Adding `safetensors` variant of this model

#1
by SFconvertbot - opened
.gitattributes CHANGED
@@ -29,3 +29,18 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zst filter=lfs diff=lfs merge=lfs -text
31
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  *.zip filter=lfs diff=lfs merge=lfs -text
30
  *.zst filter=lfs diff=lfs merge=lfs -text
31
  *tfevents* filter=lfs diff=lfs merge=lfs -text
32
+ model-00010-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
33
+ model-00005-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
34
+ model-00012-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
35
+ model-00013-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
36
+ model-00007-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
37
+ model-00008-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
38
+ model-00002-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
39
+ model-00014-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
40
+ model-00015-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
41
+ model-00006-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
42
+ model-00003-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
43
+ model-00004-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
44
+ model-00001-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
45
+ model-00009-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
46
+ model-00011-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
model-00001-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d932d8c5d7e970ad2585267925a1e559d7156c623b765c15cbc971471ffd0d8
3
+ size 964765264
model-00002-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d36831fd45099af299d83255f07541e54c9c9ad676ea587433fe66677a0812dd
3
+ size 948062304
model-00003-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76c6e9f4e3e6c50da2a48057d7ea554ed294078d6da034723211d0ff5b9df6bf
3
+ size 952248720
model-00004-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b04d7d9a9c88338a6bf5e4148a79920ae16dc2a64e5c9d07e1105adca87008cf
3
+ size 948029560
model-00005-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:661a389a27d081d56114c109583d6b28828be529800618b24e7954dca7da4787
3
+ size 948062320
model-00006-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5f84b445903962b51025e92d533de308a738ab30fe8fd411b3c21a04cebe065
3
+ size 952248744
model-00007-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f91881fa69d4d93ffa7b9c186b9894672c1d2c01bf0df996ab5aff36a20c093
3
+ size 948029576
model-00008-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af3c2974c48255d0d7ddb0a35ce4d5129d84edb4b2796ff97c164a3a03e04adc
3
+ size 948062328
model-00009-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dddf16412bbdbb6e4ed1915b794c1f0a042455295a77c9f13e6a1636ae934bd0
3
+ size 952248744
model-00010-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e50622935197311d212cd450bac1f27fa4e96df0311ba23780dc128d38978389
3
+ size 948029576
model-00011-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbef6072e902ba7fc0833481847634152121748cb645ae22b0e852be6f4cc6a1
3
+ size 948062328
model-00012-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3939e79b3f497b9de92f39296f80328225e8312d47d7e598ca804517ae3a4dc9
3
+ size 952248744
model-00013-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d3e8d76257c756334704252ecc7d7d45e89fe7cb4fc16833601d7ce632b2659
3
+ size 948029576
model-00014-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dbae3f60980092e71d65fcf4b99d35021c86e44f10097c31b08d5763c566a7c
3
+ size 948062328
