Hugging Face's logo

llama-lang-adapt
/
Gemma2-lb-AfriMGSM-8-2-2fst

PyTorch
Model card Files Community
KoseiUemura commited on
Commit
d2db851
•
1 Parent(s): c2c70cf

Upload entire model folder

Browse files
Files changed (8) hide show
  1. config.json +14 -0
  2. generation_config.json +4 -0
  3. pytorch_model-00001-of-00005.bin +3 -0
  4. pytorch_model-00002-of-00005.bin +3 -0
  5. pytorch_model-00003-of-00005.bin +3 -0
  6. pytorch_model-00004-of-00005.bin +3 -0
  7. pytorch_model-00005-of-00005.bin +3 -0
  8. pytorch_model.bin.index.json +696 -0
config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignments": "linear",
3
+ "architectures": [
4
+ "LangBridgeModel"
5
+ ],
6
+ "dim_enc": 2048,
7
+ "dim_lm": 3584,
8
+ "enc": "DKYoon/mt5-xl-lm-adapt",
9
+ "freeze_encoder": true,
10
+ "freeze_language_model": true,
11
+ "lm": "llama-lang-adapt/Gemma2-AfriMGSM-8-2-2fst",
12
+ "torch_dtype": "bfloat16",
13
+ "transformers_version": "4.44.2"
14
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.44.2"
4
+ }
pytorch_model-00001-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d4514f944a9a69b8a501eda3b427c38b058e2be48e7a879a6154e65cd3d61ee
3
+ size 3354690624
pytorch_model-00002-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bbec34e9d66c1ebadcda82b4600d707d064346dce003fc9216c96e0aed38824
3
+ size 4903371174
pytorch_model-00003-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b8e58249fdc22c1556b1e64d9afaa09a3ae62e85b1c5bbb8c86d9301ca01c97
3
+ size 4947602617
pytorch_model-00004-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:592e6c25fee4e08348f4db85bad44e0fc02ce531f21b584c91da0cc59b537686
3
+ size 4962251744
pytorch_model-00005-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4696443b44839b6b64ae436bf81dceeb6d4abefb703b0172d5e3451e9b9b972
3
+ size 3670345745
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,696 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 21838023680
4
+ },
5
+ "weight_map": {
6
+ "lb.alignment.enc_eos": "pytorch_model-00001-of-00005.bin",
7
+ "lb.alignment.linear.bias": "pytorch_model-00001-of-00005.bin",
8
+ "lb.alignment.linear.weight": "pytorch_model-00001-of-00005.bin",
9
+ "lb.embeddings.weight": "pytorch_model-00002-of-00005.bin",
10
+ "lb.enc.encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
11
+ "lb.enc.encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
12
+ "lb.enc.encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
13
+ "lb.enc.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00005.bin",
14
+ "lb.enc.encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
15
+ "lb.enc.encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
16
+ "lb.enc.encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
17
+ "lb.enc.encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
18
+ "lb.enc.encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
19
+ "lb.enc.encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
20
+ "lb.enc.encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
21
+ "lb.enc.encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
22
+ "lb.enc.encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
23
+ "lb.enc.encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
24
+ "lb.enc.encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
25
+ "lb.enc.encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
26
+ "lb.enc.encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
27
+ "lb.enc.encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
28
+ "lb.enc.encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
29
+ "lb.enc.encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
30
+ "lb.enc.encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
31
+ "lb.enc.encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
32
+ "lb.enc.encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
33
+ "lb.enc.encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
34
+ "lb.enc.encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
35
+ "lb.enc.encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
36
+ "lb.enc.encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
37
+ "lb.enc.encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
38
+ "lb.enc.encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
39
+ "lb.enc.encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
40
+ "lb.enc.encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
41
+ "lb.enc.encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
42
+ "lb.enc.encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
43
+ "lb.enc.encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
44
+ "lb.enc.encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
45
+ "lb.enc.encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
46
+ "lb.enc.encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
47
+ "lb.enc.encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
48
+ "lb.enc.encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
49
+ "lb.enc.encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
50
+ "lb.enc.encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
51
+ "lb.enc.encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
52
+ "lb.enc.encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
53
+ "lb.enc.encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
54
+ "lb.enc.encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
55
+ "lb.enc.encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
56
+ "lb.enc.encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
57
+ "lb.enc.encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
58
+ "lb.enc.encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
59
+ "lb.enc.encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
60
+ "lb.enc.encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
61
+ "lb.enc.encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
62
+ "lb.enc.encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
63
+ "lb.enc.encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
64
+ "lb.enc.encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
65
+ "lb.enc.encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
66
+ "lb.enc.encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
67
+ "lb.enc.encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
68
+ "lb.enc.encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
69
+ "lb.enc.encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
70
+ "lb.enc.encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
71
+ "lb.enc.encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
72
+ "lb.enc.encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
73
+ "lb.enc.encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
74
+ "lb.enc.encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
75
+ "lb.enc.encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
76
+ "lb.enc.encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
77
+ "lb.enc.encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
78
+ "lb.enc.encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
79
+ "lb.enc.encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
80
+ "lb.enc.encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
81
+ "lb.enc.encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
