Hugging Face's logo

kaist-ai
/
metamath-langbridge-9b

Transformers
Safetensors
Inference Endpoints
Model card Files Community
DKYoon commited on
Commit
039e901
•
1 Parent(s): cc245e1

Upload model

Browse files
Files changed (7) hide show
  1. config.json +15 -0
  2. generation_config.json +4 -0
  3. model-00001-of-00004.safetensors +3 -0
  4. model-00002-of-00004.safetensors +3 -0
  5. model-00003-of-00004.safetensors +3 -0
  6. model-00004-of-00004.safetensors +3 -0
  7. model.safetensors.index.json +520 -0
config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/sda/dongkeun/checkpoints_final/metamath-langbridge-9b",
3
+ "alignments": "linear",
4
+ "architectures": [
5
+ "LangBridgeModel"
6
+ ],
7
+ "dim_enc": 2048,
8
+ "dim_lm": 4096,
9
+ "enc": "DKYoon/mt5-xl-lm-adapt",
10
+ "freeze_encoder": true,
11
+ "freeze_language_model": true,
12
+ "lm": "meta-math/MetaMath-7B-V1.0",
13
+ "torch_dtype": "bfloat16",
14
+ "transformers_version": "4.35.2"
15
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.35.2"
4
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b3fe0bb0d23ecd6e94889cf5188b92adaf0d76a5ddf9d7b49c3fc2b71f374e8
3
+ size 4967413552
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81b5d68c3270f55e7bbd1ad2ba68d48ea294dec095ad2ae3f30f2ef29b6e8c29
3
+ size 4947390824
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d75e26d04b1477ed1fcaa46aab6104307724800fe2b9fa3faa1ec4b4b2895a20
3
+ size 4947390880
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2817f3515c3c76365c6ff6435dc6587ac98d866bb60b629d7a018e732be5885c
3
+ size 1971425896
model.safetensors.index.json ADDED
@@ -0,0 +1,520 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16833558528
4
+ },
5
+ "weight_map": {
6
+ "lb.alignment.enc_eos": "model-00001-of-00004.safetensors",
7
+ "lb.alignment.linear.bias": "model-00001-of-00004.safetensors",
8
+ "lb.alignment.linear.weight": "model-00001-of-00004.safetensors",
9
+ "lb.enc.encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
10
+ "lb.enc.encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
11
+ "lb.enc.encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
12
+ "lb.enc.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00004.safetensors",
13
+ "lb.enc.encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
14
+ "lb.enc.encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
15
+ "lb.enc.encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
16
+ "lb.enc.encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
17
+ "lb.enc.encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
18
+ "lb.enc.encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
19
+ "lb.enc.encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
20
+ "lb.enc.encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
21
+ "lb.enc.encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
22
+ "lb.enc.encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
23
+ "lb.enc.encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
24
+ "lb.enc.encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
25
+ "lb.enc.encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
26
+ "lb.enc.encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
27
+ "lb.enc.encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
28
+ "lb.enc.encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
29
+ "lb.enc.encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
30
+ "lb.enc.encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
31
+ "lb.enc.encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
32
+ "lb.enc.encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
33
+ "lb.enc.encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
34
+ "lb.enc.encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
35
+ "lb.enc.encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
36
+ "lb.enc.encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
37
+ "lb.enc.encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
38
+ "lb.enc.encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
39
+ "lb.enc.encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
40
+ "lb.enc.encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
41
+ "lb.enc.encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
42
+ "lb.enc.encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
43
+ "lb.enc.encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
44
+ "lb.enc.encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
45
+ "lb.enc.encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
46
+ "lb.enc.encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
47
+ "lb.enc.encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
48
+ "lb.enc.encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
49
+ "lb.enc.encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
50
+ "lb.enc.encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
51
+ "lb.enc.encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
52
+ "lb.enc.encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
53
+ "lb.enc.encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
54
+ "lb.enc.encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
55
+ "lb.enc.encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
56
+ "lb.enc.encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
57
+ "lb.enc.encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
58
+ "lb.enc.encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
59
+ "lb.enc.encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
60
+ "lb.enc.encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
61
+ "lb.enc.encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
62
+ "lb.enc.encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
63
+ "lb.enc.encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
64
+ "lb.enc.encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
65
+ "lb.enc.encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
66
+ "lb.enc.encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
67
+ "lb.enc.encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
68
+ "lb.enc.encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
69
+ "lb.enc.encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
70
+ "lb.enc.encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
71
+ "lb.enc.encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
72
+ "lb.enc.encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
73
+ "lb.enc.encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
74
+ "lb.enc.encoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
75
+ "lb.enc.encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
76
+ "lb.enc.encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
77
+ "lb.enc.encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
78
+ "lb.enc.encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
79
+ "lb.enc.encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
80
+ "lb.enc.encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
81
+ "lb.enc.encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
82
+ "lb.enc.encoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
83
+ "lb.enc.encoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
84
+ "lb.enc.encoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
85
+ "lb.enc.encoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
86
+ "lb.enc.encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
87
+ "lb.enc.encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
88