model-00015-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:336fe9e8ec7281ace03d991eabf92ba98f384c80d1121b870939770cbd9d4b3c
3
+ size 960681504
model.safetensors.index.json ADDED
@@ -0,0 +1,309 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14266839040
4
+ },
5
+ "weight_map": {
6
+ "lm_head.bias": "model-00015-of-00015.safetensors",
7
+ "lm_head.weight": "model-00015-of-00015.safetensors",
8
+ "transformer.h.0.attn.causal_mask": "model-00001-of-00015.safetensors",
9
+ "transformer.h.0.attn.out_proj.weight": "model-00001-of-00015.safetensors",
10
+ "transformer.h.0.attn.qkv_proj.weight": "model-00001-of-00015.safetensors",
11
+ "transformer.h.0.ln_1.bias": "model-00001-of-00015.safetensors",
12
+ "transformer.h.0.ln_1.weight": "model-00001-of-00015.safetensors",
13
+ "transformer.h.0.mlp.fc_in.bias": "model-00001-of-00015.safetensors",
14
+ "transformer.h.0.mlp.fc_in.weight": "model-00001-of-00015.safetensors",
15
+ "transformer.h.0.mlp.fc_out.bias": "model-00001-of-00015.safetensors",
16
+ "transformer.h.0.mlp.fc_out.weight": "model-00001-of-00015.safetensors",
17
+ "transformer.h.1.attn.causal_mask": "model-00001-of-00015.safetensors",
18
+ "transformer.h.1.attn.out_proj.weight": "model-00001-of-00015.safetensors",
19
+ "transformer.h.1.attn.qkv_proj.weight": "model-00001-of-00015.safetensors",
20
+ "transformer.h.1.ln_1.bias": "model-00001-of-00015.safetensors",
21
+ "transformer.h.1.ln_1.weight": "model-00001-of-00015.safetensors",
22
+ "transformer.h.1.mlp.fc_in.bias": "model-00002-of-00015.safetensors",
23
+ "transformer.h.1.mlp.fc_in.weight": "model-00002-of-00015.safetensors",
24
+ "transformer.h.1.mlp.fc_out.bias": "model-00002-of-00015.safetensors",
25
+ "transformer.h.1.mlp.fc_out.weight": "model-00002-of-00015.safetensors",
26
+ "transformer.h.10.attn.causal_mask": "model-00005-of-00015.safetensors",
27
+ "transformer.h.10.attn.out_proj.weight": "model-00005-of-00015.safetensors",
28
+ "transformer.h.10.attn.qkv_proj.weight": "model-00005-of-00015.safetensors",
29
+ "transformer.h.10.ln_1.bias": "model-00005-of-00015.safetensors",
30
+ "transformer.h.10.ln_1.weight": "model-00005-of-00015.safetensors",
31
+ "transformer.h.10.mlp.fc_in.bias": "model-00005-of-00015.safetensors",
32
+ "transformer.h.10.mlp.fc_in.weight": "model-00005-of-00015.safetensors",
33
+ "transformer.h.10.mlp.fc_out.bias": "model-00006-of-00015.safetensors",
34
+ "transformer.h.10.mlp.fc_out.weight": "model-00006-of-00015.safetensors",
35
+ "transformer.h.11.attn.causal_mask": "model-00006-of-00015.safetensors",
36
+ "transformer.h.11.attn.out_proj.weight": "model-00006-of-00015.safetensors",
37
+ "transformer.h.11.attn.qkv_proj.weight": "model-00006-of-00015.safetensors",
38
+ "transformer.h.11.ln_1.bias": "model-00006-of-00015.safetensors",
39
+ "transformer.h.11.ln_1.weight": "model-00006-of-00015.safetensors",
40
+ "transformer.h.11.mlp.fc_in.bias": "model-00006-of-00015.safetensors",
41
+ "transformer.h.11.mlp.fc_in.weight": "model-00006-of-00015.safetensors",
42
+ "transformer.h.11.mlp.fc_out.bias": "model-00006-of-00015.safetensors",
43
+ "transformer.h.11.mlp.fc_out.weight": "model-00006-of-00015.safetensors",
44
+ "transformer.h.12.attn.causal_mask": "model-00006-of-00015.safetensors",
45
+ "transformer.h.12.attn.out_proj.weight": "model-00006-of-00015.safetensors",
46
+ "transformer.h.12.attn.qkv_proj.weight": "model-00006-of-00015.safetensors",
47
+ "transformer.h.12.ln_1.bias": "model-00006-of-00015.safetensors",
48
+ "transformer.h.12.ln_1.weight": "model-00006-of-00015.safetensors",
49
+ "transformer.h.12.mlp.fc_in.bias": "model-00006-of-00015.safetensors",