82
+ "lb.enc.encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
83
+ "lb.enc.encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
84
+ "lb.enc.encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
85
+ "lb.enc.encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
86
+ "lb.enc.encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
87
+ "lb.enc.encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
88
+ "lb.enc.encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
89
+ "lb.enc.encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
90
+ "lb.enc.encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
91
+ "lb.enc.encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
92
+ "lb.enc.encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
93
+ "lb.enc.encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
94
+ "lb.enc.encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
95
+ "lb.enc.encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
96
+ "lb.enc.encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
97
+ "lb.enc.encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
98
+ "lb.enc.encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
99
+ "lb.enc.encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
100
+ "lb.enc.encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
101
+ "lb.enc.encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
102
+ "lb.enc.encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
103
+ "lb.enc.encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
104
+ "lb.enc.encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
105
+ "lb.enc.encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
106
+ "lb.enc.encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
107
+ "lb.enc.encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
108
+ "lb.enc.encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
109
+ "lb.enc.encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
110
+ "lb.enc.encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
111
+ "lb.enc.encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
112
+ "lb.enc.encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
113
+ "lb.enc.encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
114
+ "lb.enc.encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
115
+ "lb.enc.encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
116
+ "lb.enc.encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
117
+ "lb.enc.encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
118
+ "lb.enc.encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
119
+ "lb.enc.encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
120
+ "lb.enc.encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
121
+ "lb.enc.encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
122
+ "lb.enc.encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
123
+ "lb.enc.encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
124
+ "lb.enc.encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
125
+ "lb.enc.encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
126
+ "lb.enc.encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
127
+ "lb.enc.encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
128
+ "lb.enc.encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
129
+ "lb.enc.encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
130
+ "lb.enc.encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
131
+ "lb.enc.encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
132
+ "lb.enc.encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
133
+ "lb.enc.encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
134
+ "lb.enc.encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
135
+ "lb.enc.encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
136
+ "lb.enc.encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
137
+ "lb.enc.encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
138
+ "lb.enc.encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
139
+ "lb.enc.encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
140
+ "lb.enc.encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
141
+ "lb.enc.encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
142
+ "lb.enc.encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
143
+ "lb.enc.encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
144
+ "lb.enc.encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
145
+ "lb.enc.encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
146
+ "lb.enc.encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
147
+ "lb.enc.encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
148
+ "lb.enc.encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
149
+ "lb.enc.encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
150
+ "lb.enc.encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
151
+ "lb.enc.encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
152
+ "lb.enc.encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
153
+ "lb.enc.encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
154
+ "lb.enc.encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
155
+ "lb.enc.encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
156
+ "lb.enc.encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
157
+ "lb.enc.encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
158
+ "lb.enc.encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
159
+ "lb.enc.encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
160
+ "lb.enc.encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
161
+ "lb.enc.encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
162
+ "lb.enc.encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
163
+ "lb.enc.encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
164
+ "lb.enc.encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
165
+ "lb.enc.encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
166
+ "lb.enc.encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
167
+ "lb.enc.encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
168
+ "lb.enc.encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
169
+ "lb.enc.encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
170
+ "lb.enc.encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
171
+ "lb.enc.encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
172
+ "lb.enc.encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
173
+ "lb.enc.encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
174
+ "lb.enc.encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
175
+ "lb.enc.encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
176
+ "lb.enc.encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
177
+ "lb.enc.encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
178
+ "lb.enc.encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
179
+ "lb.enc.encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
180
+ "lb.enc.encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
181
+ "lb.enc.encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
182
+ "lb.enc.encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
183
+ "lb.enc.encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
