_1.weight": "pytorch_model-00009-of-00020.bin",
125
+ "cpmbee.encoder.layers.20.ffn.ffn.w_out.weight": "pytorch_model-00009-of-00020.bin",
126
+ "cpmbee.encoder.layers.20.ffn.layernorm_before_ffn.weight": "pytorch_model-00009-of-00020.bin",
127
+ "cpmbee.encoder.layers.20.self_att.layernorm_before_attention.weight": "pytorch_model-00008-of-00020.bin",
128
+ "cpmbee.encoder.layers.20.self_att.self_attention.attention_out.weight": "pytorch_model-00009-of-00020.bin",
129
+ "cpmbee.encoder.layers.20.self_att.self_attention.project_k.weight": "pytorch_model-00009-of-00020.bin",
130
+ "cpmbee.encoder.layers.20.self_att.self_attention.project_q.weight": "pytorch_model-00008-of-00020.bin",
131
+ "cpmbee.encoder.layers.20.self_att.self_attention.project_v.weight": "pytorch_model-00009-of-00020.bin",
132
+ "cpmbee.encoder.layers.21.ffn.ffn.w_in.w_0.weight": "pytorch_model-00009-of-00020.bin",
133
+ "cpmbee.encoder.layers.21.ffn.ffn.w_in.w_1.weight": "pytorch_model-00009-of-00020.bin",
134
+ "cpmbee.encoder.layers.21.ffn.ffn.w_out.weight": "pytorch_model-00009-of-00020.bin",
135
+ "cpmbee.encoder.layers.21.ffn.layernorm_before_ffn.weight": "pytorch_model-00009-of-00020.bin",
136
+ "cpmbee.encoder.layers.21.self_att.layernorm_before_attention.weight": "pytorch_model-00009-of-00020.bin",
137
+ "cpmbee.encoder.layers.21.self_att.self_attention.attention_out.weight": "pytorch_model-00009-of-00020.bin",
138
+ "cpmbee.encoder.layers.21.self_att.self_attention.project_k.weight": "pytorch_model-00009-of-00020.bin",
139
+ "cpmbee.encoder.layers.21.self_att.self_attention.project_q.weight": "pytorch_model-00009-of-00020.bin",
140
+ "cpmbee.encoder.layers.21.self_att.self_attention.project_v.weight": "pytorch_model-00009-of-00020.bin",
141
+ "cpmbee.encoder.layers.22.ffn.ffn.w_in.w_0.weight": "pytorch_model-00009-of-00020.bin",
142
+ "cpmbee.encoder.layers.22.ffn.ffn.w_in.w_1.weight": "pytorch_model-00010-of-00020.bin",
143
+ "cpmbee.encoder.layers.22.ffn.ffn.w_out.weight": "pytorch_model-00010-of-00020.bin",
144
+ "cpmbee.encoder.layers.22.ffn.layernorm_before_ffn.weight": "pytorch_model-00009-of-00020.bin",
145
+ "cpmbee.encoder.layers.22.self_att.layernorm_before_attention.weight": "pytorch_model-00009-of-00020.bin",
146
+ "cpmbee.encoder.layers.22.self_att.self_attention.attention_out.weight": "pytorch_model-00009-of-00020.bin",
147
+ "cpmbee.encoder.layers.22.self_att.self_attention.project_k.weight": "pytorch_model-00009-of-00020.bin",
148
+ "cpmbee.encoder.layers.22.self_att.self_attention.project_q.weight": "pytorch_model-00009-of-00020.bin",
149
+ "cpmbee.encoder.layers.22.self_att.self_attention.project_v.weight": "pytorch_model-00009-of-00020.bin",
150
+ "cpmbee.encoder.layers.23.ffn.ffn.w_in.w_0.weight": "pytorch_model-00010-of-00020.bin",
151
+ "cpmbee.encoder.layers.23.ffn.ffn.w_in.w_1.weight": "pytorch_model-00010-of-00020.bin",
152
+ "cpmbee.encoder.layers.23.ffn.ffn.w_out.weight": "pytorch_model-00010-of-00020.bin",
153
+ "cpmbee.encoder.layers.23.ffn.layernorm_before_ffn.weight": "pytorch_model-00010-of-00020.bin",
154
+ "cpmbee.encoder.layers.23.self_att.layernorm_before_attention.weight": "pytorch_model-00010-of-00020.bin",
155
+ "cpmbee.encoder.layers.23.self_att.self_attention.attention_out.weight": "pytorch_model-00010-of-00020.bin",
156
+ "cpmbee.encoder.layers.23.self_att.self_attention.project_k.weight": "pytorch_model-00010-of-00020.bin",
157
+ "cpmbee.encoder.layers.23.self_att.self_attention.project_q.weight": "pytorch_model-00010-of-00020.bin",
158
+ "cpmbee.encoder.layers.23.self_att.self_attention.project_v.weight": "pytorch_model-00010-of-00020.bin",
159
+ "cpmbee.encoder.layers.24.ffn.ffn.w_in.w_0.weight": "pytorch_model-00010-of-00020.bin",
160
+ "cpmbee.encoder.layers.24.ffn.ffn.w_in.w_1.weight": "pytorch_model-00010-of-00020.bin",
161
+ "cpmbee.encoder.layers.24.ffn.ffn.w_out.weight": "pytorch_model-00010-of-00020.bin",
162
+ "cpmbee.encoder.layers.24.ffn.layernorm_before_ffn.weight": "pytorch_model-00010-of-00020.bin",
163
+ "cpmbee.encoder.layers.24.self_att.layernorm_before_attention.weight": "pytorch_model-00010-of-00020.bin",
164
