v2ray commited on
Commit
f8680d0
1 Parent(s): 118579b

Upload folder using huggingface_hub

Browse files
__init__.py ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ from .configuration_grok import *
2
+ from .modeling_grok import *
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "hf/",
3
  "architectures": [
4
  "GrokForCausalLM"
5
  ],
 
1
  {
2
+ "_name_or_path": "grok",
3
  "architectures": [
4
  "GrokForCausalLM"
5
  ],
model-00001-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fae4638b4fc0299dcafe947f1cdf76bf7a69d4e9fb69c193f67ab89aa34c376c
3
+ size 4958457672
model-00002-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eac30089a1f3cd214a210a67d795a748ff00b12d73cddce7cfb7e8a04cacc2b1
3
+ size 4958655552
model-00003-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6d74b4180040b1a209adbf3f695370f465bcaee39e3f11d51096c5d10e202fb
3
+ size 4732261544
model-00004-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3058039cb929b9a468fd22d13255e595307e413144b421b793b81ccdab93d58
3
+ size 4958655592
model-00005-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28e64f1177eef0b0bc86593fb6dc4458a5b49d0d5ef5d4fafb66b567c2c7287b
3
+ size 4732261592
model-00006-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c56aef5249666b49c1343228ddbf1279c2ab4422cb98cb53b3e5b0387d27676e
3
+ size 4958655600
model-00007-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:478526e8598450fd4231dfe84832fb9865eb62c231273349ecbb2593f4b7cf72
3
+ size 4732261592
model-00008-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b4648e9c1e92a9d7344fb2e8d2dd4896a4489cc309b64f11f34110db374aa41
3
+ size 4958655600
model-00009-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d45d38b0ced5ef5f6470f47b4df1d5f74e6482a903bba04fd63f4441eaeb035c
3
+ size 4732261592
model-00010-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2a53115b58fa9544a0b0e00696cda3ece771dd77edf5dc0e9c320fcfbf782f5
3
+ size 4958655600
model-00011-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5e6b630792a33357c2993309479d172d79fedcbe9be540480e3ca582ff65a58
3
+ size 4732261592
model-00012-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96b2f0a0c985921a9c15b55f134594812e6e53f76bc91890421d32070d16f048
3
+ size 4958655600
model-00013-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96ed70e3f45808ee0ece374045275be2d0d1cee75bab3a3a863e461e5a66c1d7
3
+ size 4732261592
model-00014-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdc9513b9dd70b7974e136f843a7613653b0aeca76ece604995d6d21e93720e8
3
+ size 4958655600
model-00015-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51379d67ac3b5525ce49eda9ee30edd2e98d27697b3d888e8b2c9e2d87080510
3
+ size 4732261592
model-00016-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc38dde94a0ec295b7c57d725d3c048502aae2868de10ae96c8d623fb4606722
3
+ size 4958655600
model-00017-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d55f1848da09769f88fdc1f4933909a29a7d0686b830e4f711d903e46592cf42
3
+ size 4732261592
model-00018-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10a6ab4893eb048f142e8900e3e30bbd3c0aaeaa00704dad666c38b3ed0e63f5
3
+ size 4958655600
model-00019-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b054303f82fc96d8343b969c52174e7d3423fcf3694d0eda6c50ebb9471813c
3
+ size 2768858160
model.safetensors.index.json ADDED
@@ -0,0 +1,777 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 90213212160
4
+ },
5
+ "weight_map": {
6
+ "transformer.decoder_layer.0.moe.0.linear.weight": "model-00001-of-00019.safetensors",
7
+ "transformer.decoder_layer.0.moe.0.linear_1.weight": "model-00001-of-00019.safetensors",
8
+ "transformer.decoder_layer.0.moe.0.linear_v.weight": "model-00001-of-00019.safetensors",
9
+ "transformer.decoder_layer.0.multi_head_attention.key.weight": "model-00001-of-00019.safetensors",
10
+ "transformer.decoder_layer.0.multi_head_attention.linear.weight": "model-00001-of-00019.safetensors",
11
+ "transformer.decoder_layer.0.multi_head_attention.query.weight": "model-00001-of-00019.safetensors",
12
+ "transformer.decoder_layer.0.multi_head_attention.value.weight": "model-00001-of-00019.safetensors",
13
+ "transformer.decoder_layer.0.rms_norm.weight": "model-00001-of-00019.safetensors",
14
+ "transformer.decoder_layer.0.rms_norm_1.weight": "model-00001-of-00019.safetensors",
15
+ "transformer.decoder_layer.0.rms_norm_2.weight": "model-00001-of-00019.safetensors",
16
+ "transformer.decoder_layer.0.rms_norm_3.weight": "model-00001-of-00019.safetensors",
17
+ "transformer.decoder_layer.0.router.weight": "model-00001-of-00019.safetensors",
18
+ "transformer.decoder_layer.1.moe.0.linear.weight": "model-00001-of-00019.safetensors",
19
+ "transformer.decoder_layer.1.moe.0.linear_1.weight": "model-00001-of-00019.safetensors",
20
+ "transformer.decoder_layer.1.moe.0.linear_v.weight": "model-00001-of-00019.safetensors",
21
+ "transformer.decoder_layer.1.multi_head_attention.key.weight": "model-00001-of-00019.safetensors",
22
+ "transformer.decoder_layer.1.multi_head_attention.linear.weight": "model-00001-of-00019.safetensors",
23
+ "transformer.decoder_layer.1.multi_head_attention.query.weight": "model-00001-of-00019.safetensors",
24
+ "transformer.decoder_layer.1.multi_head_attention.value.weight": "model-00001-of-00019.safetensors",
25
+ "transformer.decoder_layer.1.rms_norm.weight": "model-00001-of-00019.safetensors",
26
+ "transformer.decoder_layer.1.rms_norm_1.weight": "model-00001-of-00019.safetensors",
27
+ "transformer.decoder_layer.1.rms_norm_2.weight": "model-00001-of-00019.safetensors",
28
+ "transformer.decoder_layer.1.rms_norm_3.weight": "model-00001-of-00019.safetensors",
29
+ "transformer.decoder_layer.1.router.weight": "model-00001-of-00019.safetensors",
30
+ "transformer.decoder_layer.10.moe.0.linear.weight": "model-00004-of-00019.safetensors",
31
+ "transformer.decoder_layer.10.moe.0.linear_1.weight": "model-00004-of-00019.safetensors",
32
+ "transformer.decoder_layer.10.moe.0.linear_v.weight": "model-00004-of-00019.safetensors",
33
+ "transformer.decoder_layer.10.multi_head_attention.key.weight": "model-00004-of-00019.safetensors",
34
+ "transformer.decoder_layer.10.multi_head_attention.linear.weight": "model-00004-of-00019.safetensors",
35
+ "transformer.decoder_layer.10.multi_head_attention.query.weight": "model-00004-of-00019.safetensors",
36
+ "transformer.decoder_layer.10.multi_head_attention.value.weight": "model-00004-of-00019.safetensors",
37
+ "transformer.decoder_layer.10.rms_norm.weight": "model-00004-of-00019.safetensors",
38
+ "transformer.decoder_layer.10.rms_norm_1.weight": "model-00004-of-00019.safetensors",
39
+ "transformer.decoder_layer.10.rms_norm_2.weight": "model-00004-of-00019.safetensors",
40
+ "transformer.decoder_layer.10.rms_norm_3.weight": "model-00004-of-00019.safetensors",
41
+ "transformer.decoder_layer.10.router.weight": "model-00004-of-00019.safetensors",
42
+ "transformer.decoder_layer.11.moe.0.linear.weight": "model-00004-of-00019.safetensors",
43
+ "transformer.decoder_layer.11.moe.0.linear_1.weight": "model-00004-of-00019.safetensors",
44
+ "transformer.decoder_layer.11.moe.0.linear_v.weight": "model-00004-of-00019.safetensors",
45
+ "transformer.decoder_layer.11.multi_head_attention.key.weight": "model-00004-of-00019.safetensors",
46
+ "transformer.decoder_layer.11.multi_head_attention.linear.weight": "model-00004-of-00019.safetensors",
47
+ "transformer.decoder_layer.11.multi_head_attention.query.weight": "model-00004-of-00019.safetensors",
48
+ "transformer.decoder_layer.11.multi_head_attention.value.weight": "model-00004-of-00019.safetensors",
49
+ "transformer.decoder_layer.11.rms_norm.weight": "model-00004-of-00019.safetensors",
50
+ "transformer.decoder_layer.11.rms_norm_1.weight": "model-00004-of-00019.safetensors",
51
+ "transformer.decoder_layer.11.rms_norm_2.weight": "model-00004-of-00019.safetensors",
52
+ "transformer.decoder_layer.11.rms_norm_3.weight": "model-00004-of-00019.safetensors",
53
+ "transformer.decoder_layer.11.router.weight": "model-00004-of-00019.safetensors",
54
+ "transformer.decoder_layer.12.moe.0.linear.weight": "model-00004-of-00019.safetensors",
55
+ "transformer.decoder_layer.12.moe.0.linear_1.weight": "model-00004-of-00019.safetensors",
56
+ "transformer.decoder_layer.12.moe.0.linear_v.weight": "model-00004-of-00019.safetensors",
57
+ "transformer.decoder_layer.12.multi_head_attention.key.weight": "model-00004-of-00019.safetensors",
58
+ "transformer.decoder_layer.12.multi_head_attention.linear.weight": "model-00004-of-00019.safetensors",
59
+ "transformer.decoder_layer.12.multi_head_attention.query.weight": "model-00004-of-00019.safetensors",
60
+ "transformer.decoder_layer.12.multi_head_attention.value.weight": "model-00004-of-00019.safetensors",
61
+ "transformer.decoder_layer.12.rms_norm.weight": "model-00004-of-00019.safetensors",
62
+ "transformer.decoder_layer.12.rms_norm_1.weight": "model-00004-of-00019.safetensors",
63
+ "transformer.decoder_layer.12.rms_norm_2.weight": "model-00004-of-00019.safetensors",
64
+ "transformer.decoder_layer.12.rms_norm_3.weight": "model-00004-of-00019.safetensors",
65
+ "transformer.decoder_layer.12.router.weight": "model-00004-of-00019.safetensors",
66
+ "transformer.decoder_layer.13.moe.0.linear.weight": "model-00005-of-00019.safetensors",
67
+ "transformer.decoder_layer.13.moe.0.linear_1.weight": "model-00005-of-00019.safetensors",
68
+ "transformer.decoder_layer.13.moe.0.linear_v.weight": "model-00005-of-00019.safetensors",
69
+ "transformer.decoder_layer.13.multi_head_attention.key.weight": "model-00005-of-00019.safetensors",
70
+ "transformer.decoder_layer.13.multi_head_attention.linear.weight": "model-00005-of-00019.safetensors",
71
+ "transformer.decoder_layer.13.multi_head_attention.query.weight": "model-00005-of-00019.safetensors",
72