+ "lb.enc.encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
89
+ "lb.enc.encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
90
+ "lb.enc.encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
91
+ "lb.enc.encoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
92
+ "lb.enc.encoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
93
+ "lb.enc.encoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
94
+ "lb.enc.encoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
95
+ "lb.enc.encoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
96
+ "lb.enc.encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
97
+ "lb.enc.encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
98
+ "lb.enc.encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
99
+ "lb.enc.encoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
100
+ "lb.enc.encoder.block.18.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
101
+ "lb.enc.encoder.block.18.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
102
+ "lb.enc.encoder.block.18.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
103
+ "lb.enc.encoder.block.18.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
104
+ "lb.enc.encoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
105
+ "lb.enc.encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
106
+ "lb.enc.encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
107
+ "lb.enc.encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
108
+ "lb.enc.encoder.block.18.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
109
+ "lb.enc.encoder.block.19.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
110
+ "lb.enc.encoder.block.19.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
111
+ "lb.enc.encoder.block.19.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
112
+ "lb.enc.encoder.block.19.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
113
+ "lb.enc.encoder.block.19.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
114
+ "lb.enc.encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
115
+ "lb.enc.encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
116
+ "lb.enc.encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
117
+ "lb.enc.encoder.block.19.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
118
+ "lb.enc.encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
119
+ "lb.enc.encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
120
+ "lb.enc.encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
121
+ "lb.enc.encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
122
+ "lb.enc.encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
123
+ "lb.enc.encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
124
+ "lb.enc.encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
125
+ "lb.enc.encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
126
+ "lb.enc.encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
127
+ "lb.enc.encoder.block.20.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
128
+ "lb.enc.encoder.block.20.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
129
+ "lb.enc.encoder.block.20.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
130
+ "lb.enc.encoder.block.20.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
131
+ "lb.enc.encoder.block.20.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
132
+ "lb.enc.encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
133
+ "lb.enc.encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
134
+ "lb.enc.encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
135
+ "lb.enc.encoder.block.20.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
136
+ "lb.enc.encoder.block.21.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
137
+ "lb.enc.encoder.block.21.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
138
+ "lb.enc.encoder.block.21.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
139
+ "lb.enc.encoder.block.21.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
140
+ "lb.enc.encoder.block.21.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
141
+ "lb.enc.encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
142
+ "lb.enc.encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
143
+ "lb.enc.encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
144
+ "lb.enc.encoder.block.21.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
145
+ "lb.enc.encoder.block.22.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
146
+ "lb.enc.encoder.block.22.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
147
+ "lb.enc.encoder.block.22.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
148
+ "lb.enc.encoder.block.22.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
149
+ "lb.enc.encoder.block.22.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
150
+ "lb.enc.encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
151
+ "lb.enc.encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
152
+ "lb.enc.encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
153
+ "lb.enc.encoder.block.22.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
154
+ "lb.enc.encoder.block.23.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
155
+ "lb.enc.encoder.block.23.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
156
+ "lb.enc.encoder.block.23.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
157
+ "lb.enc.encoder.block.23.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
158
+ "lb.enc.encoder.block.23.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
159
+ "lb.enc.encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
160
+ "lb.enc.encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
161
+ "lb.enc.encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
162
+ "lb.enc.encoder.block.23.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
163
+ "lb.enc.encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
164
+ "lb.enc.encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
165
+ "lb.enc.encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
166
+ "lb.enc.encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
167
+ "lb.enc.encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
168
+ "lb.enc.encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
169
+ "lb.enc.encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
170
+ "lb.enc.encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
171
+ "lb.enc.encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
172
+ "lb.enc.encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
173
+ "lb.enc.encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
174
+ "lb.enc.encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
175
+ "lb.enc.encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
176
+ "lb.enc.encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
177
+ "lb.enc.encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
178
+ "lb.enc.encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
179
+ "lb.enc.encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
180
+ "lb.enc.encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
181
+ "lb.enc.encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
182
+ "lb.enc.encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
183
+ "lb.enc.encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
184
+ "lb.enc.encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
185
+ "lb.enc.encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
186
+ "lb.enc.encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