50
+ "transformer.h.12.mlp.fc_in.weight": "model-00006-of-00015.safetensors",
51
+ "transformer.h.12.mlp.fc_out.bias": "model-00006-of-00015.safetensors",
52
+ "transformer.h.12.mlp.fc_out.weight": "model-00006-of-00015.safetensors",
53
+ "transformer.h.13.attn.causal_mask": "model-00006-of-00015.safetensors",
54
+ "transformer.h.13.attn.out_proj.weight": "model-00007-of-00015.safetensors",
55
+ "transformer.h.13.attn.qkv_proj.weight": "model-00007-of-00015.safetensors",
56
+ "transformer.h.13.ln_1.bias": "model-00006-of-00015.safetensors",
57
+ "transformer.h.13.ln_1.weight": "model-00006-of-00015.safetensors",
58
+ "transformer.h.13.mlp.fc_in.bias": "model-00007-of-00015.safetensors",
59
+ "transformer.h.13.mlp.fc_in.weight": "model-00007-of-00015.safetensors",
60
+ "transformer.h.13.mlp.fc_out.bias": "model-00007-of-00015.safetensors",
61
+ "transformer.h.13.mlp.fc_out.weight": "model-00007-of-00015.safetensors",
62
+ "transformer.h.14.attn.causal_mask": "model-00007-of-00015.safetensors",
63
+ "transformer.h.14.attn.out_proj.weight": "model-00007-of-00015.safetensors",
64
+ "transformer.h.14.attn.qkv_proj.weight": "model-00007-of-00015.safetensors",
65
+ "transformer.h.14.ln_1.bias": "model-00007-of-00015.safetensors",
66
+ "transformer.h.14.ln_1.weight": "model-00007-of-00015.safetensors",
67
+ "transformer.h.14.mlp.fc_in.bias": "model-00007-of-00015.safetensors",
68
+ "transformer.h.14.mlp.fc_in.weight": "model-00007-of-00015.safetensors",
69
+ "transformer.h.14.mlp.fc_out.bias": "model-00007-of-00015.safetensors",
70
+ "transformer.h.14.mlp.fc_out.weight": "model-00007-of-00015.safetensors",
71
+ "transformer.h.15.attn.causal_mask": "model-00007-of-00015.safetensors",
72
+ "transformer.h.15.attn.out_proj.weight": "model-00007-of-00015.safetensors",
73
+ "transformer.h.15.attn.qkv_proj.weight": "model-00007-of-00015.safetensors",
74
+ "transformer.h.15.ln_1.bias": "model-00007-of-00015.safetensors",
75
+ "transformer.h.15.ln_1.weight": "model-00007-of-00015.safetensors",
76
+ "transformer.h.15.mlp.fc_in.bias": "model-00008-of-00015.safetensors",
77
+ "transformer.h.15.mlp.fc_in.weight": "model-00008-of-00015.safetensors",
78
+ "transformer.h.15.mlp.fc_out.bias": "model-00008-of-00015.safetensors",
79
+ "transformer.h.15.mlp.fc_out.weight": "model-00008-of-00015.safetensors",
80
+ "transformer.h.16.attn.causal_mask": "model-00008-of-00015.safetensors",
81
+ "transformer.h.16.attn.out_proj.weight": "model-00008-of-00015.safetensors",
82
+ "transformer.h.16.attn.qkv_proj.weight": "model-00008-of-00015.safetensors",
83
+ "transformer.h.16.ln_1.bias": "model-00008-of-00015.safetensors",
84
+ "transformer.h.16.ln_1.weight": "model-00008-of-00015.safetensors",
85
+ "transformer.h.16.mlp.fc_in.bias": "model-00008-of-00015.safetensors",
86
+ "transformer.h.16.mlp.fc_in.weight": "model-00008-of-00015.safetensors",
87
+ "transformer.h.16.mlp.fc_out.bias": "model-00008-of-00015.safetensors",
88
+ "transformer.h.16.mlp.fc_out.weight": "model-00008-of-00015.safetensors",
89
+ "transformer.h.17.attn.causal_mask": "model-00008-of-00015.safetensors",
90
+ "transformer.h.17.attn.out_proj.weight": "model-00008-of-00015.safetensors",
91
+ "transformer.h.17.attn.qkv_proj.weight": "model-00008-of-00015.safetensors",
92
+ "transformer.h.17.ln_1.bias": "model-00008-of-00015.safetensors",
93
+ "transformer.h.17.ln_1.weight": "model-00008-of-00015.safetensors",
94
+ "transformer.h.17.mlp.fc_in.bias": "model-00008-of-00015.safetensors",
95
+ "transformer.h.17.mlp.fc_in.weight": "model-00008-of-00015.safetensors",