184
+ "lb.enc.encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
185
+ "lb.enc.encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
186
+ "lb.enc.encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
187
+ "lb.enc.encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
188
+ "lb.enc.encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
189
+ "lb.enc.encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
190
+ "lb.enc.encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
191
+ "lb.enc.encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
192
+ "lb.enc.encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
193
+ "lb.enc.encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
194
+ "lb.enc.encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
195
+ "lb.enc.encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
196
+ "lb.enc.encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
197
+ "lb.enc.encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
198
+ "lb.enc.encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
199
+ "lb.enc.encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
200
+ "lb.enc.encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
201
+ "lb.enc.encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
202
+ "lb.enc.encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
203
+ "lb.enc.encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
204
+ "lb.enc.encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
205
+ "lb.enc.encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
206
+ "lb.enc.encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
207
+ "lb.enc.encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
208
+ "lb.enc.encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
209
+ "lb.enc.encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
210
+ "lb.enc.encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
211
+ "lb.enc.encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
212
+ "lb.enc.encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
213
+ "lb.enc.encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
214
+ "lb.enc.encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
215
+ "lb.enc.encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
216
+ "lb.enc.encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
217
+ "lb.enc.encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
218
+ "lb.enc.encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
219
+ "lb.enc.encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
220
+ "lb.enc.encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
221
+ "lb.enc.encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
222
+ "lb.enc.encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
223
+ "lb.enc.encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
224
+ "lb.enc.encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
225
+ "lb.enc.encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
226
+ "lb.enc.encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
227
+ "lb.enc.encoder.embed_tokens.weight": "pytorch_model-00001-of-00005.bin",
228
+ "lb.enc.encoder.final_layer_norm.weight": "pytorch_model-00001-of-00005.bin",
229
+ "lb.enc.shared.weight": "pytorch_model-00001-of-00005.bin",
230
+ "lb.lm.embed_tokens.weight": "pytorch_model-00002-of-00005.bin",
231
+ "lb.lm.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
232
+ "lb.lm.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
233
+ "lb.lm.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
234
+ "lb.lm.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
235
+ "lb.lm.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
236
+ "lb.lm.layers.0.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00005.bin",
237
+ "lb.lm.layers.0.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00005.bin",
238
+ "lb.lm.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
239
+ "lb.lm.layers.0.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
240
+ "lb.lm.layers.0.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
241
+ "lb.lm.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
242
+ "lb.lm.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
243
+ "lb.lm.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
244
+ "lb.lm.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
245
+ "lb.lm.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
246
+ "lb.lm.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
247
+ "lb.lm.layers.1.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00005.bin",
248
+ "lb.lm.layers.1.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00005.bin",
249
+ "lb.lm.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
250
+ "lb.lm.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
251
+ "lb.lm.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
252
+ "lb.lm.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
253
+ "lb.lm.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
254
+ "lb.lm.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
255
+ "lb.lm.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
256
+ "lb.lm.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
257
+ "lb.lm.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
258
+ "lb.lm.layers.10.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
259
+ "lb.lm.layers.10.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
260
+ "lb.lm.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
261
+ "lb.lm.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
262
+ "lb.lm.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
263
+ "lb.lm.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
264
+ "lb.lm.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
265
+ "lb.lm.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
266
+ "lb.lm.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
267
+ "lb.lm.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
268
+ "lb.lm.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
269
+ "lb.lm.layers.11.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
270
+ "lb.lm.layers.11.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
271
+ "lb.lm.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
272
+ "lb.lm.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
273
+ "lb.lm.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
274
+ "lb.lm.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
275
+ "lb.lm.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
276
+ "lb.lm.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
277
+ "lb.lm.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
278
+ "lb.lm.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
279
+ "lb.lm.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
280
+ "lb.lm.layers.12.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
281
+ "lb.lm.layers.12.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
282
+ "lb.lm.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
283
+ "lb.lm.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
284
+ "lb.lm.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
285
+ "lb.lm.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
286
+ "lb.lm.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