187
+ "lb.enc.encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
188
+ "lb.enc.encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
189
+ "lb.enc.encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
190
+ "lb.enc.encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
191
+ "lb.enc.encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
192
+ "lb.enc.encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
193
+ "lb.enc.encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
194
+ "lb.enc.encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
195
+ "lb.enc.encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
196
+ "lb.enc.encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
197
+ "lb.enc.encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
198
+ "lb.enc.encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
199
+ "lb.enc.encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
200
+ "lb.enc.encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
201
+ "lb.enc.encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
202
+ "lb.enc.encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
203
+ "lb.enc.encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
204
+ "lb.enc.encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
205
+ "lb.enc.encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
206
+ "lb.enc.encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
207
+ "lb.enc.encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
208
+ "lb.enc.encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
209
+ "lb.enc.encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
210
+ "lb.enc.encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
211
+ "lb.enc.encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
212
+ "lb.enc.encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
213
+ "lb.enc.encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
214
+ "lb.enc.encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
215
+ "lb.enc.encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
216
+ "lb.enc.encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
217
+ "lb.enc.encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
218
+ "lb.enc.encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
219
+ "lb.enc.encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
220
+ "lb.enc.encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
221
+ "lb.enc.encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
222
+ "lb.enc.encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
223
+ "lb.enc.encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
224
+ "lb.enc.encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
225
+ "lb.enc.encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
226
+ "lb.enc.encoder.final_layer_norm.weight": "model-00001-of-00004.safetensors",
227
+ "lb.enc.shared.weight": "model-00001-of-00004.safetensors",
228
+ "lb.lm.embed_tokens.weight": "model-00001-of-00004.safetensors",
229
+ "lb.lm.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
230
+ "lb.lm.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
231
+ "lb.lm.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
232
+ "lb.lm.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
233
+ "lb.lm.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
234
+ "lb.lm.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
235
+ "lb.lm.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
236
+ "lb.lm.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
237
+ "lb.lm.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
238
+ "lb.lm.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
239
+ "lb.lm.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
240
+ "lb.lm.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
241
+ "lb.lm.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
242
+ "lb.lm.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "lb.lm.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
244
+ "lb.lm.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
245
+ "lb.lm.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
246
+ "lb.lm.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
247
+ "lb.lm.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
248
+ "lb.lm.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
249
+ "lb.lm.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
250
+ "lb.lm.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
251
+ "lb.lm.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
252
+ "lb.lm.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
253
+ "lb.lm.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
254
+ "lb.lm.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
255
+ "lb.lm.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
256
+ "lb.lm.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
257
+ "lb.lm.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
258
+ "lb.lm.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
259
+ "lb.lm.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
260
+ "lb.lm.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
261
+ "lb.lm.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
262
+ "lb.lm.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
263
+ "lb.lm.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
264
+ "lb.lm.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
265
+ "lb.lm.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
266
+ "lb.lm.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
267
+ "lb.lm.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
268
+ "lb.lm.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
269
+ "lb.lm.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
270
+ "lb.lm.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
271
+ "lb.lm.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
272
+ "lb.lm.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
273
+ "lb.lm.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
274
+ "lb.lm.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
275
+ "lb.lm.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
276
+ "lb.lm.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
277
+ "lb.lm.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
278
+ "lb.lm.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
279
+ "lb.lm.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
280
+ "lb.lm.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
281
+ "lb.lm.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
282
+ "lb.lm.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
283
+ "lb.lm.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
284
+ "lb.lm.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
285
+ "lb.lm.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
286
+ "lb.lm.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
287
+ "lb.lm.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "lb.lm.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
289
+ "lb.lm.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
290
+ "lb.lm.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
291
+ "lb.lm.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
292
+ "lb.lm.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
293
+ "lb.lm.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
294
+ "lb.lm.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
295
+ "lb.lm.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
296