+ "transformer.decoder_layer.13.multi_head_attention.value.weight": "model-00005-of-00019.safetensors",
73
+ "transformer.decoder_layer.13.rms_norm.weight": "model-00005-of-00019.safetensors",
74
+ "transformer.decoder_layer.13.rms_norm_1.weight": "model-00005-of-00019.safetensors",
75
+ "transformer.decoder_layer.13.rms_norm_2.weight": "model-00005-of-00019.safetensors",
76
+ "transformer.decoder_layer.13.rms_norm_3.weight": "model-00005-of-00019.safetensors",
77
+ "transformer.decoder_layer.13.router.weight": "model-00005-of-00019.safetensors",
78
+ "transformer.decoder_layer.14.moe.0.linear.weight": "model-00005-of-00019.safetensors",
79
+ "transformer.decoder_layer.14.moe.0.linear_1.weight": "model-00005-of-00019.safetensors",
80
+ "transformer.decoder_layer.14.moe.0.linear_v.weight": "model-00005-of-00019.safetensors",
81
+ "transformer.decoder_layer.14.multi_head_attention.key.weight": "model-00005-of-00019.safetensors",
82
+ "transformer.decoder_layer.14.multi_head_attention.linear.weight": "model-00005-of-00019.safetensors",
83
+ "transformer.decoder_layer.14.multi_head_attention.query.weight": "model-00005-of-00019.safetensors",
84
+ "transformer.decoder_layer.14.multi_head_attention.value.weight": "model-00005-of-00019.safetensors",
85
+ "transformer.decoder_layer.14.rms_norm.weight": "model-00005-of-00019.safetensors",
86
+ "transformer.decoder_layer.14.rms_norm_1.weight": "model-00005-of-00019.safetensors",
87
+ "transformer.decoder_layer.14.rms_norm_2.weight": "model-00005-of-00019.safetensors",
88
+ "transformer.decoder_layer.14.rms_norm_3.weight": "model-00005-of-00019.safetensors",
89
+ "transformer.decoder_layer.14.router.weight": "model-00005-of-00019.safetensors",
90
+ "transformer.decoder_layer.15.moe.0.linear.weight": "model-00005-of-00019.safetensors",
91
+ "transformer.decoder_layer.15.moe.0.linear_1.weight": "model-00005-of-00019.safetensors",
92
+ "transformer.decoder_layer.15.moe.0.linear_v.weight": "model-00005-of-00019.safetensors",
93
+ "transformer.decoder_layer.15.multi_head_attention.key.weight": "model-00005-of-00019.safetensors",
94
+ "transformer.decoder_layer.15.multi_head_attention.linear.weight": "model-00005-of-00019.safetensors",
95
+ "transformer.decoder_layer.15.multi_head_attention.query.weight": "model-00005-of-00019.safetensors",
96
+ "transformer.decoder_layer.15.multi_head_attention.value.weight": "model-00005-of-00019.safetensors",
97
+ "transformer.decoder_layer.15.rms_norm.weight": "model-00005-of-00019.safetensors",
98
+ "transformer.decoder_layer.15.rms_norm_1.weight": "model-00005-of-00019.safetensors",
99
+ "transformer.decoder_layer.15.rms_norm_2.weight": "model-00005-of-00019.safetensors",
100
+ "transformer.decoder_layer.15.rms_norm_3.weight": "model-00005-of-00019.safetensors",
101
+ "transformer.decoder_layer.15.router.weight": "model-00005-of-00019.safetensors",
102
+ "transformer.decoder_layer.16.moe.0.linear.weight": "model-00006-of-00019.safetensors",
103
+ "transformer.decoder_layer.16.moe.0.linear_1.weight": "model-00006-of-00019.safetensors",
104
+ "transformer.decoder_layer.16.moe.0.linear_v.weight": "model-00005-of-00019.safetensors",
105
+ "transformer.decoder_layer.16.multi_head_attention.key.weight": "model-00005-of-00019.safetensors",
106
+ "transformer.decoder_layer.16.multi_head_attention.linear.weight": "model-00005-of-00019.safetensors",
107
+ "transformer.decoder_layer.16.multi_head_attention.query.weight": "model-00005-of-00019.safetensors",
108
+ "transformer.decoder_layer.16.multi_head_attention.value.weight": "model-00005-of-00019.safetensors",
109
+ "transformer.decoder_layer.16.rms_norm.weight": "model-00006-of-00019.safetensors",
110
+ "transformer.decoder_layer.16.rms_norm_1.weight": "model-00006-of-00019.safetensors",
111
+ "transformer.decoder_layer.16.rms_norm_2.weight": "model-00006-of-00019.safetensors",
112
+ "transformer.decoder_layer.16.rms_norm_3.weight": "model-00006-of-00019.safetensors",
113
+ "transformer.decoder_layer.16.router.weight": "model-00005-of-00019.safetensors",
114
+ "transformer.decoder_layer.17.moe.0.linear.weight": "model-00006-of-00019.safetensors",
115
+ "transformer.decoder_layer.17.moe.0.linear_1.weight": "model-00006-of-00019.safetensors",
116
+ "transformer.decoder_layer.17.moe.0.linear_v.weight": "model-00006-of-00019.safetensors",
117
+ "transformer.decoder_layer.17.multi_head_attention.key.weight": "model-00006-of-00019.safetensors",
118
+ "transformer.decoder_layer.17.multi_head_attention.linear.weight": "model-00006-of-00019.safetensors",
119
+ "transformer.decoder_layer.17.multi_head_attention.query.weight": "model-00006-of-00019.safetensors",
120
+ "transformer.decoder_layer.17.multi_head_attention.value.weight": "model-00006-of-00019.safetensors",
121
+ "transformer.decoder_layer.17.rms_norm.weight": "model-00006-of-00019.safetensors",
122
+ "transformer.decoder_layer.17.rms_norm_1.weight": "model-00006-of-00019.safetensors",
123
+ "transformer.decoder_layer.17.rms_norm_2.weight": "model-00006-of-00019.safetensors",
124
+ "transformer.decoder_layer.17.rms_norm_3.weight": "model-00006-of-00019.safetensors",
125
+ "transformer.decoder_layer.17.router.weight": "model-00006-of-00019.safetensors",
126
+ "transformer.decoder_layer.18.moe.0.linear.weight": "model-00006-of-00019.safetensors",
127
+ "transformer.decoder_layer.18.moe.0.linear_1.weight": "model-00006-of-00019.safetensors",
128
+ "transformer.decoder_layer.18.moe.0.linear_v.weight": "model-00006-of-00019.safetensors",
129
+ "transformer.decoder_layer.18.multi_head_attention.key.weight": "model-00006-of-00019.safetensors",
130
+ "transformer.decoder_layer.18.multi_head_attention.linear.weight": "model-00006-of-00019.safetensors",
131
+ "transformer.decoder_layer.18.multi_head_attention.query.weight": "model-00006-of-00019.safetensors",
132
+ "transformer.decoder_layer.18.multi_head_attention.value.weight": "model-00006-of-00019.safetensors",
133
+ "transformer.decoder_layer.18.rms_norm.weight": "model-00006-of-00019.safetensors",
134
+ "transformer.decoder_layer.18.rms_norm_1.weight": "model-00006-of-00019.safetensors",
135
+ "transformer.decoder_layer.18.rms_norm_2.weight": "model-00006-of-00019.safetensors",
136
+ "transformer.decoder_layer.18.rms_norm_3.weight": "model-00006-of-00019.safetensors",
137
+ "transformer.decoder_layer.18.router.weight": "model-00006-of-00019.safetensors",
138
+ "transformer.decoder_layer.19.moe.0.linear.weight": "model-00006-of-00019.safetensors",
139
+ "transformer.decoder_layer.19.moe.0.linear_1.weight": "model-00006-of-00019.safetensors",
140
+ "transformer.decoder_layer.19.moe.0.linear_v.weight": "model-00006-of-00019.safetensors",
141
+ "transformer.decoder_layer.19.multi_head_attention.key.weight": "model-00006-of-00019.safetensors",
142
+ "transformer.decoder_layer.19.multi_head_attention.linear.weight": "model-00006-of-00019.safetensors",
143
+ "transformer.decoder_layer.19.multi_head_attention.query.weight": "model-00006-of-00019.safetensors",
144
+ "transformer.decoder_layer.19.multi_head_attention.value.weight": "model-00006-of-00019.safetensors",
145
+ "transformer.decoder_layer.19.rms_norm.weight": "model-00006-of-00019.safetensors",
146
+ "transformer.decoder_layer.19.rms_norm_1.weight": "model-00006-of-00019.safetensors",
147
+ "transformer.decoder_layer.19.rms_norm_2.weight": "model-00006-of-00019.safetensors",
148
+ "transformer.decoder_layer.19.rms_norm_3.weight": "model-00006-of-00019.safetensors",
149
+ "transformer.decoder_layer.19.router.weight": "model-00006-of-00019.safetensors",
150
+ "transformer.decoder_layer.2.moe.0.linear.weight": "model-00002-of-00019.safetensors",
151
+ "transformer.decoder_layer.2.moe.0.linear_1.weight": "model-00002-of-00019.safetensors",
152
+ "transformer.decoder_layer.2.moe.0.linear_v.weight": "model-00001-of-00019.safetensors",
153
+ "transformer.decoder_layer.2.multi_head_attention.key.weight": "model-00001-of-00019.safetensors",
154
+ "transformer.decoder_layer.2.multi_head_attention.linear.weight": "model-00001-of-00019.safetensors",
155
+ "transformer.decoder_layer.2.multi_head_attention.query.weight": "model-00001-of-00019.safetensors",
156
+ "transformer.decoder_layer.2.multi_head_attention.value.weight": "model-00001-of-00019.safetensors",
157
+ "transformer.decoder_layer.2.rms_norm.weight": "model-00002-of-00019.safetensors",
158
+ "transformer.decoder_layer.2.rms_norm_1.weight": "model-00002-of-00019.safetensors",
159
+ "transformer.decoder_layer.2.rms_norm_2.weight": "model-00002-of-00019.safetensors",
160
+ "transformer.decoder_layer.2.rms_norm_3.weight": "model-00002-of-00019.safetensors",
161
+ "transformer.decoder_layer.2.router.weight": "model-00001-of-00019.safetensors",
162
+ "transformer.decoder_layer.20.moe.0.linear.weight": "model-00007-of-00019.safetensors",
163
+ "transformer.decoder_layer.20.moe.0.linear_1.weight": "model-00007-of-00019.safetensors",
164
+ "transformer.decoder_layer.20.moe.0.linear_v.weight": "model-00007-of-00019.safetensors",
165
+ "transformer.decoder_layer.20.multi_head_attention.key.weight": "model-00007-of-00019.safetensors",
166
+ "transformer.decoder_layer.20.multi_head_attention.linear.weight": "model-00007-of-00019.safetensors",
167
+ "transformer.decoder_layer.20.multi_head_attention.query.weight": "model-00007-of-00019.safetensors",
168
+ "transformer.decoder_layer.20.multi_head_attention.value.weight": "model-00007-of-00019.safetensors",
169
+ "transformer.decoder_layer.20.rms_norm.weight": "model-00007-of-00019.safetensors",
170
+ "transformer.decoder_layer.20.rms_norm_1.weight": "model-00007-of-00019.safetensors",
171
+ "transformer.decoder_layer.20.rms_norm_2.weight": "model-00007-of-00019.safetensors",
172
+ "transformer.decoder_layer.20.rms_norm_3.weight": "model-00007-of-00019.safetensors",
173
+ "transformer.decoder_layer.20.router.weight": "model-00007-of-00019.safetensors",