287
+ "lb.lm.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
288
+ "lb.lm.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
289
+ "lb.lm.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
290
+ "lb.lm.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
291
+ "lb.lm.layers.13.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
292
+ "lb.lm.layers.13.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
293
+ "lb.lm.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
294
+ "lb.lm.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
295
+ "lb.lm.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
296
+ "lb.lm.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
297
+ "lb.lm.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
298
+ "lb.lm.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
299
+ "lb.lm.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
300
+ "lb.lm.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
301
+ "lb.lm.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
302
+ "lb.lm.layers.14.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
303
+ "lb.lm.layers.14.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
304
+ "lb.lm.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
305
+ "lb.lm.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
306
+ "lb.lm.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
307
+ "lb.lm.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
308
+ "lb.lm.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
309
+ "lb.lm.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
310
+ "lb.lm.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
311
+ "lb.lm.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
312
+ "lb.lm.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
313
+ "lb.lm.layers.15.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
314
+ "lb.lm.layers.15.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
315
+ "lb.lm.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
316
+ "lb.lm.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
317
+ "lb.lm.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
318
+ "lb.lm.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
319
+ "lb.lm.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
320
+ "lb.lm.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
321
+ "lb.lm.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
322
+ "lb.lm.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
323
+ "lb.lm.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
324
+ "lb.lm.layers.16.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
325
+ "lb.lm.layers.16.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
326
+ "lb.lm.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
327
+ "lb.lm.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
328
+ "lb.lm.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
329
+ "lb.lm.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
330
+ "lb.lm.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
331
+ "lb.lm.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
332
+ "lb.lm.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
333
+ "lb.lm.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
334
+ "lb.lm.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
335
+ "lb.lm.layers.17.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
336
+ "lb.lm.layers.17.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
337
+ "lb.lm.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
338
+ "lb.lm.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
339
+ "lb.lm.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
340
+ "lb.lm.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
341
+ "lb.lm.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
342
+ "lb.lm.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
343
+ "lb.lm.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
344
+ "lb.lm.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
345
+ "lb.lm.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
346
+ "lb.lm.layers.18.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
347
+ "lb.lm.layers.18.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
348
+ "lb.lm.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
349
+ "lb.lm.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
350
+ "lb.lm.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
351
+ "lb.lm.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
352
+ "lb.lm.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
353
+ "lb.lm.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
354
+ "lb.lm.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
355
+ "lb.lm.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
356
+ "lb.lm.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
357
+ "lb.lm.layers.19.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
358
+ "lb.lm.layers.19.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
359
+ "lb.lm.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
360
+ "lb.lm.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
361
+ "lb.lm.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
362
+ "lb.lm.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
363
+ "lb.lm.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
364
+ "lb.lm.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
365
+ "lb.lm.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
366
+ "lb.lm.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
367
+ "lb.lm.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
368
+ "lb.lm.layers.2.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00005.bin",
369
+ "lb.lm.layers.2.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00005.bin",
370
+ "lb.lm.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
371
+ "lb.lm.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
372
+ "lb.lm.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
373
+ "lb.lm.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
374
+ "lb.lm.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
375
+ "lb.lm.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
376
+ "lb.lm.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
377
+ "lb.lm.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
378
+ "lb.lm.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
379
+ "lb.lm.layers.20.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
380
+ "lb.lm.layers.20.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
381
+ "lb.lm.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
382
+ "lb.lm.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
383
+ "lb.lm.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
384
+ "lb.lm.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
385
+ "lb.lm.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
386
+ "lb.lm.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
387
+ "lb.lm.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
388
+ "lb.lm.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
389
+ "lb.lm.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
390
+ "lb.lm.layers.21.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
391