+ "lb.lm.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
297
+ "lb.lm.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
298
+ "lb.lm.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
299
+ "lb.lm.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
300
+ "lb.lm.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
301
+ "lb.lm.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
302
+ "lb.lm.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
303
+ "lb.lm.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
304
+ "lb.lm.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
305
+ "lb.lm.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
306
+ "lb.lm.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
307
+ "lb.lm.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
308
+ "lb.lm.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
309
+ "lb.lm.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
310
+ "lb.lm.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
311
+ "lb.lm.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
312
+ "lb.lm.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
313
+ "lb.lm.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
314
+ "lb.lm.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
315
+ "lb.lm.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
316
+ "lb.lm.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
317
+ "lb.lm.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
318
+ "lb.lm.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
319
+ "lb.lm.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
320
+ "lb.lm.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
321
+ "lb.lm.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
322
+ "lb.lm.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
323
+ "lb.lm.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
324
+ "lb.lm.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
325
+ "lb.lm.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
326
+ "lb.lm.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
327
+ "lb.lm.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
328
+ "lb.lm.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
329
+ "lb.lm.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
330
+ "lb.lm.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
331
+ "lb.lm.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
332
+ "lb.lm.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
333
+ "lb.lm.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
334
+ "lb.lm.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
335
+ "lb.lm.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
336
+ "lb.lm.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
337
+ "lb.lm.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
338
+ "lb.lm.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
339
+ "lb.lm.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
340
+ "lb.lm.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
341
+ "lb.lm.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
342
+ "lb.lm.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
343
+ "lb.lm.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
344
+ "lb.lm.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
345
+ "lb.lm.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
346
+ "lb.lm.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
347
+ "lb.lm.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
348
+ "lb.lm.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
349
+ "lb.lm.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
350
+ "lb.lm.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
351
+ "lb.lm.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
352
+ "lb.lm.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
353
+ "lb.lm.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
354
+ "lb.lm.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
355
+ "lb.lm.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
356
+ "lb.lm.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
357
+ "lb.lm.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
358
+ "lb.lm.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
359
+ "lb.lm.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
360
+ "lb.lm.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
361
+ "lb.lm.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
362
+ "lb.lm.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
363
+ "lb.lm.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
364
+ "lb.lm.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
365
+ "lb.lm.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
366
+ "lb.lm.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
367
+ "lb.lm.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
368
+ "lb.lm.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
369
+ "lb.lm.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
370
+ "lb.lm.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
371
+ "lb.lm.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
372
+ "lb.lm.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
373
+ "lb.lm.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
374
+ "lb.lm.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
375
+ "lb.lm.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
376
+ "lb.lm.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
377
+ "lb.lm.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
378
+ "lb.lm.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
379
+ "lb.lm.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
380
+ "lb.lm.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
381
+ "lb.lm.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
382
+ "lb.lm.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
383
+ "lb.lm.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
384
+ "lb.lm.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
385
+ "lb.lm.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
386
+ "lb.lm.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
387
+ "lb.lm.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
388
+ "lb.lm.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
389
+ "lb.lm.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
390
+ "lb.lm.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
391
+ "lb.lm.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
392
+ "lb.lm.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
393
+ "lb.lm.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
394
+ "lb.lm.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
395
+ "lb.lm.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
396
+ "lb.lm.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
397
+ "lb.lm.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
398
+ "lb.lm.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
399
+ "lb.lm.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
400
+ "lb.lm.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
401
+ "lb.lm.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
402
+ "lb.lm.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
403
+ "lb.lm.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
404
+ "lb.lm.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
405
+ "lb.lm.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
406
+ "lb.lm.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
407
+ "lb.lm.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
408