+ "cpmbee.encoder.layers.24.self_att.self_attention.attention_out.weight": "pytorch_model-00010-of-00020.bin",
165
+ "cpmbee.encoder.layers.24.self_att.self_attention.project_k.weight": "pytorch_model-00010-of-00020.bin",
166
+ "cpmbee.encoder.layers.24.self_att.self_attention.project_q.weight": "pytorch_model-00010-of-00020.bin",
167
+ "cpmbee.encoder.layers.24.self_att.self_attention.project_v.weight": "pytorch_model-00010-of-00020.bin",
168
+ "cpmbee.encoder.layers.25.ffn.ffn.w_in.w_0.weight": "pytorch_model-00011-of-00020.bin",
169
+ "cpmbee.encoder.layers.25.ffn.ffn.w_in.w_1.weight": "pytorch_model-00011-of-00020.bin",
170
+ "cpmbee.encoder.layers.25.ffn.ffn.w_out.weight": "pytorch_model-00011-of-00020.bin",
171
+ "cpmbee.encoder.layers.25.ffn.layernorm_before_ffn.weight": "pytorch_model-00011-of-00020.bin",
172
+ "cpmbee.encoder.layers.25.self_att.layernorm_before_attention.weight": "pytorch_model-00010-of-00020.bin",
173
+ "cpmbee.encoder.layers.25.self_att.self_attention.attention_out.weight": "pytorch_model-00011-of-00020.bin",
174
+ "cpmbee.encoder.layers.25.self_att.self_attention.project_k.weight": "pytorch_model-00011-of-00020.bin",
175
+ "cpmbee.encoder.layers.25.self_att.self_attention.project_q.weight": "pytorch_model-00010-of-00020.bin",
176
+ "cpmbee.encoder.layers.25.self_att.self_attention.project_v.weight": "pytorch_model-00011-of-00020.bin",
177
+ "cpmbee.encoder.layers.26.ffn.ffn.w_in.w_0.weight": "pytorch_model-00011-of-00020.bin",
178
+ "cpmbee.encoder.layers.26.ffn.ffn.w_in.w_1.weight": "pytorch_model-00011-of-00020.bin",
179
+ "cpmbee.encoder.layers.26.ffn.ffn.w_out.weight": "pytorch_model-00011-of-00020.bin",
180
+ "cpmbee.encoder.layers.26.ffn.layernorm_before_ffn.weight": "pytorch_model-00011-of-00020.bin",
181
+ "cpmbee.encoder.layers.26.self_att.layernorm_before_attention.weight": "pytorch_model-00011-of-00020.bin",
182
+ "cpmbee.encoder.layers.26.self_att.self_attention.attention_out.weight": "pytorch_model-00011-of-00020.bin",
183
+ "cpmbee.encoder.layers.26.self_att.self_attention.project_k.weight": "pytorch_model-00011-of-00020.bin",
184
+ "cpmbee.encoder.layers.26.self_att.self_attention.project_q.weight": "pytorch_model-00011-of-00020.bin",
185
+ "cpmbee.encoder.layers.26.self_att.self_attention.project_v.weight": "pytorch_model-00011-of-00020.bin",
186
+ "cpmbee.encoder.layers.27.ffn.ffn.w_in.w_0.weight": "pytorch_model-00011-of-00020.bin",
187
+ "cpmbee.encoder.layers.27.ffn.ffn.w_in.w_1.weight": "pytorch_model-00012-of-00020.bin",
188
+ "cpmbee.encoder.layers.27.ffn.ffn.w_out.weight": "pytorch_model-00012-of-00020.bin",
189
+ "cpmbee.encoder.layers.27.ffn.layernorm_before_ffn.weight": "pytorch_model-00011-of-00020.bin",
190
+ "cpmbee.encoder.layers.27.self_att.layernorm_before_attention.weight": "pytorch_model-00011-of-00020.bin",
191
+ "cpmbee.encoder.layers.27.self_att.self_attention.attention_out.weight": "pytorch_model-00011-of-00020.bin",
192
+ "cpmbee.encoder.layers.27.self_att.self_attention.project_k.weight": "pytorch_model-00011-of-00020.bin",
193
+ "cpmbee.encoder.layers.27.self_att.self_attention.project_q.weight": "pytorch_model-00011-of-00020.bin",
194
+ "cpmbee.encoder.layers.27.self_att.self_attention.project_v.weight": "pytorch_model-00011-of-00020.bin",
195
+ "cpmbee.encoder.layers.28.ffn.ffn.w_in.w_0.weight": "pytorch_model-00012-of-00020.bin",
196
+ "cpmbee.encoder.layers.28.ffn.ffn.w_in.w_1.weight": "pytorch_model-00012-of-00020.bin",
197
+ "cpmbee.encoder.layers.28.ffn.ffn.w_out.weight": "pytorch_model-00012-of-00020.bin",
198
+ "cpmbee.encoder.layers.28.ffn.layernorm_before_ffn.weight": "pytorch_model-00012-of-00020.bin",
199
+ "cpmbee.encoder.layers.28.self_att.layernorm_before_attention.weight": "pytorch_model-00012-of-00020.bin",
200
+ "cpmbee.encoder.layers.28.self_att.self_attention.attention_out.weight": "pytorch_model-00012-of-00020.bin",
201
+ "cpmbee.encoder.layers.28.self_att.self_attention.project_k.weight": "pytorch_model-00012-of-00020.bin",
202
+ "cpmbee.encoder.layers.28.self_att.self_attention.project_q.weight": "pytorch_model-00012-of-00020.bin",
203