+ "lb.lm.layers.21.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
392
+ "lb.lm.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
393
+ "lb.lm.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
394
+ "lb.lm.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
395
+ "lb.lm.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
396
+ "lb.lm.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
397
+ "lb.lm.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
398
+ "lb.lm.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
399
+ "lb.lm.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
400
+ "lb.lm.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
401
+ "lb.lm.layers.22.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
402
+ "lb.lm.layers.22.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
403
+ "lb.lm.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
404
+ "lb.lm.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
405
+ "lb.lm.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
406
+ "lb.lm.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
407
+ "lb.lm.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
408
+ "lb.lm.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
409
+ "lb.lm.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
410
+ "lb.lm.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
411
+ "lb.lm.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
412
+ "lb.lm.layers.23.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
413
+ "lb.lm.layers.23.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
414
+ "lb.lm.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
415
+ "lb.lm.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
416
+ "lb.lm.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
417
+ "lb.lm.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
418
+ "lb.lm.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
419
+ "lb.lm.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
420
+ "lb.lm.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
421
+ "lb.lm.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
422
+ "lb.lm.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
423
+ "lb.lm.layers.24.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
424
+ "lb.lm.layers.24.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
425
+ "lb.lm.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
426
+ "lb.lm.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
427
+ "lb.lm.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
428
+ "lb.lm.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
429
+ "lb.lm.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
430
+ "lb.lm.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
431
+ "lb.lm.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
432
+ "lb.lm.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
433
+ "lb.lm.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
434
+ "lb.lm.layers.25.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
435
+ "lb.lm.layers.25.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
436
+ "lb.lm.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
437
+ "lb.lm.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
438
+ "lb.lm.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
439
+ "lb.lm.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
440
+ "lb.lm.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
441
+ "lb.lm.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
442
+ "lb.lm.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
443
+ "lb.lm.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
444
+ "lb.lm.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
445
+ "lb.lm.layers.26.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
446
+ "lb.lm.layers.26.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
447
+ "lb.lm.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
448
+ "lb.lm.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
449
+ "lb.lm.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
450
+ "lb.lm.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
451
+ "lb.lm.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
452
+ "lb.lm.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
453
+ "lb.lm.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
454
+ "lb.lm.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
455
+ "lb.lm.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
456
+ "lb.lm.layers.27.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
457
+ "lb.lm.layers.27.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
458
+ "lb.lm.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
459
+ "lb.lm.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
460
+ "lb.lm.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
461
+ "lb.lm.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
462
+ "lb.lm.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
463
+ "lb.lm.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
464
+ "lb.lm.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
465
+ "lb.lm.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
466
+ "lb.lm.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
467
+ "lb.lm.layers.28.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
468
+ "lb.lm.layers.28.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
469
+ "lb.lm.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
470
+ "lb.lm.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
471
+ "lb.lm.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
472
+ "lb.lm.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
473
+ "lb.lm.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
474
+ "lb.lm.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
475
+ "lb.lm.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
476
+ "lb.lm.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
477
+ "lb.lm.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
478
+ "lb.lm.layers.29.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
479
+ "lb.lm.layers.29.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
480
+ "lb.lm.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
481
+ "lb.lm.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
482
+ "lb.lm.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
483
+ "lb.lm.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
484
+ "lb.lm.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
485
+ "lb.lm.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
486
+ "lb.lm.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
487
+ "lb.lm.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
488
+ "lb.lm.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
489
+ "lb.lm.layers.3.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00005.bin",
490
+ "lb.lm.layers.3.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00005.bin",
491
+ "lb.lm.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
492
+ "lb.lm.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
493
+ "lb.lm.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
494
+ "lb.lm.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
495
+ "lb.lm.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
496
+ "lb.lm.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