+ "lb.lm.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
409
+ "lb.lm.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
410
+ "lb.lm.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
411
+ "lb.lm.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
412
+ "lb.lm.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
413
+ "lb.lm.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
414
+ "lb.lm.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
415
+ "lb.lm.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
416
+ "lb.lm.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
417
+ "lb.lm.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
418
+ "lb.lm.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
419
+ "lb.lm.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
420
+ "lb.lm.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
421
+ "lb.lm.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
422
+ "lb.lm.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
423
+ "lb.lm.layers.28.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
424
+ "lb.lm.layers.28.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
425
+ "lb.lm.layers.28.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
426
+ "lb.lm.layers.28.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
427
+ "lb.lm.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
428
+ "lb.lm.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
429
+ "lb.lm.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
430
+ "lb.lm.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
431
+ "lb.lm.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
432
+ "lb.lm.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
433
+ "lb.lm.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
434
+ "lb.lm.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
435
+ "lb.lm.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
436
+ "lb.lm.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
437
+ "lb.lm.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
438
+ "lb.lm.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
439
+ "lb.lm.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
440
+ "lb.lm.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
441
+ "lb.lm.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
442
+ "lb.lm.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
443
+ "lb.lm.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
444
+ "lb.lm.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
445
+ "lb.lm.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
446
+ "lb.lm.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
447
+ "lb.lm.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
448
+ "lb.lm.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
449
+ "lb.lm.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
450
+ "lb.lm.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
451
+ "lb.lm.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
452
+ "lb.lm.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
453
+ "lb.lm.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
454
+ "lb.lm.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
455
+ "lb.lm.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
456
+ "lb.lm.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
457
+ "lb.lm.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
458
+ "lb.lm.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
459
+ "lb.lm.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
460
+ "lb.lm.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
461
+ "lb.lm.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
462
+ "lb.lm.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
463
+ "lb.lm.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
464
+ "lb.lm.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
465
+ "lb.lm.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
466
+ "lb.lm.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
467
+ "lb.lm.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
468
+ "lb.lm.layers.4.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
469
+ "lb.lm.layers.4.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
470
+ "lb.lm.layers.4.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
471
+ "lb.lm.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
472
+ "lb.lm.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
473
+ "lb.lm.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
474
+ "lb.lm.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
475
+ "lb.lm.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
476
+ "lb.lm.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
477
+ "lb.lm.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
478
+ "lb.lm.layers.5.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
479
+ "lb.lm.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
480
+ "lb.lm.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
481
+ "lb.lm.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
482
+ "lb.lm.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
483
+ "lb.lm.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
484
+ "lb.lm.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
485
+ "lb.lm.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
486
+ "lb.lm.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
487
+ "lb.lm.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
488
+ "lb.lm.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
489
+ "lb.lm.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
490
+ "lb.lm.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
491
+ "lb.lm.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
492
+ "lb.lm.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
493
+ "lb.lm.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
494
+ "lb.lm.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
495
+ "lb.lm.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
496
+ "lb.lm.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
497
+ "lb.lm.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
498
+ "lb.lm.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
499
+ "lb.lm.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
500
+ "lb.lm.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
501
+ "lb.lm.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
502
+ "lb.lm.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
503
+ "lb.lm.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
504
+ "lb.lm.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
505
+ "lb.lm.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
506
+ "lb.lm.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
507
+ "lb.lm.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
508
+ "lb.lm.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
509
+ "lb.lm.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
510
+ "lb.lm.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
511
+ "lb.lm.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
512
+ "lb.lm.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
513
+ "lb.lm.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
514
+ "lb.lm.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
515
+ "lb.lm.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
516
+ "lb.lm.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
517
+ "lb.lm.norm.weight": "model-00004-of-00004.safetensors",
518
+ "lb.lm_head.weight": "model-00004-of-00004.safetensors"
519
+ }
520
+ }