+ "cpmbee.encoder.layers.28.self_att.self_attention.project_v.weight": "pytorch_model-00012-of-00020.bin",
204
+ "cpmbee.encoder.layers.29.ffn.ffn.w_in.w_0.weight": "pytorch_model-00012-of-00020.bin",
205
+ "cpmbee.encoder.layers.29.ffn.ffn.w_in.w_1.weight": "pytorch_model-00012-of-00020.bin",
206
+ "cpmbee.encoder.layers.29.ffn.ffn.w_out.weight": "pytorch_model-00012-of-00020.bin",
207
+ "cpmbee.encoder.layers.29.ffn.layernorm_before_ffn.weight": "pytorch_model-00012-of-00020.bin",
208
+ "cpmbee.encoder.layers.29.self_att.layernorm_before_attention.weight": "pytorch_model-00012-of-00020.bin",
209
+ "cpmbee.encoder.layers.29.self_att.self_attention.attention_out.weight": "pytorch_model-00012-of-00020.bin",
210
+ "cpmbee.encoder.layers.29.self_att.self_attention.project_k.weight": "pytorch_model-00012-of-00020.bin",
211
+ "cpmbee.encoder.layers.29.self_att.self_attention.project_q.weight": "pytorch_model-00012-of-00020.bin",
212
+ "cpmbee.encoder.layers.29.self_att.self_attention.project_v.weight": "pytorch_model-00012-of-00020.bin",
213
+ "cpmbee.encoder.layers.3.ffn.ffn.w_in.w_0.weight": "pytorch_model-00002-of-00020.bin",
214
+ "cpmbee.encoder.layers.3.ffn.ffn.w_in.w_1.weight": "pytorch_model-00002-of-00020.bin",
215
+ "cpmbee.encoder.layers.3.ffn.ffn.w_out.weight": "pytorch_model-00002-of-00020.bin",
216
+ "cpmbee.encoder.layers.3.ffn.layernorm_before_ffn.weight": "pytorch_model-00002-of-00020.bin",
217
+ "cpmbee.encoder.layers.3.self_att.layernorm_before_attention.weight": "pytorch_model-00002-of-00020.bin",
218
+ "cpmbee.encoder.layers.3.self_att.self_attention.attention_out.weight": "pytorch_model-00002-of-00020.bin",
219
+ "cpmbee.encoder.layers.3.self_att.self_attention.project_k.weight": "pytorch_model-00002-of-00020.bin",
220
+ "cpmbee.encoder.layers.3.self_att.self_attention.project_q.weight": "pytorch_model-00002-of-00020.bin",
221
+ "cpmbee.encoder.layers.3.self_att.self_attention.project_v.weight": "pytorch_model-00002-of-00020.bin",
222
+ "cpmbee.encoder.layers.30.ffn.ffn.w_in.w_0.weight": "pytorch_model-00013-of-00020.bin",
223
+ "cpmbee.encoder.layers.30.ffn.ffn.w_in.w_1.weight": "pytorch_model-00013-of-00020.bin",
224
+ "cpmbee.encoder.layers.30.ffn.ffn.w_out.weight": "pytorch_model-00013-of-00020.bin",
225
+ "cpmbee.encoder.layers.30.ffn.layernorm_before_ffn.weight": "pytorch_model-00013-of-00020.bin",
226
+ "cpmbee.encoder.layers.30.self_att.layernorm_before_attention.weight": "pytorch_model-00012-of-00020.bin",
227
+ "cpmbee.encoder.layers.30.self_att.self_attention.attention_out.weight": "pytorch_model-00013-of-00020.bin",
228
+ "cpmbee.encoder.layers.30.self_att.self_attention.project_k.weight": "pytorch_model-00013-of-00020.bin",
229
+ "cpmbee.encoder.layers.30.self_att.self_attention.project_q.weight": "pytorch_model-00012-of-00020.bin",
230
+ "cpmbee.encoder.layers.30.self_att.self_attention.project_v.weight": "pytorch_model-00013-of-00020.bin",
231
+ "cpmbee.encoder.layers.31.ffn.ffn.w_in.w_0.weight": "pytorch_model-00013-of-00020.bin",
232
+ "cpmbee.encoder.layers.31.ffn.ffn.w_in.w_1.weight": "pytorch_model-00013-of-00020.bin",
233
+ "cpmbee.encoder.layers.31.ffn.ffn.w_out.weight": "pytorch_model-00013-of-00020.bin",
234
+ "cpmbee.encoder.layers.31.ffn.layernorm_before_ffn.weight": "pytorch_model-00013-of-00020.bin",
235
+ "cpmbee.encoder.layers.31.self_att.layernorm_before_attention.weight": "pytorch_model-00013-of-00020.bin",
236
+ "cpmbee.encoder.layers.31.self_att.self_attention.attention_out.weight": "pytorch_model-00013-of-00020.bin",
237
+ "cpmbee.encoder.layers.31.self_att.self_attention.project_k.weight": "pytorch_model-00013-of-00020.bin",
238
+ "cpmbee.encoder.layers.31.self_att.self_attention.project_q.weight": "pytorch_model-00013-of-00020.bin",
239
+ "cpmbee.encoder.layers.31.self_att.self_attention.project_v.weight": "pytorch_model-00013-of-00020.bin",
240
+ "cpmbee.encoder.layers.32.ffn.ffn.w_in.w_0.weight": "pytorch_model-00013-of-00020.bin",
241
+ "cpmbee.encoder.layers.32.ffn.ffn.w_in.w_1.weight": "pytorch_model-00014-of-00020.bin",
242
+ "cpmbee.encoder.layers.32.ffn.ffn.w_out.weight": "pytorch_model-00014-of-00020.bin",
243