497
+ "lb.lm.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
498
+ "lb.lm.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
499
+ "lb.lm.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
500
+ "lb.lm.layers.30.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
501
+ "lb.lm.layers.30.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
502
+ "lb.lm.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
503
+ "lb.lm.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
504
+ "lb.lm.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
505
+ "lb.lm.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
506
+ "lb.lm.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
507
+ "lb.lm.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
508
+ "lb.lm.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
509
+ "lb.lm.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
510
+ "lb.lm.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
511
+ "lb.lm.layers.31.post_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
512
+ "lb.lm.layers.31.pre_feedforward_layernorm.weight": "pytorch_model-00004-of-00005.bin",
513
+ "lb.lm.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
514
+ "lb.lm.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
515
+ "lb.lm.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
516
+ "lb.lm.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
517
+ "lb.lm.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
518
+ "lb.lm.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
519
+ "lb.lm.layers.32.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
520
+ "lb.lm.layers.32.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
521
+ "lb.lm.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
522
+ "lb.lm.layers.32.post_feedforward_layernorm.weight": "pytorch_model-00005-of-00005.bin",
523
+ "lb.lm.layers.32.pre_feedforward_layernorm.weight": "pytorch_model-00005-of-00005.bin",
524
+ "lb.lm.layers.32.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
525
+ "lb.lm.layers.32.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
526
+ "lb.lm.layers.32.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
527
+ "lb.lm.layers.32.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
528
+ "lb.lm.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
529
+ "lb.lm.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
530
+ "lb.lm.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
531
+ "lb.lm.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
532
+ "lb.lm.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
533
+ "lb.lm.layers.33.post_feedforward_layernorm.weight": "pytorch_model-00005-of-00005.bin",
534
+ "lb.lm.layers.33.pre_feedforward_layernorm.weight": "pytorch_model-00005-of-00005.bin",
535
+ "lb.lm.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
536
+ "lb.lm.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
537
+ "lb.lm.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
538
+ "lb.lm.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
539
+ "lb.lm.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
540
+ "lb.lm.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
541
+ "lb.lm.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
542
+ "lb.lm.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
543
+ "lb.lm.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
544
+ "lb.lm.layers.34.post_feedforward_layernorm.weight": "pytorch_model-00005-of-00005.bin",
545
+ "lb.lm.layers.34.pre_feedforward_layernorm.weight": "pytorch_model-00005-of-00005.bin",
546
+ "lb.lm.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
547
+ "lb.lm.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
548
+ "lb.lm.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
549
+ "lb.lm.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
550
+ "lb.lm.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
551
+ "lb.lm.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
552
+ "lb.lm.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
553
+ "lb.lm.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
554
+ "lb.lm.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
555
+ "lb.lm.layers.35.post_feedforward_layernorm.weight": "pytorch_model-00005-of-00005.bin",
556
+ "lb.lm.layers.35.pre_feedforward_layernorm.weight": "pytorch_model-00005-of-00005.bin",
557
+ "lb.lm.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
558
+ "lb.lm.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
559
+ "lb.lm.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
560
+ "lb.lm.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
561
+ "lb.lm.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
562
+ "lb.lm.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
563
+ "lb.lm.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
564
+ "lb.lm.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
565
+ "lb.lm.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
566
+ "lb.lm.layers.36.post_feedforward_layernorm.weight": "pytorch_model-00005-of-00005.bin",
567
+ "lb.lm.layers.36.pre_feedforward_layernorm.weight": "pytorch_model-00005-of-00005.bin",
568
+ "lb.lm.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
569
+ "lb.lm.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
570
+ "lb.lm.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
571
+ "lb.lm.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
572
+ "lb.lm.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
573
+ "lb.lm.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
574
+ "lb.lm.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
575
+ "lb.lm.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
576
+ "lb.lm.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
577
+ "lb.lm.layers.37.post_feedforward_layernorm.weight": "pytorch_model-00005-of-00005.bin",
578
+ "lb.lm.layers.37.pre_feedforward_layernorm.weight": "pytorch_model-00005-of-00005.bin",
579
+ "lb.lm.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
580
+ "lb.lm.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
581
+ "lb.lm.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
582
+ "lb.lm.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
583
+ "lb.lm.layers.38.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
584
+ "lb.lm.layers.38.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
585
+ "lb.lm.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
586
+ "lb.lm.layers.38.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
587
+ "lb.lm.layers.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
588
+ "lb.lm.layers.38.post_feedforward_layernorm.weight": "pytorch_model-00005-of-00005.bin",
589
+ "lb.lm.layers.38.pre_feedforward_layernorm.weight": "pytorch_model-00005-of-00005.bin",
590
+ "lb.lm.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
591
+ "lb.lm.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
592
+ "lb.lm.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
593
+ "lb.lm.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
594
+ "lb.lm.layers.39.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
595
+ "lb.lm.layers.39.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
596