174
+ "transformer.decoder_layer.21.moe.0.linear.weight": "model-00007-of-00019.safetensors",
175
+ "transformer.decoder_layer.21.moe.0.linear_1.weight": "model-00007-of-00019.safetensors",
176
+ "transformer.decoder_layer.21.moe.0.linear_v.weight": "model-00007-of-00019.safetensors",
177
+ "transformer.decoder_layer.21.multi_head_attention.key.weight": "model-00007-of-00019.safetensors",
178
+ "transformer.decoder_layer.21.multi_head_attention.linear.weight": "model-00007-of-00019.safetensors",
179
+ "transformer.decoder_layer.21.multi_head_attention.query.weight": "model-00007-of-00019.safetensors",
180
+ "transformer.decoder_layer.21.multi_head_attention.value.weight": "model-00007-of-00019.safetensors",
181
+ "transformer.decoder_layer.21.rms_norm.weight": "model-00007-of-00019.safetensors",
182
+ "transformer.decoder_layer.21.rms_norm_1.weight": "model-00007-of-00019.safetensors",
183
+ "transformer.decoder_layer.21.rms_norm_2.weight": "model-00007-of-00019.safetensors",
184
+ "transformer.decoder_layer.21.rms_norm_3.weight": "model-00007-of-00019.safetensors",
185
+ "transformer.decoder_layer.21.router.weight": "model-00007-of-00019.safetensors",
186
+ "transformer.decoder_layer.22.moe.0.linear.weight": "model-00007-of-00019.safetensors",
187
+ "transformer.decoder_layer.22.moe.0.linear_1.weight": "model-00007-of-00019.safetensors",
188
+ "transformer.decoder_layer.22.moe.0.linear_v.weight": "model-00007-of-00019.safetensors",
189
+ "transformer.decoder_layer.22.multi_head_attention.key.weight": "model-00007-of-00019.safetensors",
190
+ "transformer.decoder_layer.22.multi_head_attention.linear.weight": "model-00007-of-00019.safetensors",
191
+ "transformer.decoder_layer.22.multi_head_attention.query.weight": "model-00007-of-00019.safetensors",
192
+ "transformer.decoder_layer.22.multi_head_attention.value.weight": "model-00007-of-00019.safetensors",
193
+ "transformer.decoder_layer.22.rms_norm.weight": "model-00007-of-00019.safetensors",
194
+ "transformer.decoder_layer.22.rms_norm_1.weight": "model-00007-of-00019.safetensors",
195
+ "transformer.decoder_layer.22.rms_norm_2.weight": "model-00007-of-00019.safetensors",
196
+ "transformer.decoder_layer.22.rms_norm_3.weight": "model-00007-of-00019.safetensors",
197
+ "transformer.decoder_layer.22.router.weight": "model-00007-of-00019.safetensors",
198
+ "transformer.decoder_layer.23.moe.0.linear.weight": "model-00008-of-00019.safetensors",
199
+ "transformer.decoder_layer.23.moe.0.linear_1.weight": "model-00008-of-00019.safetensors",
200
+ "transformer.decoder_layer.23.moe.0.linear_v.weight": "model-00007-of-00019.safetensors",
201
+ "transformer.decoder_layer.23.multi_head_attention.key.weight": "model-00007-of-00019.safetensors",
202
+ "transformer.decoder_layer.23.multi_head_attention.linear.weight": "model-00007-of-00019.safetensors",
203
+ "transformer.decoder_layer.23.multi_head_attention.query.weight": "model-00007-of-00019.safetensors",
204
+ "transformer.decoder_layer.23.multi_head_attention.value.weight": "model-00007-of-00019.safetensors",
205
+ "transformer.decoder_layer.23.rms_norm.weight": "model-00008-of-00019.safetensors",
206
+ "transformer.decoder_layer.23.rms_norm_1.weight": "model-00008-of-00019.safetensors",
207
+ "transformer.decoder_layer.23.rms_norm_2.weight": "model-00008-of-00019.safetensors",
208
+ "transformer.decoder_layer.23.rms_norm_3.weight": "model-00008-of-00019.safetensors",
209
+ "transformer.decoder_layer.23.router.weight": "model-00007-of-00019.safetensors",
210
+ "transformer.decoder_layer.24.moe.0.linear.weight": "model-00008-of-00019.safetensors",
211
+ "transformer.decoder_layer.24.moe.0.linear_1.weight": "model-00008-of-00019.safetensors",
212
+ "transformer.decoder_layer.24.moe.0.linear_v.weight": "model-00008-of-00019.safetensors",
213
+ "transformer.decoder_layer.24.multi_head_attention.key.weight": "model-00008-of-00019.safetensors",
214
+ "transformer.decoder_layer.24.multi_head_attention.linear.weight": "model-00008-of-00019.safetensors",
215
+ "transformer.decoder_layer.24.multi_head_attention.query.weight": "model-00008-of-00019.safetensors",
216
+ "transformer.decoder_layer.24.multi_head_attention.value.weight": "model-00008-of-00019.safetensors",
217
+ "transformer.decoder_layer.24.rms_norm.weight": "model-00008-of-00019.safetensors",
218
+ "transformer.decoder_layer.24.rms_norm_1.weight": "model-00008-of-00019.safetensors",
219
+ "transformer.decoder_layer.24.rms_norm_2.weight": "model-00008-of-00019.safetensors",
220
+ "transformer.decoder_layer.24.rms_norm_3.weight": "model-00008-of-00019.safetensors",
221
+ "transformer.decoder_layer.24.router.weight": "model-00008-of-00019.safetensors",
222
+ "transformer.decoder_layer.25.moe.0.linear.weight": "model-00008-of-00019.safetensors",
223
+ "transformer.decoder_layer.25.moe.0.linear_1.weight": "model-00008-of-00019.safetensors",
224
+ "transformer.decoder_layer.25.moe.0.linear_v.weight": "model-00008-of-00019.safetensors",
225
+ "transformer.decoder_layer.25.multi_head_attention.key.weight": "model-00008-of-00019.safetensors",
226
+ "transformer.decoder_layer.25.multi_head_attention.linear.weight": "model-00008-of-00019.safetensors",
227
+ "transformer.decoder_layer.25.multi_head_attention.query.weight": "model-00008-of-00019.safetensors",
228
+ "transformer.decoder_layer.25.multi_head_attention.value.weight": "model-00008-of-00019.safetensors",
229
+ "transformer.decoder_layer.25.rms_norm.weight": "model-00008-of-00019.safetensors",
230
+ "transformer.decoder_layer.25.rms_norm_1.weight": "model-00008-of-00019.safetensors",
231
+ "transformer.decoder_layer.25.rms_norm_2.weight": "model-00008-of-00019.safetensors",
232
+ "transformer.decoder_layer.25.rms_norm_3.weight": "model-00008-of-00019.safetensors",
233
+ "transformer.decoder_layer.25.router.weight": "model-00008-of-00019.safetensors",
234
+ "transformer.decoder_layer.26.moe.0.linear.weight": "model-00008-of-00019.safetensors",
235
+ "transformer.decoder_layer.26.moe.0.linear_1.weight": "model-00008-of-00019.safetensors",
236
+ "transformer.decoder_layer.26.moe.0.linear_v.weight": "model-00008-of-00019.safetensors",
237
+ "transformer.decoder_layer.26.multi_head_attention.key.weight": "model-00008-of-00019.safetensors",
238
+ "transformer.decoder_layer.26.multi_head_attention.linear.weight": "model-00008-of-00019.safetensors",
239
+ "transformer.decoder_layer.26.multi_head_attention.query.weight": "model-00008-of-00019.safetensors",
240
+ "transformer.decoder_layer.26.multi_head_attention.value.weight": "model-00008-of-00019.safetensors",
241
+ "transformer.decoder_layer.26.rms_norm.weight": "model-00008-of-00019.safetensors",
242
+ "transformer.decoder_layer.26.rms_norm_1.weight": "model-00008-of-00019.safetensors",
243
+ "transformer.decoder_layer.26.rms_norm_2.weight": "model-00008-of-00019.safetensors",
244
+ "transformer.decoder_layer.26.rms_norm_3.weight": "model-00008-of-00019.safetensors",
245
+ "transformer.decoder_layer.26.router.weight": "model-00008-of-00019.safetensors",
246
+ "transformer.decoder_layer.27.moe.0.linear.weight": "model-00009-of-00019.safetensors",
247
+ "transformer.decoder_layer.27.moe.0.linear_1.weight": "model-00009-of-00019.safetensors",
248
+ "transformer.decoder_layer.27.moe.0.linear_v.weight": "model-00009-of-00019.safetensors",
249
+ "transformer.decoder_layer.27.multi_head_attention.key.weight": "model-00009-of-00019.safetensors",
250
+ "transformer.decoder_layer.27.multi_head_attention.linear.weight": "model-00009-of-00019.safetensors",
251
+ "transformer.decoder_layer.27.multi_head_attention.query.weight": "model-00009-of-00019.safetensors",
252
+ "transformer.decoder_layer.27.multi_head_attention.value.weight": "model-00009-of-00019.safetensors",
253
+ "transformer.decoder_layer.27.rms_norm.weight": "model-00009-of-00019.safetensors",
254
+ "transformer.decoder_layer.27.rms_norm_1.weight": "model-00009-of-00019.safetensors",
255
+ "transformer.decoder_layer.27.rms_norm_2.weight": "model-00009-of-00019.safetensors",
256
+ "transformer.decoder_layer.27.rms_norm_3.weight": "model-00009-of-00019.safetensors",
257
+ "transformer.decoder_layer.27.router.weight": "model-00009-of-00019.safetensors",
258
+ "transformer.decoder_layer.28.moe.0.linear.weight": "model-00009-of-00019.safetensors",
259
+ "transformer.decoder_layer.28.moe.0.linear_1.weight": "model-00009-of-00019.safetensors",
260
+ "transformer.decoder_layer.28.moe.0.linear_v.weight": "model-00009-of-00019.safetensors",
261
+ "transformer.decoder_layer.28.multi_head_attention.key.weight": "model-00009-of-00019.safetensors",
262
+ "transformer.decoder_layer.28.multi_head_attention.linear.weight": "model-00009-of-00019.safetensors",
263
+ "transformer.decoder_layer.28.multi_head_attention.query.weight": "model-00009-of-00019.safetensors",
264
+ "transformer.decoder_layer.28.multi_head_attention.value.weight": "model-00009-of-00019.safetensors",
265
+ "transformer.decoder_layer.28.rms_norm.weight": "model-00009-of-00019.safetensors",
266
+ "transformer.decoder_layer.28.rms_norm_1.weight": "model-00009-of-00019.safetensors",
267
+ "transformer.decoder_layer.28.rms_norm_2.weight": "model-00009-of-00019.safetensors",
268
+ "transformer.decoder_layer.28.rms_norm_3.weight": "model-00009-of-00019.safetensors",
269
+ "transformer.decoder_layer.28.router.weight": "model-00009-of-00019.safetensors",
270
+ "transformer.decoder_layer.29.moe.0.linear.weight": "model-00009-of-00019.safetensors",
271
+ "transformer.decoder_layer.29.moe.0.linear_1.weight": "model-00009-of-00019.safetensors",
272
+ "transformer.decoder_layer.29.moe.0.linear_v.weight": "model-00009-of-00019.safetensors",
273
+ "transformer.decoder_layer.29.multi_head_attention.key.weight": "model-00009-of-00019.safetensors",
274