+ "cpmbee.encoder.layers.32.ffn.layernorm_before_ffn.weight": "pytorch_model-00013-of-00020.bin",
244
+ "cpmbee.encoder.layers.32.self_att.layernorm_before_attention.weight": "pytorch_model-00013-of-00020.bin",
245
+ "cpmbee.encoder.layers.32.self_att.self_attention.attention_out.weight": "pytorch_model-00013-of-00020.bin",
246
+ "cpmbee.encoder.layers.32.self_att.self_attention.project_k.weight": "pytorch_model-00013-of-00020.bin",
247
+ "cpmbee.encoder.layers.32.self_att.self_attention.project_q.weight": "pytorch_model-00013-of-00020.bin",
248
+ "cpmbee.encoder.layers.32.self_att.self_attention.project_v.weight": "pytorch_model-00013-of-00020.bin",
249
+ "cpmbee.encoder.layers.33.ffn.ffn.w_in.w_0.weight": "pytorch_model-00014-of-00020.bin",
250
+ "cpmbee.encoder.layers.33.ffn.ffn.w_in.w_1.weight": "pytorch_model-00014-of-00020.bin",
251
+ "cpmbee.encoder.layers.33.ffn.ffn.w_out.weight": "pytorch_model-00014-of-00020.bin",
252
+ "cpmbee.encoder.layers.33.ffn.layernorm_before_ffn.weight": "pytorch_model-00014-of-00020.bin",
253
+ "cpmbee.encoder.layers.33.self_att.layernorm_before_attention.weight": "pytorch_model-00014-of-00020.bin",
254
+ "cpmbee.encoder.layers.33.self_att.self_attention.attention_out.weight": "pytorch_model-00014-of-00020.bin",
255
+ "cpmbee.encoder.layers.33.self_att.self_attention.project_k.weight": "pytorch_model-00014-of-00020.bin",
256
+ "cpmbee.encoder.layers.33.self_att.self_attention.project_q.weight": "pytorch_model-00014-of-00020.bin",
257
+ "cpmbee.encoder.layers.33.self_att.self_attention.project_v.weight": "pytorch_model-00014-of-00020.bin",
258
+ "cpmbee.encoder.layers.34.ffn.ffn.w_in.w_0.weight": "pytorch_model-00014-of-00020.bin",
259
+ "cpmbee.encoder.layers.34.ffn.ffn.w_in.w_1.weight": "pytorch_model-00014-of-00020.bin",
260
+ "cpmbee.encoder.layers.34.ffn.ffn.w_out.weight": "pytorch_model-00014-of-00020.bin",
261
+ "cpmbee.encoder.layers.34.ffn.layernorm_before_ffn.weight": "pytorch_model-00014-of-00020.bin",
262
+ "cpmbee.encoder.layers.34.self_att.layernorm_before_attention.weight": "pytorch_model-00014-of-00020.bin",
263
+ "cpmbee.encoder.layers.34.self_att.self_attention.attention_out.weight": "pytorch_model-00014-of-00020.bin",
264
+ "cpmbee.encoder.layers.34.self_att.self_attention.project_k.weight": "pytorch_model-00014-of-00020.bin",
265
+ "cpmbee.encoder.layers.34.self_att.self_attention.project_q.weight": "pytorch_model-00014-of-00020.bin",
266
+ "cpmbee.encoder.layers.34.self_att.self_attention.project_v.weight": "pytorch_model-00014-of-00020.bin",
267
+ "cpmbee.encoder.layers.35.ffn.ffn.w_in.w_0.weight": "pytorch_model-00015-of-00020.bin",
268
+ "cpmbee.encoder.layers.35.ffn.ffn.w_in.w_1.weight": "pytorch_model-00015-of-00020.bin",
269
+ "cpmbee.encoder.layers.35.ffn.ffn.w_out.weight": "pytorch_model-00015-of-00020.bin",
270
+ "cpmbee.encoder.layers.35.ffn.layernorm_before_ffn.weight": "pytorch_model-00015-of-00020.bin",
271
+ "cpmbee.encoder.layers.35.self_att.layernorm_before_attention.weight": "pytorch_model-00014-of-00020.bin",
272
+ "cpmbee.encoder.layers.35.self_att.self_attention.attention_out.weight": "pytorch_model-00015-of-00020.bin",
273
+ "cpmbee.encoder.layers.35.self_att.self_attention.project_k.weight": "pytorch_model-00015-of-00020.bin",
274
+ "cpmbee.encoder.layers.35.self_att.self_attention.project_q.weight": "pytorch_model-00014-of-00020.bin",
275
+ "cpmbee.encoder.layers.35.self_att.self_attention.project_v.weight": "pytorch_model-00015-of-00020.bin",
276
+ "cpmbee.encoder.layers.36.ffn.ffn.w_in.w_0.weight": "pytorch_model-00015-of-00020.bin",
277
+ "cpmbee.encoder.layers.36.ffn.ffn.w_in.w_1.weight": "pytorch_model-00015-of-00020.bin",
278
+ "cpmbee.encoder.layers.36.ffn.ffn.w_out.weight": "pytorch_model-00015-of-00020.bin",
279
+ "cpmbee.encoder.layers.36.ffn.layernorm_before_ffn.weight": "pytorch_model-00015-of-00020.bin",
280
+ "cpmbee.encoder.layers.36.self_att.layernorm_before_attention.weight": "pytorch_model-00015-of-00020.bin",
281
+ "cpmbee.encoder.layers.36.self_att.self_attention.attention_out.weight": "pytorch_model-00015-of-00020.bin",
282
+ "cpmbee.encoder.layers.36.self_att.self_attention.project_k.weight": "pytorch_model-00015-of-00020.bin",