+ "lb.lm.layers.39.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
597
+ "lb.lm.layers.39.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
598
+ "lb.lm.layers.39.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
599
+ "lb.lm.layers.39.post_feedforward_layernorm.weight": "pytorch_model-00005-of-00005.bin",
600
+ "lb.lm.layers.39.pre_feedforward_layernorm.weight": "pytorch_model-00005-of-00005.bin",
601
+ "lb.lm.layers.39.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
602
+ "lb.lm.layers.39.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
603
+ "lb.lm.layers.39.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
604
+ "lb.lm.layers.39.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
605
+ "lb.lm.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
606
+ "lb.lm.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
607
+ "lb.lm.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
608
+ "lb.lm.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
609
+ "lb.lm.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
610
+ "lb.lm.layers.4.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00005.bin",
611
+ "lb.lm.layers.4.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00005.bin",
612
+ "lb.lm.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
613
+ "lb.lm.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
614
+ "lb.lm.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
615
+ "lb.lm.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
616
+ "lb.lm.layers.40.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
617
+ "lb.lm.layers.40.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
618
+ "lb.lm.layers.40.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
619
+ "lb.lm.layers.40.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
620
+ "lb.lm.layers.40.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
621
+ "lb.lm.layers.40.post_feedforward_layernorm.weight": "pytorch_model-00005-of-00005.bin",
622
+ "lb.lm.layers.40.pre_feedforward_layernorm.weight": "pytorch_model-00005-of-00005.bin",
623
+ "lb.lm.layers.40.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
624
+ "lb.lm.layers.40.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
625
+ "lb.lm.layers.40.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
626
+ "lb.lm.layers.40.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
627
+ "lb.lm.layers.41.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
628
+ "lb.lm.layers.41.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
629
+ "lb.lm.layers.41.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
630
+ "lb.lm.layers.41.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
631
+ "lb.lm.layers.41.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
632
+ "lb.lm.layers.41.post_feedforward_layernorm.weight": "pytorch_model-00005-of-00005.bin",
633
+ "lb.lm.layers.41.pre_feedforward_layernorm.weight": "pytorch_model-00005-of-00005.bin",
634
+ "lb.lm.layers.41.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
635
+ "lb.lm.layers.41.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
636
+ "lb.lm.layers.41.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
637
+ "lb.lm.layers.41.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
638
+ "lb.lm.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
639
+ "lb.lm.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
640
+ "lb.lm.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
641
+ "lb.lm.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
642
+ "lb.lm.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
643
+ "lb.lm.layers.5.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00005.bin",
644
+ "lb.lm.layers.5.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00005.bin",
645
+ "lb.lm.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
646
+ "lb.lm.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
647
+ "lb.lm.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
648
+ "lb.lm.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
649
+ "lb.lm.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
650
+ "lb.lm.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
651
+ "lb.lm.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
652
+ "lb.lm.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
653
+ "lb.lm.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
654
+ "lb.lm.layers.6.post_feedforward_layernorm.weight": "pytorch_model-00002-of-00005.bin",
655
+ "lb.lm.layers.6.pre_feedforward_layernorm.weight": "pytorch_model-00002-of-00005.bin",
656
+ "lb.lm.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
657
+ "lb.lm.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
658
+ "lb.lm.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
659
+ "lb.lm.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
660
+ "lb.lm.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
661
+ "lb.lm.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
662
+ "lb.lm.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
663
+ "lb.lm.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
664
+ "lb.lm.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
665
+ "lb.lm.layers.7.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
666
+ "lb.lm.layers.7.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
667
+ "lb.lm.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
668
+ "lb.lm.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
669
+ "lb.lm.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
670
+ "lb.lm.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
671
+ "lb.lm.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
672
+ "lb.lm.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
673
+ "lb.lm.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
674
+ "lb.lm.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
675
+ "lb.lm.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
676
+ "lb.lm.layers.8.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
677
+ "lb.lm.layers.8.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
678
+ "lb.lm.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
679
+ "lb.lm.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
680
+ "lb.lm.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
681
+ "lb.lm.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
682
+ "lb.lm.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
683
+ "lb.lm.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
684
+ "lb.lm.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
685
+ "lb.lm.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
686
+ "lb.lm.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
687
+ "lb.lm.layers.9.post_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
688
+ "lb.lm.layers.9.pre_feedforward_layernorm.weight": "pytorch_model-00003-of-00005.bin",
689
+ "lb.lm.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
690
+ "lb.lm.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
691
+ "lb.lm.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
692
+ "lb.lm.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
693
+ "lb.lm.norm.weight": "pytorch_model-00005-of-00005.bin",
694
+ "lb.lm_head.weight": "pytorch_model-00002-of-00005.bin"
695
+ }
696
+ }