+ "transformer.decoder_layer.29.multi_head_attention.linear.weight": "model-00009-of-00019.safetensors",
275
+ "transformer.decoder_layer.29.multi_head_attention.query.weight": "model-00009-of-00019.safetensors",
276
+ "transformer.decoder_layer.29.multi_head_attention.value.weight": "model-00009-of-00019.safetensors",
277
+ "transformer.decoder_layer.29.rms_norm.weight": "model-00009-of-00019.safetensors",
278
+ "transformer.decoder_layer.29.rms_norm_1.weight": "model-00009-of-00019.safetensors",
279
+ "transformer.decoder_layer.29.rms_norm_2.weight": "model-00009-of-00019.safetensors",
280
+ "transformer.decoder_layer.29.rms_norm_3.weight": "model-00009-of-00019.safetensors",
281
+ "transformer.decoder_layer.29.router.weight": "model-00009-of-00019.safetensors",
282
+ "transformer.decoder_layer.3.moe.0.linear.weight": "model-00002-of-00019.safetensors",
283
+ "transformer.decoder_layer.3.moe.0.linear_1.weight": "model-00002-of-00019.safetensors",
284
+ "transformer.decoder_layer.3.moe.0.linear_v.weight": "model-00002-of-00019.safetensors",
285
+ "transformer.decoder_layer.3.multi_head_attention.key.weight": "model-00002-of-00019.safetensors",
286
+ "transformer.decoder_layer.3.multi_head_attention.linear.weight": "model-00002-of-00019.safetensors",
287
+ "transformer.decoder_layer.3.multi_head_attention.query.weight": "model-00002-of-00019.safetensors",
288
+ "transformer.decoder_layer.3.multi_head_attention.value.weight": "model-00002-of-00019.safetensors",
289
+ "transformer.decoder_layer.3.rms_norm.weight": "model-00002-of-00019.safetensors",
290
+ "transformer.decoder_layer.3.rms_norm_1.weight": "model-00002-of-00019.safetensors",
291
+ "transformer.decoder_layer.3.rms_norm_2.weight": "model-00002-of-00019.safetensors",
292
+ "transformer.decoder_layer.3.rms_norm_3.weight": "model-00002-of-00019.safetensors",
293
+ "transformer.decoder_layer.3.router.weight": "model-00002-of-00019.safetensors",
294
+ "transformer.decoder_layer.30.moe.0.linear.weight": "model-00010-of-00019.safetensors",
295
+ "transformer.decoder_layer.30.moe.0.linear_1.weight": "model-00010-of-00019.safetensors",
296
+ "transformer.decoder_layer.30.moe.0.linear_v.weight": "model-00009-of-00019.safetensors",
297
+ "transformer.decoder_layer.30.multi_head_attention.key.weight": "model-00009-of-00019.safetensors",
298
+ "transformer.decoder_layer.30.multi_head_attention.linear.weight": "model-00009-of-00019.safetensors",
299
+ "transformer.decoder_layer.30.multi_head_attention.query.weight": "model-00009-of-00019.safetensors",
300
+ "transformer.decoder_layer.30.multi_head_attention.value.weight": "model-00009-of-00019.safetensors",
301
+ "transformer.decoder_layer.30.rms_norm.weight": "model-00010-of-00019.safetensors",
302
+ "transformer.decoder_layer.30.rms_norm_1.weight": "model-00010-of-00019.safetensors",
303
+ "transformer.decoder_layer.30.rms_norm_2.weight": "model-00010-of-00019.safetensors",
304
+ "transformer.decoder_layer.30.rms_norm_3.weight": "model-00010-of-00019.safetensors",
305
+ "transformer.decoder_layer.30.router.weight": "model-00009-of-00019.safetensors",
306
+ "transformer.decoder_layer.31.moe.0.linear.weight": "model-00010-of-00019.safetensors",
307
+ "transformer.decoder_layer.31.moe.0.linear_1.weight": "model-00010-of-00019.safetensors",
308
+ "transformer.decoder_layer.31.moe.0.linear_v.weight": "model-00010-of-00019.safetensors",
309
+ "transformer.decoder_layer.31.multi_head_attention.key.weight": "model-00010-of-00019.safetensors",
310
+ "transformer.decoder_layer.31.multi_head_attention.linear.weight": "model-00010-of-00019.safetensors",
311
+ "transformer.decoder_layer.31.multi_head_attention.query.weight": "model-00010-of-00019.safetensors",
312
+ "transformer.decoder_layer.31.multi_head_attention.value.weight": "model-00010-of-00019.safetensors",
313
+ "transformer.decoder_layer.31.rms_norm.weight": "model-00010-of-00019.safetensors",
314
+ "transformer.decoder_layer.31.rms_norm_1.weight": "model-00010-of-00019.safetensors",
315
+ "transformer.decoder_layer.31.rms_norm_2.weight": "model-00010-of-00019.safetensors",
316
+ "transformer.decoder_layer.31.rms_norm_3.weight": "model-00010-of-00019.safetensors",
317
+ "transformer.decoder_layer.31.router.weight": "model-00010-of-00019.safetensors",
318
+ "transformer.decoder_layer.32.moe.0.linear.weight": "model-00010-of-00019.safetensors",
319
+ "transformer.decoder_layer.32.moe.0.linear_1.weight": "model-00010-of-00019.safetensors",
320
+ "transformer.decoder_layer.32.moe.0.linear_v.weight": "model-00010-of-00019.safetensors",
321
+ "transformer.decoder_layer.32.multi_head_attention.key.weight": "model-00010-of-00019.safetensors",
322
+ "transformer.decoder_layer.32.multi_head_attention.linear.weight": "model-00010-of-00019.safetensors",
323
+ "transformer.decoder_layer.32.multi_head_attention.query.weight": "model-00010-of-00019.safetensors",
324
+ "transformer.decoder_layer.32.multi_head_attention.value.weight": "model-00010-of-00019.safetensors",
325
+ "transformer.decoder_layer.32.rms_norm.weight": "model-00010-of-00019.safetensors",
326
+ "transformer.decoder_layer.32.rms_norm_1.weight": "model-00010-of-00019.safetensors",
327
+ "transformer.decoder_layer.32.rms_norm_2.weight": "model-00010-of-00019.safetensors",
328
+ "transformer.decoder_layer.32.rms_norm_3.weight": "model-00010-of-00019.safetensors",
329
+ "transformer.decoder_layer.32.router.weight": "model-00010-of-00019.safetensors",
330
+ "transformer.decoder_layer.33.moe.0.linear.weight": "model-00010-of-00019.safetensors",
331
+ "transformer.decoder_layer.33.moe.0.linear_1.weight": "model-00010-of-00019.safetensors",
332
+ "transformer.decoder_layer.33.moe.0.linear_v.weight": "model-00010-of-00019.safetensors",
333
+ "transformer.decoder_layer.33.multi_head_attention.key.weight": "model-00010-of-00019.safetensors",
334
+ "transformer.decoder_layer.33.multi_head_attention.linear.weight": "model-00010-of-00019.safetensors",
335
+ "transformer.decoder_layer.33.multi_head_attention.query.weight": "model-00010-of-00019.safetensors",
336
+ "transformer.decoder_layer.33.multi_head_attention.value.weight": "model-00010-of-00019.safetensors",
337
+ "transformer.decoder_layer.33.rms_norm.weight": "model-00010-of-00019.safetensors",
338
+ "transformer.decoder_layer.33.rms_norm_1.weight": "model-00010-of-00019.safetensors",
339
+ "transformer.decoder_layer.33.rms_norm_2.weight": "model-00010-of-00019.safetensors",
340
+ "transformer.decoder_layer.33.rms_norm_3.weight": "model-00010-of-00019.safetensors",
341
+ "transformer.decoder_layer.33.router.weight": "model-00010-of-00019.safetensors",
342
+ "transformer.decoder_layer.34.moe.0.linear.weight": "model-00011-of-00019.safetensors",
343
+ "transformer.decoder_layer.34.moe.0.linear_1.weight": "model-00011-of-00019.safetensors",
344
+ "transformer.decoder_layer.34.moe.0.linear_v.weight": "model-00011-of-00019.safetensors",
345
+ "transformer.decoder_layer.34.multi_head_attention.key.weight": "model-00011-of-00019.safetensors",
346
+ "transformer.decoder_layer.34.multi_head_attention.linear.weight": "model-00011-of-00019.safetensors",
347
+ "transformer.decoder_layer.34.multi_head_attention.query.weight": "model-00011-of-00019.safetensors",
348
+ "transformer.decoder_layer.34.multi_head_attention.value.weight": "model-00011-of-00019.safetensors",
349
+ "transformer.decoder_layer.34.rms_norm.weight": "model-00011-of-00019.safetensors",
350
+ "transformer.decoder_layer.34.rms_norm_1.weight": "model-00011-of-00019.safetensors",
351
+ "transformer.decoder_layer.34.rms_norm_2.weight": "model-00011-of-00019.safetensors",
352
+ "transformer.decoder_layer.34.rms_norm_3.weight": "model-00011-of-00019.safetensors",
353
+ "transformer.decoder_layer.34.router.weight": "model-00011-of-00019.safetensors",
354
+ "transformer.decoder_layer.35.moe.0.linear.weight": "model-00011-of-00019.safetensors",
355
+ "transformer.decoder_layer.35.moe.0.linear_1.weight": "model-00011-of-00019.safetensors",
356
+ "transformer.decoder_layer.35.moe.0.linear_v.weight": "model-00011-of-00019.safetensors",
357
+ "transformer.decoder_layer.35.multi_head_attention.key.weight": "model-00011-of-00019.safetensors",
358
+ "transformer.decoder_layer.35.multi_head_attention.linear.weight": "model-00011-of-00019.safetensors",
359
+ "transformer.decoder_layer.35.multi_head_attention.query.weight": "model-00011-of-00019.safetensors",
360
+ "transformer.decoder_layer.35.multi_head_attention.value.weight": "model-00011-of-00019.safetensors",
361
+ "transformer.decoder_layer.35.rms_norm.weight": "model-00011-of-00019.safetensors",
362
+ "transformer.decoder_layer.35.rms_norm_1.weight": "model-00011-of-00019.safetensors",
363
+ "transformer.decoder_layer.35.rms_norm_2.weight": "model-00011-of-00019.safetensors",
364
+ "transformer.decoder_layer.35.rms_norm_3.weight": "model-00011-of-00019.safetensors",
365
+ "transformer.decoder_layer.35.router.weight": "model-00011-of-00019.safetensors",
366
+ "transformer.decoder_layer.36.moe.0.linear.weight": "model-00011-of-00019.safetensors",
367
+ "transformer.decoder_layer.36.moe.0.linear_1.weight": "model-00011-of-00019.safetensors",
368
+ "transformer.decoder_layer.36.moe.0.linear_v.weight": "model-00011-of-00019.safetensors",
369
+ "transformer.decoder_layer.36.multi_head_attention.key.weight": "model-00011-of-00019.safetensors",
370
+ "transformer.decoder_layer.36.multi_head_attention.linear.weight": "model-00011-of-00019.safetensors",
371
+ "transformer.decoder_layer.36.multi_head_attention.query.weight": "model-00011-of-00019.safetensors",
372
+ "transformer.decoder_layer.36.multi_head_attention.value.weight": "model-00011-of-00019.safetensors",
373
+ "transformer.decoder_layer.36.rms_norm.weight": "model-00011-of-00019.safetensors",
374
+ "transformer.decoder_layer.36.rms_norm_1.weight": "model-00011-of-00019.safetensors",
375