283
+ "cpmbee.encoder.layers.36.self_att.self_attention.project_q.weight": "pytorch_model-00015-of-00020.bin",
284
+ "cpmbee.encoder.layers.36.self_att.self_attention.project_v.weight": "pytorch_model-00015-of-00020.bin",
285
+ "cpmbee.encoder.layers.37.ffn.ffn.w_in.w_0.weight": "pytorch_model-00015-of-00020.bin",
286
+ "cpmbee.encoder.layers.37.ffn.ffn.w_in.w_1.weight": "pytorch_model-00016-of-00020.bin",
287
+ "cpmbee.encoder.layers.37.ffn.ffn.w_out.weight": "pytorch_model-00016-of-00020.bin",
288
+ "cpmbee.encoder.layers.37.ffn.layernorm_before_ffn.weight": "pytorch_model-00015-of-00020.bin",
289
+ "cpmbee.encoder.layers.37.self_att.layernorm_before_attention.weight": "pytorch_model-00015-of-00020.bin",
290
+ "cpmbee.encoder.layers.37.self_att.self_attention.attention_out.weight": "pytorch_model-00015-of-00020.bin",
291
+ "cpmbee.encoder.layers.37.self_att.self_attention.project_k.weight": "pytorch_model-00015-of-00020.bin",
292
+ "cpmbee.encoder.layers.37.self_att.self_attention.project_q.weight": "pytorch_model-00015-of-00020.bin",
293
+ "cpmbee.encoder.layers.37.self_att.self_attention.project_v.weight": "pytorch_model-00015-of-00020.bin",
294
+ "cpmbee.encoder.layers.38.ffn.ffn.w_in.w_0.weight": "pytorch_model-00016-of-00020.bin",
295
+ "cpmbee.encoder.layers.38.ffn.ffn.w_in.w_1.weight": "pytorch_model-00016-of-00020.bin",
296
+ "cpmbee.encoder.layers.38.ffn.ffn.w_out.weight": "pytorch_model-00016-of-00020.bin",
297
+ "cpmbee.encoder.layers.38.ffn.layernorm_before_ffn.weight": "pytorch_model-00016-of-00020.bin",
298
+ "cpmbee.encoder.layers.38.self_att.layernorm_before_attention.weight": "pytorch_model-00016-of-00020.bin",
299
+ "cpmbee.encoder.layers.38.self_att.self_attention.attention_out.weight": "pytorch_model-00016-of-00020.bin",
300
+ "cpmbee.encoder.layers.38.self_att.self_attention.project_k.weight": "pytorch_model-00016-of-00020.bin",
301
+ "cpmbee.encoder.layers.38.self_att.self_attention.project_q.weight": "pytorch_model-00016-of-00020.bin",
302
+ "cpmbee.encoder.layers.38.self_att.self_attention.project_v.weight": "pytorch_model-00016-of-00020.bin",
303
+ "cpmbee.encoder.layers.39.ffn.ffn.w_in.w_0.weight": "pytorch_model-00016-of-00020.bin",
304
+ "cpmbee.encoder.layers.39.ffn.ffn.w_in.w_1.weight": "pytorch_model-00016-of-00020.bin",
305
+ "cpmbee.encoder.layers.39.ffn.ffn.w_out.weight": "pytorch_model-00016-of-00020.bin",
306
+ "cpmbee.encoder.layers.39.ffn.layernorm_before_ffn.weight": "pytorch_model-00016-of-00020.bin",
307
+ "cpmbee.encoder.layers.39.self_att.layernorm_before_attention.weight": "pytorch_model-00016-of-00020.bin",
308
+ "cpmbee.encoder.layers.39.self_att.self_attention.attention_out.weight": "pytorch_model-00016-of-00020.bin",
309
+ "cpmbee.encoder.layers.39.self_att.self_attention.project_k.weight": "pytorch_model-00016-of-00020.bin",
310
+ "cpmbee.encoder.layers.39.self_att.self_attention.project_q.weight": "pytorch_model-00016-of-00020.bin",
311
+ "cpmbee.encoder.layers.39.self_att.self_attention.project_v.weight": "pytorch_model-00016-of-00020.bin",
312
+ "cpmbee.encoder.layers.4.ffn.ffn.w_in.w_0.weight": "pytorch_model-00002-of-00020.bin",
313
+ "cpmbee.encoder.layers.4.ffn.ffn.w_in.w_1.weight": "pytorch_model-00002-of-00020.bin",
314
+ "cpmbee.encoder.layers.4.ffn.ffn.w_out.weight": "pytorch_model-00002-of-00020.bin",
315
+ "cpmbee.encoder.layers.4.ffn.layernorm_before_ffn.weight": "pytorch_model-00002-of-00020.bin",
316
+ "cpmbee.encoder.layers.4.self_att.layernorm_before_attention.weight": "pytorch_model-00002-of-00020.bin",
317
+ "cpmbee.encoder.layers.4.self_att.self_attention.attention_out.weight": "pytorch_model-00002-of-00020.bin",
318
+ "cpmbee.encoder.layers.4.self_att.self_attention.project_k.weight": "pytorch_model-00002-of-00020.bin",
319
+ "cpmbee.encoder.layers.4.self_att.self_attention.project_q.weight": "pytorch_model-00002-of-00020.bin",
320
+ "cpmbee.encoder.layers.4.self_att.self_attention.project_v.weight": "pytorch_model-00002-of-00020.bin",
321
+ "cpmbee.encoder.layers.40.ffn.ffn.w_in.w_0.weight": "pytorch_model-00017-of-00020.bin",
322