96
+ "transformer.h.17.mlp.fc_out.bias": "model-00009-of-00015.safetensors",
97
+ "transformer.h.17.mlp.fc_out.weight": "model-00009-of-00015.safetensors",
98
+ "transformer.h.18.attn.causal_mask": "model-00009-of-00015.safetensors",
99
+ "transformer.h.18.attn.out_proj.weight": "model-00009-of-00015.safetensors",
100
+ "transformer.h.18.attn.qkv_proj.weight": "model-00009-of-00015.safetensors",
101
+ "transformer.h.18.ln_1.bias": "model-00009-of-00015.safetensors",
102
+ "transformer.h.18.ln_1.weight": "model-00009-of-00015.safetensors",
103
+ "transformer.h.18.mlp.fc_in.bias": "model-00009-of-00015.safetensors",
104
+ "transformer.h.18.mlp.fc_in.weight": "model-00009-of-00015.safetensors",
105
+ "transformer.h.18.mlp.fc_out.bias": "model-00009-of-00015.safetensors",
106
+ "transformer.h.18.mlp.fc_out.weight": "model-00009-of-00015.safetensors",
107
+ "transformer.h.19.attn.causal_mask": "model-00009-of-00015.safetensors",
108
+ "transformer.h.19.attn.out_proj.weight": "model-00009-of-00015.safetensors",
109
+ "transformer.h.19.attn.qkv_proj.weight": "model-00009-of-00015.safetensors",
110
+ "transformer.h.19.ln_1.bias": "model-00009-of-00015.safetensors",
111
+ "transformer.h.19.ln_1.weight": "model-00009-of-00015.safetensors",
112
+ "transformer.h.19.mlp.fc_in.bias": "model-00009-of-00015.safetensors",
113
+ "transformer.h.19.mlp.fc_in.weight": "model-00009-of-00015.safetensors",
114
+ "transformer.h.19.mlp.fc_out.bias": "model-00009-of-00015.safetensors",
115
+ "transformer.h.19.mlp.fc_out.weight": "model-00009-of-00015.safetensors",
116
+ "transformer.h.2.attn.causal_mask": "model-00002-of-00015.safetensors",
117
+ "transformer.h.2.attn.out_proj.weight": "model-00002-of-00015.safetensors",
118
+ "transformer.h.2.attn.qkv_proj.weight": "model-00002-of-00015.safetensors",
119
+ "transformer.h.2.ln_1.bias": "model-00002-of-00015.safetensors",
120
+ "transformer.h.2.ln_1.weight": "model-00002-of-00015.safetensors",
121
+ "transformer.h.2.mlp.fc_in.bias": "model-00002-of-00015.safetensors",
122
+ "transformer.h.2.mlp.fc_in.weight": "model-00002-of-00015.safetensors",
123
+ "transformer.h.2.mlp.fc_out.bias": "model-00002-of-00015.safetensors",
124
+ "transformer.h.2.mlp.fc_out.weight": "model-00002-of-00015.safetensors",
125
+ "transformer.h.20.attn.causal_mask": "model-00009-of-00015.safetensors",
126
+ "transformer.h.20.attn.out_proj.weight": "model-00010-of-00015.safetensors",
127
+ "transformer.h.20.attn.qkv_proj.weight": "model-00010-of-00015.safetensors",
128
+ "transformer.h.20.ln_1.bias": "model-00009-of-00015.safetensors",
129
+ "transformer.h.20.ln_1.weight": "model-00009-of-00015.safetensors",
130
+ "transformer.h.20.mlp.fc_in.bias": "model-00010-of-00015.safetensors",
131
+ "transformer.h.20.mlp.fc_in.weight": "model-00010-of-00015.safetensors",
132
+ "transformer.h.20.mlp.fc_out.bias": "model-00010-of-00015.safetensors",
133
+ "transformer.h.20.mlp.fc_out.weight": "model-00010-of-00015.safetensors",
134
+ "transformer.h.21.attn.causal_mask": "model-00010-of-00015.safetensors",
135
+ "transformer.h.21.attn.out_proj.weight": "model-00010-of-00015.safetensors",
136
+ "transformer.h.21.attn.qkv_proj.weight": "model-00010-of-00015.safetensors",
137
+ "transformer.h.21.ln_1.bias": "model-00010-of-00015.safetensors",
138
+ "transformer.h.21.ln_1.weight": "model-00010-of-00015.safetensors",
139
+ "transformer.h.21.mlp.fc_in.bias": "model-00010-of-00015.safetensors",
140
+ "transformer.h.21.mlp.fc_in.weight": "model-00010-of-00015.safetensors",
141
+ "transformer.h.21.mlp.fc_out.bias": "model-00010-of-00015.safetensors",