+ "transformer.decoder_layer.36.rms_norm_2.weight": "model-00011-of-00019.safetensors",
376
+ "transformer.decoder_layer.36.rms_norm_3.weight": "model-00011-of-00019.safetensors",
377
+ "transformer.decoder_layer.36.router.weight": "model-00011-of-00019.safetensors",
378
+ "transformer.decoder_layer.37.moe.0.linear.weight": "model-00012-of-00019.safetensors",
379
+ "transformer.decoder_layer.37.moe.0.linear_1.weight": "model-00012-of-00019.safetensors",
380
+ "transformer.decoder_layer.37.moe.0.linear_v.weight": "model-00011-of-00019.safetensors",
381
+ "transformer.decoder_layer.37.multi_head_attention.key.weight": "model-00011-of-00019.safetensors",
382
+ "transformer.decoder_layer.37.multi_head_attention.linear.weight": "model-00011-of-00019.safetensors",
383
+ "transformer.decoder_layer.37.multi_head_attention.query.weight": "model-00011-of-00019.safetensors",
384
+ "transformer.decoder_layer.37.multi_head_attention.value.weight": "model-00011-of-00019.safetensors",
385
+ "transformer.decoder_layer.37.rms_norm.weight": "model-00012-of-00019.safetensors",
386
+ "transformer.decoder_layer.37.rms_norm_1.weight": "model-00012-of-00019.safetensors",
387
+ "transformer.decoder_layer.37.rms_norm_2.weight": "model-00012-of-00019.safetensors",
388
+ "transformer.decoder_layer.37.rms_norm_3.weight": "model-00012-of-00019.safetensors",
389
+ "transformer.decoder_layer.37.router.weight": "model-00011-of-00019.safetensors",
390
+ "transformer.decoder_layer.38.moe.0.linear.weight": "model-00012-of-00019.safetensors",
391
+ "transformer.decoder_layer.38.moe.0.linear_1.weight": "model-00012-of-00019.safetensors",
392
+ "transformer.decoder_layer.38.moe.0.linear_v.weight": "model-00012-of-00019.safetensors",
393
+ "transformer.decoder_layer.38.multi_head_attention.key.weight": "model-00012-of-00019.safetensors",
394
+ "transformer.decoder_layer.38.multi_head_attention.linear.weight": "model-00012-of-00019.safetensors",
395
+ "transformer.decoder_layer.38.multi_head_attention.query.weight": "model-00012-of-00019.safetensors",
396
+ "transformer.decoder_layer.38.multi_head_attention.value.weight": "model-00012-of-00019.safetensors",
397
+ "transformer.decoder_layer.38.rms_norm.weight": "model-00012-of-00019.safetensors",
398
+ "transformer.decoder_layer.38.rms_norm_1.weight": "model-00012-of-00019.safetensors",
399
+ "transformer.decoder_layer.38.rms_norm_2.weight": "model-00012-of-00019.safetensors",
400
+ "transformer.decoder_layer.38.rms_norm_3.weight": "model-00012-of-00019.safetensors",
401
+ "transformer.decoder_layer.38.router.weight": "model-00012-of-00019.safetensors",
402
+ "transformer.decoder_layer.39.moe.0.linear.weight": "model-00012-of-00019.safetensors",
403
+ "transformer.decoder_layer.39.moe.0.linear_1.weight": "model-00012-of-00019.safetensors",
404
+ "transformer.decoder_layer.39.moe.0.linear_v.weight": "model-00012-of-00019.safetensors",
405
+ "transformer.decoder_layer.39.multi_head_attention.key.weight": "model-00012-of-00019.safetensors",
406
+ "transformer.decoder_layer.39.multi_head_attention.linear.weight": "model-00012-of-00019.safetensors",
407
+ "transformer.decoder_layer.39.multi_head_attention.query.weight": "model-00012-of-00019.safetensors",
408
+ "transformer.decoder_layer.39.multi_head_attention.value.weight": "model-00012-of-00019.safetensors",
409
+ "transformer.decoder_layer.39.rms_norm.weight": "model-00012-of-00019.safetensors",
410
+ "transformer.decoder_layer.39.rms_norm_1.weight": "model-00012-of-00019.safetensors",
411
+ "transformer.decoder_layer.39.rms_norm_2.weight": "model-00012-of-00019.safetensors",
412
+ "transformer.decoder_layer.39.rms_norm_3.weight": "model-00012-of-00019.safetensors",
413
+ "transformer.decoder_layer.39.router.weight": "model-00012-of-00019.safetensors",
414
+ "transformer.decoder_layer.4.moe.0.linear.weight": "model-00002-of-00019.safetensors",
415
+ "transformer.decoder_layer.4.moe.0.linear_1.weight": "model-00002-of-00019.safetensors",
416
+ "transformer.decoder_layer.4.moe.0.linear_v.weight": "model-00002-of-00019.safetensors",
417
+ "transformer.decoder_layer.4.multi_head_attention.key.weight": "model-00002-of-00019.safetensors",
418
+ "transformer.decoder_layer.4.multi_head_attention.linear.weight": "model-00002-of-00019.safetensors",
419
+ "transformer.decoder_layer.4.multi_head_attention.query.weight": "model-00002-of-00019.safetensors",
420
+ "transformer.decoder_layer.4.multi_head_attention.value.weight": "model-00002-of-00019.safetensors",
421
+ "transformer.decoder_layer.4.rms_norm.weight": "model-00002-of-00019.safetensors",
422
+ "transformer.decoder_layer.4.rms_norm_1.weight": "model-00002-of-00019.safetensors",
423
+ "transformer.decoder_layer.4.rms_norm_2.weight": "model-00002-of-00019.safetensors",
424
+ "transformer.decoder_layer.4.rms_norm_3.weight": "model-00002-of-00019.safetensors",
425
+ "transformer.decoder_layer.4.router.weight": "model-00002-of-00019.safetensors",
426
+ "transformer.decoder_layer.40.moe.0.linear.weight": "model-00012-of-00019.safetensors",
427
+ "transformer.decoder_layer.40.moe.0.linear_1.weight": "model-00012-of-00019.safetensors",
428
+ "transformer.decoder_layer.40.moe.0.linear_v.weight": "model-00012-of-00019.safetensors",
429
+ "transformer.decoder_layer.40.multi_head_attention.key.weight": "model-00012-of-00019.safetensors",
430
+ "transformer.decoder_layer.40.multi_head_attention.linear.weight": "model-00012-of-00019.safetensors",
431
+ "transformer.decoder_layer.40.multi_head_attention.query.weight": "model-00012-of-00019.safetensors",
432
+ "transformer.decoder_layer.40.multi_head_attention.value.weight": "model-00012-of-00019.safetensors",
433
+ "transformer.decoder_layer.40.rms_norm.weight": "model-00012-of-00019.safetensors",
434
+ "transformer.decoder_layer.40.rms_norm_1.weight": "model-00012-of-00019.safetensors",
435
+ "transformer.decoder_layer.40.rms_norm_2.weight": "model-00012-of-00019.safetensors",
436
+ "transformer.decoder_layer.40.rms_norm_3.weight": "model-00012-of-00019.safetensors",
437
+ "transformer.decoder_layer.40.router.weight": "model-00012-of-00019.safetensors",
438
+ "transformer.decoder_layer.41.moe.0.linear.weight": "model-00013-of-00019.safetensors",
439
+ "transformer.decoder_layer.41.moe.0.linear_1.weight": "model-00013-of-00019.safetensors",
440
+ "transformer.decoder_layer.41.moe.0.linear_v.weight": "model-00013-of-00019.safetensors",
441
+ "transformer.decoder_layer.41.multi_head_attention.key.weight": "model-00013-of-00019.safetensors",
442
+ "transformer.decoder_layer.41.multi_head_attention.linear.weight": "model-00013-of-00019.safetensors",
443
+ "transformer.decoder_layer.41.multi_head_attention.query.weight": "model-00013-of-00019.safetensors",
444
+ "transformer.decoder_layer.41.multi_head_attention.value.weight": "model-00013-of-00019.safetensors",
445
+ "transformer.decoder_layer.41.rms_norm.weight": "model-00013-of-00019.safetensors",
446
+ "transformer.decoder_layer.41.rms_norm_1.weight": "model-00013-of-00019.safetensors",
447
+ "transformer.decoder_layer.41.rms_norm_2.weight": "model-00013-of-00019.safetensors",
448
+ "transformer.decoder_layer.41.rms_norm_3.weight": "model-00013-of-00019.safetensors",
449
+ "transformer.decoder_layer.41.router.weight": "model-00013-of-00019.safetensors",
450
+ "transformer.decoder_layer.42.moe.0.linear.weight": "model-00013-of-00019.safetensors",
451
+ "transformer.decoder_layer.42.moe.0.linear_1.weight": "model-00013-of-00019.safetensors",
452
+ "transformer.decoder_layer.42.moe.0.linear_v.weight": "model-00013-of-00019.safetensors",
453
+ "transformer.decoder_layer.42.multi_head_attention.key.weight": "model-00013-of-00019.safetensors",
454
+ "transformer.decoder_layer.42.multi_head_attention.linear.weight": "model-00013-of-00019.safetensors",
455
+ "transformer.decoder_layer.42.multi_head_attention.query.weight": "model-00013-of-00019.safetensors",
456
+ "transformer.decoder_layer.42.multi_head_attention.value.weight": "model-00013-of-00019.safetensors",
457
+ "transformer.decoder_layer.42.rms_norm.weight": "model-00013-of-00019.safetensors",
458
+ "transformer.decoder_layer.42.rms_norm_1.weight": "model-00013-of-00019.safetensors",
459
+ "transformer.decoder_layer.42.rms_norm_2.weight": "model-00013-of-00019.safetensors",
460
+ "transformer.decoder_layer.42.rms_norm_3.weight": "model-00013-of-00019.safetensors",
461
+ "transformer.decoder_layer.42.router.weight": "model-00013-of-00019.safetensors",
462
+ "transformer.decoder_layer.43.moe.0.linear.weight": "model-00013-of-00019.safetensors",
463
+ "transformer.decoder_layer.43.moe.0.linear_1.weight": "model-00013-of-00019.safetensors",
464
+ "transformer.decoder_layer.43.moe.0.linear_v.weight": "model-00013-of-00019.safetensors",
465
+ "transformer.decoder_layer.43.multi_head_attention.key.weight": "model-00013-of-00019.safetensors",
466
+ "transformer.decoder_layer.43.multi_head_attention.linear.weight": "model-00013-of-00019.safetensors",
467
+ "transformer.decoder_layer.43.multi_head_attention.query.weight": "model-00013-of-00019.safetensors",
468
+ "transformer.decoder_layer.43.multi_head_attention.value.weight": "model-00013-of-00019.safetensors",
469
+ "transformer.decoder_layer.43.rms_norm.weight": "model-00013-of-00019.safetensors",
470
+ "transformer.decoder_layer.43.rms_norm_1.weight": "model-00013-of-00019.safetensors",
471
+ "transformer.decoder_layer.43.rms_norm_2.weight": "model-00013-of-00019.safetensors",
472
+ "transformer.decoder_layer.43.rms_norm_3.weight": "model-00013-of-00019.safetensors",
473
+ "transformer.decoder_layer.43.router.weight": "model-00013-of-00019.safetensors",
474
+ "transformer.decoder_layer.44.moe.0.linear.weight": "model-00014-of-00019.safetensors",
475
+ "transformer.decoder_layer.44.moe.0.linear_1.weight": "model-00014-of-00019.safetensors",
476