+ "cpmbee.encoder.layers.40.ffn.ffn.w_in.w_1.weight": "pytorch_model-00017-of-00020.bin",
323
+ "cpmbee.encoder.layers.40.ffn.ffn.w_out.weight": "pytorch_model-00017-of-00020.bin",
324
+ "cpmbee.encoder.layers.40.ffn.layernorm_before_ffn.weight": "pytorch_model-00017-of-00020.bin",
325
+ "cpmbee.encoder.layers.40.self_att.layernorm_before_attention.weight": "pytorch_model-00016-of-00020.bin",
326
+ "cpmbee.encoder.layers.40.self_att.self_attention.attention_out.weight": "pytorch_model-00017-of-00020.bin",
327
+ "cpmbee.encoder.layers.40.self_att.self_attention.project_k.weight": "pytorch_model-00017-of-00020.bin",
328
+ "cpmbee.encoder.layers.40.self_att.self_attention.project_q.weight": "pytorch_model-00016-of-00020.bin",
329
+ "cpmbee.encoder.layers.40.self_att.self_attention.project_v.weight": "pytorch_model-00017-of-00020.bin",
330
+ "cpmbee.encoder.layers.41.ffn.ffn.w_in.w_0.weight": "pytorch_model-00017-of-00020.bin",
331
+ "cpmbee.encoder.layers.41.ffn.ffn.w_in.w_1.weight": "pytorch_model-00017-of-00020.bin",
332
+ "cpmbee.encoder.layers.41.ffn.ffn.w_out.weight": "pytorch_model-00017-of-00020.bin",
333
+ "cpmbee.encoder.layers.41.ffn.layernorm_before_ffn.weight": "pytorch_model-00017-of-00020.bin",
334
+ "cpmbee.encoder.layers.41.self_att.layernorm_before_attention.weight": "pytorch_model-00017-of-00020.bin",
335
+ "cpmbee.encoder.layers.41.self_att.self_attention.attention_out.weight": "pytorch_model-00017-of-00020.bin",
336
+ "cpmbee.encoder.layers.41.self_att.self_attention.project_k.weight": "pytorch_model-00017-of-00020.bin",
337
+ "cpmbee.encoder.layers.41.self_att.self_attention.project_q.weight": "pytorch_model-00017-of-00020.bin",
338
+ "cpmbee.encoder.layers.41.self_att.self_attention.project_v.weight": "pytorch_model-00017-of-00020.bin",
339
+ "cpmbee.encoder.layers.42.ffn.ffn.w_in.w_0.weight": "pytorch_model-00017-of-00020.bin",
340
+ "cpmbee.encoder.layers.42.ffn.ffn.w_in.w_1.weight": "pytorch_model-00018-of-00020.bin",
341
+ "cpmbee.encoder.layers.42.ffn.ffn.w_out.weight": "pytorch_model-00018-of-00020.bin",
342
+ "cpmbee.encoder.layers.42.ffn.layernorm_before_ffn.weight": "pytorch_model-00017-of-00020.bin",
343
+ "cpmbee.encoder.layers.42.self_att.layernorm_before_attention.weight": "pytorch_model-00017-of-00020.bin",
344
+ "cpmbee.encoder.layers.42.self_att.self_attention.attention_out.weight": "pytorch_model-00017-of-00020.bin",
345
+ "cpmbee.encoder.layers.42.self_att.self_attention.project_k.weight": "pytorch_model-00017-of-00020.bin",
346
+ "cpmbee.encoder.layers.42.self_att.self_attention.project_q.weight": "pytorch_model-00017-of-00020.bin",
347
+ "cpmbee.encoder.layers.42.self_att.self_attention.project_v.weight": "pytorch_model-00017-of-00020.bin",
348
+ "cpmbee.encoder.layers.43.ffn.ffn.w_in.w_0.weight": "pytorch_model-00018-of-00020.bin",
349
+ "cpmbee.encoder.layers.43.ffn.ffn.w_in.w_1.weight": "pytorch_model-00018-of-00020.bin",
350
+ "cpmbee.encoder.layers.43.ffn.ffn.w_out.weight": "pytorch_model-00018-of-00020.bin",
351
+ "cpmbee.encoder.layers.43.ffn.layernorm_before_ffn.weight": "pytorch_model-00018-of-00020.bin",
352
+ "cpmbee.encoder.layers.43.self_att.layernorm_before_attention.weight": "pytorch_model-00018-of-00020.bin",
353
+ "cpmbee.encoder.layers.43.self_att.self_attention.attention_out.weight": "pytorch_model-00018-of-00020.bin",
354
+ "cpmbee.encoder.layers.43.self_att.self_attention.project_k.weight": "pytorch_model-00018-of-00020.bin",
355
+ "cpmbee.encoder.layers.43.self_att.self_attention.project_q.weight": "pytorch_model-00018-of-00020.bin",
356
+ "cpmbee.encoder.layers.43.self_att.self_attention.project_v.weight": "pytorch_model-00018-of-00020.bin",
357
+ "cpmbee.encoder.layers.44.ffn.ffn.w_in.w_0.weight": "pytorch_model-00018-of-00020.bin",
358
+ "cpmbee.encoder.layers.44.ffn.ffn.w_in.w_1.weight": "pytorch_model-00018-of-00020.bin",
359
+ "cpmbee.encoder.layers.44.ffn.ffn.w_out.weight": "pytorch_model-00018-of-00020.bin",
360
+ "cpmbee.encoder.layers.44.ffn.layernorm_before_ffn.weight": "pytorch_model-00018-of-00020.bin",
361
+ "cpmbee.encoder.layers.44.self_att.layernorm_before_attention.weight": "pytorch_model-00018-of-00020.bin",