+ "transformer.decoder_layer.44.moe.0.linear_v.weight": "model-00013-of-00019.safetensors",
477
+ "transformer.decoder_layer.44.multi_head_attention.key.weight": "model-00013-of-00019.safetensors",
478
+ "transformer.decoder_layer.44.multi_head_attention.linear.weight": "model-00013-of-00019.safetensors",
479
+ "transformer.decoder_layer.44.multi_head_attention.query.weight": "model-00013-of-00019.safetensors",
480
+ "transformer.decoder_layer.44.multi_head_attention.value.weight": "model-00013-of-00019.safetensors",
481
+ "transformer.decoder_layer.44.rms_norm.weight": "model-00014-of-00019.safetensors",
482
+ "transformer.decoder_layer.44.rms_norm_1.weight": "model-00014-of-00019.safetensors",
483
+ "transformer.decoder_layer.44.rms_norm_2.weight": "model-00014-of-00019.safetensors",
484
+ "transformer.decoder_layer.44.rms_norm_3.weight": "model-00014-of-00019.safetensors",
485
+ "transformer.decoder_layer.44.router.weight": "model-00013-of-00019.safetensors",
486
+ "transformer.decoder_layer.45.moe.0.linear.weight": "model-00014-of-00019.safetensors",
487
+ "transformer.decoder_layer.45.moe.0.linear_1.weight": "model-00014-of-00019.safetensors",
488
+ "transformer.decoder_layer.45.moe.0.linear_v.weight": "model-00014-of-00019.safetensors",
489
+ "transformer.decoder_layer.45.multi_head_attention.key.weight": "model-00014-of-00019.safetensors",
490
+ "transformer.decoder_layer.45.multi_head_attention.linear.weight": "model-00014-of-00019.safetensors",
491
+ "transformer.decoder_layer.45.multi_head_attention.query.weight": "model-00014-of-00019.safetensors",
492
+ "transformer.decoder_layer.45.multi_head_attention.value.weight": "model-00014-of-00019.safetensors",
493
+ "transformer.decoder_layer.45.rms_norm.weight": "model-00014-of-00019.safetensors",
494
+ "transformer.decoder_layer.45.rms_norm_1.weight": "model-00014-of-00019.safetensors",
495
+ "transformer.decoder_layer.45.rms_norm_2.weight": "model-00014-of-00019.safetensors",
496
+ "transformer.decoder_layer.45.rms_norm_3.weight": "model-00014-of-00019.safetensors",
497
+ "transformer.decoder_layer.45.router.weight": "model-00014-of-00019.safetensors",
498
+ "transformer.decoder_layer.46.moe.0.linear.weight": "model-00014-of-00019.safetensors",
499
+ "transformer.decoder_layer.46.moe.0.linear_1.weight": "model-00014-of-00019.safetensors",
500
+ "transformer.decoder_layer.46.moe.0.linear_v.weight": "model-00014-of-00019.safetensors",
501
+ "transformer.decoder_layer.46.multi_head_attention.key.weight": "model-00014-of-00019.safetensors",
502
+ "transformer.decoder_layer.46.multi_head_attention.linear.weight": "model-00014-of-00019.safetensors",
503
+ "transformer.decoder_layer.46.multi_head_attention.query.weight": "model-00014-of-00019.safetensors",
504
+ "transformer.decoder_layer.46.multi_head_attention.value.weight": "model-00014-of-00019.safetensors",
505
+ "transformer.decoder_layer.46.rms_norm.weight": "model-00014-of-00019.safetensors",
506
+ "transformer.decoder_layer.46.rms_norm_1.weight": "model-00014-of-00019.safetensors",
507
+ "transformer.decoder_layer.46.rms_norm_2.weight": "model-00014-of-00019.safetensors",
508
+ "transformer.decoder_layer.46.rms_norm_3.weight": "model-00014-of-00019.safetensors",
509
+ "transformer.decoder_layer.46.router.weight": "model-00014-of-00019.safetensors",
510
+ "transformer.decoder_layer.47.moe.0.linear.weight": "model-00014-of-00019.safetensors",
511
+ "transformer.decoder_layer.47.moe.0.linear_1.weight": "model-00014-of-00019.safetensors",
512
+ "transformer.decoder_layer.47.moe.0.linear_v.weight": "model-00014-of-00019.safetensors",
513
+ "transformer.decoder_layer.47.multi_head_attention.key.weight": "model-00014-of-00019.safetensors",
514
+ "transformer.decoder_layer.47.multi_head_attention.linear.weight": "model-00014-of-00019.safetensors",
515
+ "transformer.decoder_layer.47.multi_head_attention.query.weight": "model-00014-of-00019.safetensors",
516
+ "transformer.decoder_layer.47.multi_head_attention.value.weight": "model-00014-of-00019.safetensors",
517
+ "transformer.decoder_layer.47.rms_norm.weight": "model-00014-of-00019.safetensors",
518
+ "transformer.decoder_layer.47.rms_norm_1.weight": "model-00014-of-00019.safetensors",
519
+ "transformer.decoder_layer.47.rms_norm_2.weight": "model-00014-of-00019.safetensors",
520
+ "transformer.decoder_layer.47.rms_norm_3.weight": "model-00014-of-00019.safetensors",
521
+ "transformer.decoder_layer.47.router.weight": "model-00014-of-00019.safetensors",
522
+ "transformer.decoder_layer.48.moe.0.linear.weight": "model-00015-of-00019.safetensors",
523
+ "transformer.decoder_layer.48.moe.0.linear_1.weight": "model-00015-of-00019.safetensors",
524
+ "transformer.decoder_layer.48.moe.0.linear_v.weight": "model-00015-of-00019.safetensors",
525
+ "transformer.decoder_layer.48.multi_head_attention.key.weight": "model-00015-of-00019.safetensors",
526
+ "transformer.decoder_layer.48.multi_head_attention.linear.weight": "model-00015-of-00019.safetensors",
527
+ "transformer.decoder_layer.48.multi_head_attention.query.weight": "model-00015-of-00019.safetensors",
528
+ "transformer.decoder_layer.48.multi_head_attention.value.weight": "model-00015-of-00019.safetensors",
529
+ "transformer.decoder_layer.48.rms_norm.weight": "model-00015-of-00019.safetensors",
530
+ "transformer.decoder_layer.48.rms_norm_1.weight": "model-00015-of-00019.safetensors",
531
+ "transformer.decoder_layer.48.rms_norm_2.weight": "model-00015-of-00019.safetensors",
532
+ "transformer.decoder_layer.48.rms_norm_3.weight": "model-00015-of-00019.safetensors",
533
+ "transformer.decoder_layer.48.router.weight": "model-00015-of-00019.safetensors",
534
+ "transformer.decoder_layer.49.moe.0.linear.weight": "model-00015-of-00019.safetensors",
535
+ "transformer.decoder_layer.49.moe.0.linear_1.weight": "model-00015-of-00019.safetensors",
536
+ "transformer.decoder_layer.49.moe.0.linear_v.weight": "model-00015-of-00019.safetensors",
537
+ "transformer.decoder_layer.49.multi_head_attention.key.weight": "model-00015-of-00019.safetensors",
538
+ "transformer.decoder_layer.49.multi_head_attention.linear.weight": "model-00015-of-00019.safetensors",
539
+ "transformer.decoder_layer.49.multi_head_attention.query.weight": "model-00015-of-00019.safetensors",
540
+ "transformer.decoder_layer.49.multi_head_attention.value.weight": "model-00015-of-00019.safetensors",
541
+ "transformer.decoder_layer.49.rms_norm.weight": "model-00015-of-00019.safetensors",
542
+ "transformer.decoder_layer.49.rms_norm_1.weight": "model-00015-of-00019.safetensors",
543
+ "transformer.decoder_layer.49.rms_norm_2.weight": "model-00015-of-00019.safetensors",
544
+ "transformer.decoder_layer.49.rms_norm_3.weight": "model-00015-of-00019.safetensors",
545
+ "transformer.decoder_layer.49.router.weight": "model-00015-of-00019.safetensors",
546
+ "transformer.decoder_layer.5.moe.0.linear.weight": "model-00002-of-00019.safetensors",
547
+ "transformer.decoder_layer.5.moe.0.linear_1.weight": "model-00002-of-00019.safetensors",
548
+ "transformer.decoder_layer.5.moe.0.linear_v.weight": "model-00002-of-00019.safetensors",
549
+ "transformer.decoder_layer.5.multi_head_attention.key.weight": "model-00002-of-00019.safetensors",
550
+ "transformer.decoder_layer.5.multi_head_attention.linear.weight": "model-00002-of-00019.safetensors",
551
+ "transformer.decoder_layer.5.multi_head_attention.query.weight": "model-00002-of-00019.safetensors",
552
+ "transformer.decoder_layer.5.multi_head_attention.value.weight": "model-00002-of-00019.safetensors",
553
+ "transformer.decoder_layer.5.rms_norm.weight": "model-00002-of-00019.safetensors",
554
+ "transformer.decoder_layer.5.rms_norm_1.weight": "model-00002-of-00019.safetensors",
555
+ "transformer.decoder_layer.5.rms_norm_2.weight": "model-00002-of-00019.safetensors",
556
+ "transformer.decoder_layer.5.rms_norm_3.weight": "model-00002-of-00019.safetensors",
557
+ "transformer.decoder_layer.5.router.weight": "model-00002-of-00019.safetensors",
558
+ "transformer.decoder_layer.50.moe.0.linear.weight": "model-00015-of-00019.safetensors",
559
+ "transformer.decoder_layer.50.moe.0.linear_1.weight": "model-00015-of-00019.safetensors",
560
+ "transformer.decoder_layer.50.moe.0.linear_v.weight": "model-00015-of-00019.safetensors",
561
+ "transformer.decoder_layer.50.multi_head_attention.key.weight": "model-00015-of-00019.safetensors",
562
+ "transformer.decoder_layer.50.multi_head_attention.linear.weight": "model-00015-of-00019.safetensors",
563
+ "transformer.decoder_layer.50.multi_head_attention.query.weight": "model-00015-of-00019.safetensors",
564
+ "transformer.decoder_layer.50.multi_head_attention.value.weight": "model-00015-of-00019.safetensors",
565
+ "transformer.decoder_layer.50.rms_norm.weight": "model-00015-of-00019.safetensors",
566
+ "transformer.decoder_layer.50.rms_norm_1.weight": "model-00015-of-00019.safetensors",
567
+ "transformer.decoder_layer.50.rms_norm_2.weight": "model-00015-of-00019.safetensors",
568
+ "transformer.decoder_layer.50.rms_norm_3.weight": "model-00015-of-00019.safetensors",
569
+ "transformer.decoder_layer.50.router.weight": "model-00015-of-00019.safetensors",
570
+ "transformer.decoder_layer.51.moe.0.linear.weight": "model-00016-of-00019.safetensors",
571
+ "transformer.decoder_layer.51.moe.0.linear_1.weight": "model-00016-of-00019.safetensors",
572
+ "transformer.decoder_layer.51.moe.0.linear_v.weight": "model-00015-of-00019.safetensors",
573
+ "transformer.decoder_layer.51.multi_head_attention.key.weight": "model-00015-of-00019.safetensors",
574
+ "transformer.decoder_layer.51.multi_head_attention.linear.weight": "model-00015-of-00019.safetensors",
575
+ "transformer.decoder_layer.51.multi_head_attention.query.weight": "model-00015-of-00019.safetensors",
576
+ "transformer.decoder_layer.51.multi_head_attention.value.weight": "model-00015-of-00019.safetensors",
577
+ "transformer.decoder_layer.51.rms_norm.weight": "model-00016-of-00019.safetensors",
578
+ "transformer.decoder_layer.51.rms_norm_1.weight": "model-00016-of-00019.safetensors",
579
+ "transformer.decoder_layer.51.rms_norm_2.weight": "model-00016-of-00019.safetensors",
580
+ "transformer.decoder_layer.51.rms_norm_3.weight": "model-00016-of-00019.safetensors",
581
+ "transformer.decoder_layer.51.router.weight": "model-00015-of-00019.safetensors",
582
+ "transformer.decoder_layer.52.moe.0.linear.weight": "model-00016-of-00019.safetensors",
583
+ "transformer.decoder_layer.52.moe.0.linear_1.weight": "model-00016-of-00019.safetensors",
584
+ "transformer.decoder_layer.52.moe.0.linear_v.weight": "model-00016-of-00019.safetensors",
585
+ "transformer.decoder_layer.52.multi_head_attention.key.weight": "model-00016-of-00019.safetensors",
586
+ "transformer.decoder_layer.52.multi_head_attention.linear.weight": "model-00016-of-00019.safetensors",
587
+ "transformer.decoder_layer.52.multi_head_attention.query.weight": "model-00016-of-00019.safetensors",
588
+ "transformer.decoder_layer.52.multi_head_attention.value.weight": "model-00016-of-00019.safetensors",
589
+ "transformer.decoder_layer.52.rms_norm.weight": "model-00016-of-00019.safetensors",
590
+ "transformer.decoder_layer.52.rms_norm_1.weight": "model-00016-of-00019.safetensors",
591
+ "transformer.decoder_layer.52.rms_norm_2.weight": "model-00016-of-00019.safetensors",
592
+ "transformer.decoder_layer.52.rms_norm_3.weight": "model-00016-of-00019.safetensors",
593
+ "transformer.decoder_layer.52.router.weight": "model-00016-of-00019.safetensors",
594
+ "transformer.decoder_layer.53.moe.0.linear.weight": "model-00016-of-00019.safetensors",
595
+ "transformer.decoder_layer.53.moe.0.linear_1.weight": "model-00016-of-00019.safetensors",
596
+ "transformer.decoder_layer.53.moe.0.linear_v.weight": "model-00016-of-00019.safetensors",
597
+ "transformer.decoder_layer.53.multi_head_attention.key.weight": "model-00016-of-00019.safetensors",
598
+ "transformer.decoder_layer.53.multi_head_attention.linear.weight": "model-00016-of-00019.safetensors",
599
+ "transformer.decoder_layer.53.multi_head_attention.query.weight": "model-00016-of-00019.safetensors",
600
+ "transformer.decoder_layer.53.multi_head_attention.value.weight": "model-00016-of-00019.safetensors",
601
+ "transformer.decoder_layer.53.rms_norm.weight": "model-00016-of-00019.safetensors",
602
+ "transformer.decoder_layer.53.rms_norm_1.weight": "model-00016-of-00019.safetensors",
603
+ "transformer.decoder_layer.53.rms_norm_2.weight": "model-00016-of-00019.safetensors",
604
+ "transformer.decoder_layer.53.rms_norm_3.weight": "model-00016-of-00019.safetensors",
605
+ "transformer.decoder_layer.53.router.weight": "model-00016-of-00019.safetensors",
606
+ "transformer.decoder_layer.54.moe.0.linear.weight": "model-00016-of-00019.safetensors",
607
+ "transformer.decoder_layer.54.moe.0.linear_1.weight": "model-00016-of-00019.safetensors",
608
+ "transformer.decoder_layer.54.moe.0.linear_v.weight": "model-00016-of-00019.safetensors",
609
+ "transformer.decoder_layer.54.multi_head_attention.key.weight": "model-00016-of-00019.safetensors",
610
+ "transformer.decoder_layer.54.multi_head_attention.linear.weight": "model-00016-of-00019.safetensors",
611
+ "transformer.decoder_layer.54.multi_head_attention.query.weight": "model-00016-of-00019.safetensors",
612
+ "transformer.decoder_layer.54.multi_head_attention.value.weight": "model-00016-of-00019.safetensors",
613
+ "transformer.decoder_layer.54.rms_norm.weight": "model-00016-of-00019.safetensors",
614
+ "transformer.decoder_layer.54.rms_norm_1.weight": "model-00016-of-00019.safetensors",
615
+ "transformer.decoder_layer.54.rms_norm_2.weight": "model-00016-of-00019.safetensors",
616
+ "transformer.decoder_layer.54.rms_norm_3.weight": "model-00016-of-00019.safetensors",
617
+ "transformer.decoder_layer.54.router.weight": "model-00016-of-00019.safetensors",
618
+ "transformer.decoder_layer.55.moe.0.linear.weight": "model-00017-of-00019.safetensors",
619
+ "transformer.decoder_layer.55.moe.0.linear_1.weight": "model-00017-of-00019.safetensors",
620
+ "transformer.decoder_layer.55.moe.0.linear_v.weight": "model-00017-of-00019.safetensors",
621
+ "transformer.decoder_layer.55.multi_head_attention.key.weight": "model-00017-of-00019.safetensors",
622
+ "transformer.decoder_layer.55.multi_head_attention.linear.weight": "model-00017-of-00019.safetensors",
623
+ "transformer.decoder_layer.55.multi_head_attention.query.weight": "model-00017-of-00019.safetensors",
624
+ "transformer.decoder_layer.55.multi_head_attention.value.weight": "model-00017-of-00019.safetensors",
625
+ "transformer.decoder_layer.55.rms_norm.weight": "model-00017-of-00019.safetensors",
626
+ "transformer.decoder_layer.55.rms_norm_1.weight": "model-00017-of-00019.safetensors",
627
+ "transformer.decoder_layer.55.rms_norm_2.weight": "model-00017-of-00019.safetensors",
628
+ "transformer.decoder_layer.55.rms_norm_3.weight": "model-00017-of-00019.safetensors",
629
+ "transformer.decoder_layer.55.router.weight": "model-00017-of-00019.safetensors",
630
+ "transformer.decoder_layer.56.moe.0.linear.weight": "model-00017-of-00019.safetensors",
631
+ "transformer.decoder_layer.56.moe.0.linear_1.weight": "model-00017-of-00019.safetensors",
632
+ "transformer.decoder_layer.56.moe.0.linear_v.weight": "model-00017-of-00019.safetensors",
633
+ "transformer.decoder_layer.56.multi_head_attention.key.weight": "model-00017-of-00019.safetensors",
634
+ "transformer.decoder_layer.56.multi_head_attention.linear.weight": "model-00017-of-00019.safetensors",
635
+ "transformer.decoder_layer.56.multi_head_attention.query.weight": "model-00017-of-00019.safetensors",
636
+ "transformer.decoder_layer.56.multi_head_attention.value.weight": "model-00017-of-00019.safetensors",
637
+ "transformer.decoder_layer.56.rms_norm.weight": "model-00017-of-00019.safetensors",
638
+ "transformer.decoder_layer.56.rms_norm_1.weight": "model-00017-of-00019.safetensors",
639
+ "transformer.decoder_layer.56.rms_norm_2.weight": "model-00017-of-00019.safetensors",
640
+ "transformer.decoder_layer.56.rms_norm_3.weight": "model-00017-of-00019.safetensors",
641
+ "transformer.decoder_layer.56.router.weight": "model-00017-of-00019.safetensors",
642
+ "transformer.decoder_layer.57.moe.0.linear.weight": "model-00017-of-00019.safetensors",
643
+ "transformer.decoder_layer.57.moe.0.linear_1.weight": "model-00017-of-00019.safetensors",
644
+ "transformer.decoder_layer.57.moe.0.linear_v.weight": "model-00017-of-00019.safetensors",
645
+ "transformer.decoder_layer.57.multi_head_attention.key.weight": "model-00017-of-00019.safetensors",
646
+ "transformer.decoder_layer.57.multi_head_attention.linear.weight": "model-00017-of-00019.safetensors",
647
+ "transformer.decoder_layer.57.multi_head_attention.query.weight": "model-00017-of-00019.safetensors",
648
+ "transformer.decoder_layer.57.multi_head_attention.value.weight": "model-00017-of-00019.safetensors",
649
+ "transformer.decoder_layer.57.rms_norm.weight": "model-00017-of-00019.safetensors",
650
+ "transformer.decoder_layer.57.rms_norm_1.weight": "model-00017-of-00019.safetensors",
651
+ "transformer.decoder_layer.57.rms_norm_2.weight": "model-00017-of-00019.safetensors",
652
+ "transformer.decoder_layer.57.rms_norm_3.weight": "model-00017-of-00019.safetensors",
653
+ "transformer.decoder_layer.57.router.weight": "model-00017-of-00019.safetensors",
654
+ "transformer.decoder_layer.58.moe.0.linear.weight": "model-00018-of-00019.safetensors",
655
+ "transformer.decoder_layer.58.moe.0.linear_1.weight": "model-00018-of-00019.safetensors",
656
+ "transformer.decoder_layer.58.moe.0.linear_v.weight": "model-00017-of-00019.safetensors",
657
+ "transformer.decoder_layer.58.multi_head_attention.key.weight": "model-00017-of-00019.safetensors",
658
+ "transformer.decoder_layer.58.multi_head_attention.linear.weight": "model-00017-of-00019.safetensors",
659
+ "transformer.decoder_layer.58.multi_head_attention.query.weight": "model-00017-of-00019.safetensors",
660
+ "transformer.decoder_layer.58.multi_head_attention.value.weight": "model-00017-of-00019.safetensors",
661
+ "transformer.decoder_layer.58.rms_norm.weight": "model-00018-of-00019.safetensors",
662
+ "transformer.decoder_layer.58.rms_norm_1.weight": "model-00018-of-00019.safetensors",
663
+ "transformer.decoder_layer.58.rms_norm_2.weight": "model-00018-of-00019.safetensors",
664
+ "transformer.decoder_layer.58.rms_norm_3.weight": "model-00018-of-00019.safetensors",
665
+ "transformer.decoder_layer.58.router.weight": "model-00017-of-00019.safetensors",
666
+ "transformer.decoder_layer.59.moe.0.linear.weight": "model-00018-of-00019.safetensors",
667
+ "transformer.decoder_layer.59.moe.0.linear_1.weight": "model-00018-of-00019.safetensors",
668
+ "transformer.decoder_layer.59.moe.0.linear_v.weight": "model-00018-of-00019.safetensors",
669
+ "transformer.decoder_layer.59.multi_head_attention.key.weight": "model-00018-of-00019.safetensors",
670
+ "transformer.decoder_layer.59.multi_head_attention.linear.weight": "model-00018-of-00019.safetensors",
671
+ "transformer.decoder_layer.59.multi_head_attention.query.weight": "model-00018-of-00019.safetensors",
672
+ "transformer.decoder_layer.59.multi_head_attention.value.weight": "model-00018-of-00019.safetensors",
673
+ "transformer.decoder_layer.59.rms_norm.weight": "model-00018-of-00019.safetensors",
674
+ "transformer.decoder_layer.59.rms_norm_1.weight": "model-00018-of-00019.safetensors",
675
+ "transformer.decoder_layer.59.rms_norm_2.weight": "model-00018-of-00019.safetensors",
676
+ "transformer.decoder_layer.59.rms_norm_3.weight": "model-00018-of-00019.safetensors",
677
+ "transformer.decoder_layer.59.router.weight": "model-00018-of-00019.safetensors",