362
+ "cpmbee.encoder.layers.44.self_att.self_attention.attention_out.weight": "pytorch_model-00018-of-00020.bin",
363
+ "cpmbee.encoder.layers.44.self_att.self_attention.project_k.weight": "pytorch_model-00018-of-00020.bin",
364
+ "cpmbee.encoder.layers.44.self_att.self_attention.project_q.weight": "pytorch_model-00018-of-00020.bin",
365
+ "cpmbee.encoder.layers.44.self_att.self_attention.project_v.weight": "pytorch_model-00018-of-00020.bin",
366
+ "cpmbee.encoder.layers.45.ffn.ffn.w_in.w_0.weight": "pytorch_model-00019-of-00020.bin",
367
+ "cpmbee.encoder.layers.45.ffn.ffn.w_in.w_1.weight": "pytorch_model-00019-of-00020.bin",
368
+ "cpmbee.encoder.layers.45.ffn.ffn.w_out.weight": "pytorch_model-00019-of-00020.bin",
369
+ "cpmbee.encoder.layers.45.ffn.layernorm_before_ffn.weight": "pytorch_model-00019-of-00020.bin",
370
+ "cpmbee.encoder.layers.45.self_att.layernorm_before_attention.weight": "pytorch_model-00018-of-00020.bin",
371
+ "cpmbee.encoder.layers.45.self_att.self_attention.attention_out.weight": "pytorch_model-00019-of-00020.bin",
372
+ "cpmbee.encoder.layers.45.self_att.self_attention.project_k.weight": "pytorch_model-00019-of-00020.bin",
373
+ "cpmbee.encoder.layers.45.self_att.self_attention.project_q.weight": "pytorch_model-00018-of-00020.bin",
374
+ "cpmbee.encoder.layers.45.self_att.self_attention.project_v.weight": "pytorch_model-00019-of-00020.bin",
375
+ "cpmbee.encoder.layers.46.ffn.ffn.w_in.w_0.weight": "pytorch_model-00019-of-00020.bin",
376
+ "cpmbee.encoder.layers.46.ffn.ffn.w_in.w_1.weight": "pytorch_model-00019-of-00020.bin",
377
+ "cpmbee.encoder.layers.46.ffn.ffn.w_out.weight": "pytorch_model-00019-of-00020.bin",
378
+ "cpmbee.encoder.layers.46.ffn.layernorm_before_ffn.weight": "pytorch_model-00019-of-00020.bin",
379
+ "cpmbee.encoder.layers.46.self_att.layernorm_before_attention.weight": "pytorch_model-00019-of-00020.bin",
380
+ "cpmbee.encoder.layers.46.self_att.self_attention.attention_out.weight": "pytorch_model-00019-of-00020.bin",
381
+ "cpmbee.encoder.layers.46.self_att.self_attention.project_k.weight": "pytorch_model-00019-of-00020.bin",
382
+ "cpmbee.encoder.layers.46.self_att.self_attention.project_q.weight": "pytorch_model-00019-of-00020.bin",
383
+ "cpmbee.encoder.layers.46.self_att.self_attention.project_v.weight": "pytorch_model-00019-of-00020.bin",
384
+ "cpmbee.encoder.layers.47.ffn.ffn.w_in.w_0.weight": "pytorch_model-00019-of-00020.bin",
385
+ "cpmbee.encoder.layers.47.ffn.ffn.w_in.w_1.weight": "pytorch_model-00020-of-00020.bin",
386
+ "cpmbee.encoder.layers.47.ffn.ffn.w_out.weight": "pytorch_model-00020-of-00020.bin",
387
+ "cpmbee.encoder.layers.47.ffn.layernorm_before_ffn.weight": "pytorch_model-00019-of-00020.bin",
388
+ "cpmbee.encoder.layers.47.self_att.layernorm_before_attention.weight": "pytorch_model-00019-of-00020.bin",
389
+ "cpmbee.encoder.layers.47.self_att.self_attention.attention_out.weight": "pytorch_model-00019-of-00020.bin",
390
+ "cpmbee.encoder.layers.47.self_att.self_attention.project_k.weight": "pytorch_model-00019-of-00020.bin",
391
+ "cpmbee.encoder.layers.47.self_att.self_attention.project_q.weight": "pytorch_model-00019-of-00020.bin",
392
+ "cpmbee.encoder.layers.47.self_att.self_attention.project_v.weight": "pytorch_model-00019-of-00020.bin",
393
+ "cpmbee.encoder.layers.5.ffn.ffn.w_in.w_0.weight": "pytorch_model-00003-of-00020.bin",
394
+ "cpmbee.encoder.layers.5.ffn.ffn.w_in.w_1.weight": "pytorch_model-00003-of-00020.bin",
395
+ "cpmbee.encoder.layers.5.ffn.ffn.w_out.weight": "pytorch_model-00003-of-00020.bin",
396
+ "cpmbee.encoder.layers.5.ffn.layernorm_before_ffn.weight": "pytorch_model-00003-of-00020.bin",
397
+ "cpmbee.encoder.layers.5.self_att.layernorm_before_attention.weight": "pytorch_model-00002-of-00020.bin",
398
+ "cpmbee.encoder.layers.5.self_att.self_attention.attention_out.weight": "pytorch_model-00003-of-00020.bin",
399
+ "cpmbee.encoder.layers.5.self_att.self_attention.project_k.weight": "pytorch_model-00003-of-00020.bin",
400
+ "cpmbee.encoder.layers.5.self_att.self_attention.project_q.weight": "pytorch_model-00002-of-00020.bin",
401