678
+ "transformer.decoder_layer.6.moe.0.linear.weight": "model-00003-of-00019.safetensors",
679
+ "transformer.decoder_layer.6.moe.0.linear_1.weight": "model-00003-of-00019.safetensors",
680
+ "transformer.decoder_layer.6.moe.0.linear_v.weight": "model-00003-of-00019.safetensors",
681
+ "transformer.decoder_layer.6.multi_head_attention.key.weight": "model-00003-of-00019.safetensors",
682
+ "transformer.decoder_layer.6.multi_head_attention.linear.weight": "model-00003-of-00019.safetensors",
683
+ "transformer.decoder_layer.6.multi_head_attention.query.weight": "model-00003-of-00019.safetensors",
684
+ "transformer.decoder_layer.6.multi_head_attention.value.weight": "model-00003-of-00019.safetensors",
685
+ "transformer.decoder_layer.6.rms_norm.weight": "model-00003-of-00019.safetensors",
686
+ "transformer.decoder_layer.6.rms_norm_1.weight": "model-00003-of-00019.safetensors",
687
+ "transformer.decoder_layer.6.rms_norm_2.weight": "model-00003-of-00019.safetensors",
688
+ "transformer.decoder_layer.6.rms_norm_3.weight": "model-00003-of-00019.safetensors",
689
+ "transformer.decoder_layer.6.router.weight": "model-00003-of-00019.safetensors",
690
+ "transformer.decoder_layer.60.moe.0.linear.weight": "model-00018-of-00019.safetensors",
691
+ "transformer.decoder_layer.60.moe.0.linear_1.weight": "model-00018-of-00019.safetensors",
692
+ "transformer.decoder_layer.60.moe.0.linear_v.weight": "model-00018-of-00019.safetensors",
693
+ "transformer.decoder_layer.60.multi_head_attention.key.weight": "model-00018-of-00019.safetensors",
694
+ "transformer.decoder_layer.60.multi_head_attention.linear.weight": "model-00018-of-00019.safetensors",
695
+ "transformer.decoder_layer.60.multi_head_attention.query.weight": "model-00018-of-00019.safetensors",
696
+ "transformer.decoder_layer.60.multi_head_attention.value.weight": "model-00018-of-00019.safetensors",
697
+ "transformer.decoder_layer.60.rms_norm.weight": "model-00018-of-00019.safetensors",
698
+ "transformer.decoder_layer.60.rms_norm_1.weight": "model-00018-of-00019.safetensors",
699
+ "transformer.decoder_layer.60.rms_norm_2.weight": "model-00018-of-00019.safetensors",
700
+ "transformer.decoder_layer.60.rms_norm_3.weight": "model-00018-of-00019.safetensors",
701
+ "transformer.decoder_layer.60.router.weight": "model-00018-of-00019.safetensors",
702
+ "transformer.decoder_layer.61.moe.0.linear.weight": "model-00018-of-00019.safetensors",
703
+ "transformer.decoder_layer.61.moe.0.linear_1.weight": "model-00018-of-00019.safetensors",
704
+ "transformer.decoder_layer.61.moe.0.linear_v.weight": "model-00018-of-00019.safetensors",
705
+ "transformer.decoder_layer.61.multi_head_attention.key.weight": "model-00018-of-00019.safetensors",
706
+ "transformer.decoder_layer.61.multi_head_attention.linear.weight": "model-00018-of-00019.safetensors",
707
+ "transformer.decoder_layer.61.multi_head_attention.query.weight": "model-00018-of-00019.safetensors",
708
+ "transformer.decoder_layer.61.multi_head_attention.value.weight": "model-00018-of-00019.safetensors",
709
+ "transformer.decoder_layer.61.rms_norm.weight": "model-00018-of-00019.safetensors",
710
+ "transformer.decoder_layer.61.rms_norm_1.weight": "model-00018-of-00019.safetensors",
711
+ "transformer.decoder_layer.61.rms_norm_2.weight": "model-00018-of-00019.safetensors",
712
+ "transformer.decoder_layer.61.rms_norm_3.weight": "model-00018-of-00019.safetensors",
713
+ "transformer.decoder_layer.61.router.weight": "model-00018-of-00019.safetensors",
714
+ "transformer.decoder_layer.62.moe.0.linear.weight": "model-00019-of-00019.safetensors",
715
+ "transformer.decoder_layer.62.moe.0.linear_1.weight": "model-00019-of-00019.safetensors",
716
+ "transformer.decoder_layer.62.moe.0.linear_v.weight": "model-00019-of-00019.safetensors",
717
+ "transformer.decoder_layer.62.multi_head_attention.key.weight": "model-00019-of-00019.safetensors",
718
+ "transformer.decoder_layer.62.multi_head_attention.linear.weight": "model-00019-of-00019.safetensors",
719
+ "transformer.decoder_layer.62.multi_head_attention.query.weight": "model-00019-of-00019.safetensors",
720
+ "transformer.decoder_layer.62.multi_head_attention.value.weight": "model-00019-of-00019.safetensors",
721
+ "transformer.decoder_layer.62.rms_norm.weight": "model-00019-of-00019.safetensors",
722
+ "transformer.decoder_layer.62.rms_norm_1.weight": "model-00019-of-00019.safetensors",
723
+ "transformer.decoder_layer.62.rms_norm_2.weight": "model-00019-of-00019.safetensors",
724
+ "transformer.decoder_layer.62.rms_norm_3.weight": "model-00019-of-00019.safetensors",
725
+ "transformer.decoder_layer.62.router.weight": "model-00019-of-00019.safetensors",
726
+ "transformer.decoder_layer.63.moe.0.linear.weight": "model-00019-of-00019.safetensors",
727
+ "transformer.decoder_layer.63.moe.0.linear_1.weight": "model-00019-of-00019.safetensors",
728
+ "transformer.decoder_layer.63.moe.0.linear_v.weight": "model-00019-of-00019.safetensors",
729
+ "transformer.decoder_layer.63.multi_head_attention.key.weight": "model-00019-of-00019.safetensors",
730
+ "transformer.decoder_layer.63.multi_head_attention.linear.weight": "model-00019-of-00019.safetensors",
731
+ "transformer.decoder_layer.63.multi_head_attention.query.weight": "model-00019-of-00019.safetensors",
732
+ "transformer.decoder_layer.63.multi_head_attention.value.weight": "model-00019-of-00019.safetensors",
733
+ "transformer.decoder_layer.63.rms_norm.weight": "model-00019-of-00019.safetensors",
734
+ "transformer.decoder_layer.63.rms_norm_1.weight": "model-00019-of-00019.safetensors",
735
+ "transformer.decoder_layer.63.rms_norm_2.weight": "model-00019-of-00019.safetensors",
736
+ "transformer.decoder_layer.63.rms_norm_3.weight": "model-00019-of-00019.safetensors",
737
+ "transformer.decoder_layer.63.router.weight": "model-00019-of-00019.safetensors",
738
+ "transformer.decoder_layer.7.moe.0.linear.weight": "model-00003-of-00019.safetensors",
739
+ "transformer.decoder_layer.7.moe.0.linear_1.weight": "model-00003-of-00019.safetensors",
740
+ "transformer.decoder_layer.7.moe.0.linear_v.weight": "model-00003-of-00019.safetensors",
741
+ "transformer.decoder_layer.7.multi_head_attention.key.weight": "model-00003-of-00019.safetensors",
742
+ "transformer.decoder_layer.7.multi_head_attention.linear.weight": "model-00003-of-00019.safetensors",
743
+ "transformer.decoder_layer.7.multi_head_attention.query.weight": "model-00003-of-00019.safetensors",
744
+ "transformer.decoder_layer.7.multi_head_attention.value.weight": "model-00003-of-00019.safetensors",
745
+ "transformer.decoder_layer.7.rms_norm.weight": "model-00003-of-00019.safetensors",
746
+ "transformer.decoder_layer.7.rms_norm_1.weight": "model-00003-of-00019.safetensors",
747
+ "transformer.decoder_layer.7.rms_norm_2.weight": "model-00003-of-00019.safetensors",
748
+ "transformer.decoder_layer.7.rms_norm_3.weight": "model-00003-of-00019.safetensors",
749
+ "transformer.decoder_layer.7.router.weight": "model-00003-of-00019.safetensors",
750
+ "transformer.decoder_layer.8.moe.0.linear.weight": "model-00003-of-00019.safetensors",
751
+ "transformer.decoder_layer.8.moe.0.linear_1.weight": "model-00003-of-00019.safetensors",
752
+ "transformer.decoder_layer.8.moe.0.linear_v.weight": "model-00003-of-00019.safetensors",
753
+ "transformer.decoder_layer.8.multi_head_attention.key.weight": "model-00003-of-00019.safetensors",
754
+ "transformer.decoder_layer.8.multi_head_attention.linear.weight": "model-00003-of-00019.safetensors",
755
+ "transformer.decoder_layer.8.multi_head_attention.query.weight": "model-00003-of-00019.safetensors",
756
+ "transformer.decoder_layer.8.multi_head_attention.value.weight": "model-00003-of-00019.safetensors",
757
+ "transformer.decoder_layer.8.rms_norm.weight": "model-00003-of-00019.safetensors",
758
+ "transformer.decoder_layer.8.rms_norm_1.weight": "model-00003-of-00019.safetensors",
759
+ "transformer.decoder_layer.8.rms_norm_2.weight": "model-00003-of-00019.safetensors",
760
+ "transformer.decoder_layer.8.rms_norm_3.weight": "model-00003-of-00019.safetensors",
761
+ "transformer.decoder_layer.8.router.weight": "model-00003-of-00019.safetensors",
762
+ "transformer.decoder_layer.9.moe.0.linear.weight": "model-00004-of-00019.safetensors",
763
+ "transformer.decoder_layer.9.moe.0.linear_1.weight": "model-00004-of-00019.safetensors",
764
+ "transformer.decoder_layer.9.moe.0.linear_v.weight": "model-00003-of-00019.safetensors",
765
+ "transformer.decoder_layer.9.multi_head_attention.key.weight": "model-00003-of-00019.safetensors",
766
+ "transformer.decoder_layer.9.multi_head_attention.linear.weight": "model-00003-of-00019.safetensors",
767
+ "transformer.decoder_layer.9.multi_head_attention.query.weight": "model-00003-of-00019.safetensors",
768
+ "transformer.decoder_layer.9.multi_head_attention.value.weight": "model-00003-of-00019.safetensors",
769
+ "transformer.decoder_layer.9.rms_norm.weight": "model-00004-of-00019.safetensors",
770
+ "transformer.decoder_layer.9.rms_norm_1.weight": "model-00004-of-00019.safetensors",
771
+ "transformer.decoder_layer.9.rms_norm_2.weight": "model-00004-of-00019.safetensors",
772
+ "transformer.decoder_layer.9.rms_norm_3.weight": "model-00004-of-00019.safetensors",
773
+ "transformer.decoder_layer.9.router.weight": "model-00003-of-00019.safetensors",
774
+ "transformer.in_out_embed.weight": "model-00001-of-00019.safetensors",
775
+ "transformer.rms_norm.weight": "model-00019-of-00019.safetensors"
776
+ }
777
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,6 +1,7 @@
1
  {
2
  "add_bos_token": false,
3
  "add_eos_token": false,
 
4
  "added_tokens_decoder": {
5
  "0": {
6
  "content": "<unk>",
 
1
  {
2
  "add_bos_token": false,
3
  "add_eos_token": false,
4
+ "add_prefix_space": true,
5
  "added_tokens_decoder": {
6
  "0": {
7
  "content": "<unk>",