+ "cpmbee.encoder.layers.5.self_att.self_attention.project_v.weight": "pytorch_model-00003-of-00020.bin",
402
+ "cpmbee.encoder.layers.6.ffn.ffn.w_in.w_0.weight": "pytorch_model-00003-of-00020.bin",
403
+ "cpmbee.encoder.layers.6.ffn.ffn.w_in.w_1.weight": "pytorch_model-00003-of-00020.bin",
404
+ "cpmbee.encoder.layers.6.ffn.ffn.w_out.weight": "pytorch_model-00003-of-00020.bin",
405
+ "cpmbee.encoder.layers.6.ffn.layernorm_before_ffn.weight": "pytorch_model-00003-of-00020.bin",
406
+ "cpmbee.encoder.layers.6.self_att.layernorm_before_attention.weight": "pytorch_model-00003-of-00020.bin",
407
+ "cpmbee.encoder.layers.6.self_att.self_attention.attention_out.weight": "pytorch_model-00003-of-00020.bin",
408
+ "cpmbee.encoder.layers.6.self_att.self_attention.project_k.weight": "pytorch_model-00003-of-00020.bin",
409
+ "cpmbee.encoder.layers.6.self_att.self_attention.project_q.weight": "pytorch_model-00003-of-00020.bin",
410
+ "cpmbee.encoder.layers.6.self_att.self_attention.project_v.weight": "pytorch_model-00003-of-00020.bin",
411
+ "cpmbee.encoder.layers.7.ffn.ffn.w_in.w_0.weight": "pytorch_model-00003-of-00020.bin",
412
+ "cpmbee.encoder.layers.7.ffn.ffn.w_in.w_1.weight": "pytorch_model-00004-of-00020.bin",
413
+ "cpmbee.encoder.layers.7.ffn.ffn.w_out.weight": "pytorch_model-00004-of-00020.bin",
414
+ "cpmbee.encoder.layers.7.ffn.layernorm_before_ffn.weight": "pytorch_model-00003-of-00020.bin",
415
+ "cpmbee.encoder.layers.7.self_att.layernorm_before_attention.weight": "pytorch_model-00003-of-00020.bin",
416
+ "cpmbee.encoder.layers.7.self_att.self_attention.attention_out.weight": "pytorch_model-00003-of-00020.bin",
417
+ "cpmbee.encoder.layers.7.self_att.self_attention.project_k.weight": "pytorch_model-00003-of-00020.bin",
418
+ "cpmbee.encoder.layers.7.self_att.self_attention.project_q.weight": "pytorch_model-00003-of-00020.bin",
419
+ "cpmbee.encoder.layers.7.self_att.self_attention.project_v.weight": "pytorch_model-00003-of-00020.bin",
420
+ "cpmbee.encoder.layers.8.ffn.ffn.w_in.w_0.weight": "pytorch_model-00004-of-00020.bin",
421
+ "cpmbee.encoder.layers.8.ffn.ffn.w_in.w_1.weight": "pytorch_model-00004-of-00020.bin",
422
+ "cpmbee.encoder.layers.8.ffn.ffn.w_out.weight": "pytorch_model-00004-of-00020.bin",
423
+ "cpmbee.encoder.layers.8.ffn.layernorm_before_ffn.weight": "pytorch_model-00004-of-00020.bin",
424
+ "cpmbee.encoder.layers.8.self_att.layernorm_before_attention.weight": "pytorch_model-00004-of-00020.bin",
425
+ "cpmbee.encoder.layers.8.self_att.self_attention.attention_out.weight": "pytorch_model-00004-of-00020.bin",
426
+ "cpmbee.encoder.layers.8.self_att.self_attention.project_k.weight": "pytorch_model-00004-of-00020.bin",
427
+ "cpmbee.encoder.layers.8.self_att.self_attention.project_q.weight": "pytorch_model-00004-of-00020.bin",
428
+ "cpmbee.encoder.layers.8.self_att.self_attention.project_v.weight": "pytorch_model-00004-of-00020.bin",
429
+ "cpmbee.encoder.layers.9.ffn.ffn.w_in.w_0.weight": "pytorch_model-00004-of-00020.bin",
430
+ "cpmbee.encoder.layers.9.ffn.ffn.w_in.w_1.weight": "pytorch_model-00004-of-00020.bin",
431
+ "cpmbee.encoder.layers.9.ffn.ffn.w_out.weight": "pytorch_model-00004-of-00020.bin",
432
+ "cpmbee.encoder.layers.9.ffn.layernorm_before_ffn.weight": "pytorch_model-00004-of-00020.bin",
433
+ "cpmbee.encoder.layers.9.self_att.layernorm_before_attention.weight": "pytorch_model-00004-of-00020.bin",
434
+ "cpmbee.encoder.layers.9.self_att.self_attention.attention_out.weight": "pytorch_model-00004-of-00020.bin",
435
+ "cpmbee.encoder.layers.9.self_att.self_attention.project_k.weight": "pytorch_model-00004-of-00020.bin",
436
+ "cpmbee.encoder.layers.9.self_att.self_attention.project_q.weight": "pytorch_model-00004-of-00020.bin",
437
+ "cpmbee.encoder.layers.9.self_att.self_attention.project_v.weight": "pytorch_model-00004-of-00020.bin",
438
+ "cpmbee.encoder.output_layernorm.weight": "pytorch_model-00020-of-00020.bin",
439
+ "cpmbee.input_embedding.weight": "pytorch_model-00020-of-00020.bin",
440
+ "cpmbee.position_bias.relative_attention_bias": "pytorch_model-00020-of-00020.bin",
441
+ "lm_head.weight": "pytorch_model-00020-of-00020.bin"
442
+ }
443
+ }