142
+ "transformer.h.21.mlp.fc_out.weight": "model-00010-of-00015.safetensors",
143
+ "transformer.h.22.attn.causal_mask": "model-00010-of-00015.safetensors",
144
+ "transformer.h.22.attn.out_proj.weight": "model-00010-of-00015.safetensors",
145
+ "transformer.h.22.attn.qkv_proj.weight": "model-00010-of-00015.safetensors",
146
+ "transformer.h.22.ln_1.bias": "model-00010-of-00015.safetensors",
147
+ "transformer.h.22.ln_1.weight": "model-00010-of-00015.safetensors",
148
+ "transformer.h.22.mlp.fc_in.bias": "model-00011-of-00015.safetensors",
149
+ "transformer.h.22.mlp.fc_in.weight": "model-00011-of-00015.safetensors",
150
+ "transformer.h.22.mlp.fc_out.bias": "model-00011-of-00015.safetensors",
151
+ "transformer.h.22.mlp.fc_out.weight": "model-00011-of-00015.safetensors",
152
+ "transformer.h.23.attn.causal_mask": "model-00011-of-00015.safetensors",
153
+ "transformer.h.23.attn.out_proj.weight": "model-00011-of-00015.safetensors",
154
+ "transformer.h.23.attn.qkv_proj.weight": "model-00011-of-00015.safetensors",
155
+ "transformer.h.23.ln_1.bias": "model-00011-of-00015.safetensors",
156
+ "transformer.h.23.ln_1.weight": "model-00011-of-00015.safetensors",
157
+ "transformer.h.23.mlp.fc_in.bias": "model-00011-of-00015.safetensors",
158
+ "transformer.h.23.mlp.fc_in.weight": "model-00011-of-00015.safetensors",
159
+ "transformer.h.23.mlp.fc_out.bias": "model-00011-of-00015.safetensors",
160
+ "transformer.h.23.mlp.fc_out.weight": "model-00011-of-00015.safetensors",
161
+ "transformer.h.24.attn.causal_mask": "model-00011-of-00015.safetensors",
162
+ "transformer.h.24.attn.out_proj.weight": "model-00011-of-00015.safetensors",
163
+ "transformer.h.24.attn.qkv_proj.weight": "model-00011-of-00015.safetensors",
164
+ "transformer.h.24.ln_1.bias": "model-00011-of-00015.safetensors",
165
+ "transformer.h.24.ln_1.weight": "model-00011-of-00015.safetensors",
166
+ "transformer.h.24.mlp.fc_in.bias": "model-00011-of-00015.safetensors",
167
+ "transformer.h.24.mlp.fc_in.weight": "model-00011-of-00015.safetensors",
168
+ "transformer.h.24.mlp.fc_out.bias": "model-00012-of-00015.safetensors",
169
+ "transformer.h.24.mlp.fc_out.weight": "model-00012-of-00015.safetensors",
170
+ "transformer.h.25.attn.causal_mask": "model-00012-of-00015.safetensors",
171
+ "transformer.h.25.attn.out_proj.weight": "model-00012-of-00015.safetensors",
172
+ "transformer.h.25.attn.qkv_proj.weight": "model-00012-of-00015.safetensors",
173
+ "transformer.h.25.ln_1.bias": "model-00012-of-00015.safetensors",
174
+ "transformer.h.25.ln_1.weight": "model-00012-of-00015.safetensors",
175
+ "transformer.h.25.mlp.fc_in.bias": "model-00012-of-00015.safetensors",
176
+ "transformer.h.25.mlp.fc_in.weight": "model-00012-of-00015.safetensors",
177
+ "transformer.h.25.mlp.fc_out.bias": "model-00012-of-00015.safetensors",
178
+ "transformer.h.25.mlp.fc_out.weight": "model-00012-of-00015.safetensors",
179
+ "transformer.h.26.attn.causal_mask": "model-00012-of-00015.safetensors",
180
+ "transformer.h.26.attn.out_proj.weight": "model-00012-of-00015.safetensors",
181
+ "transformer.h.26.attn.qkv_proj.weight": "model-00012-of-00015.safetensors",
182
+ "transformer.h.26.ln_1.bias": "model-00012-of-00015.safetensors",
183
+ "transformer.h.26.ln_1.weight": "model-00012-of-00015.safetensors",
184
+ "transformer.h.26.mlp.fc_in.bias": "model-00012-of-00015.safetensors",
185
+ "transformer.h.26.mlp.fc_in.weight": "model-00012-of-00015.safetensors",
186
+ "transformer.h.26.mlp.fc_out.bias": "model-00012-of-00015.safetensors",
187
+ "transformer.h.26.mlp.fc_out.weight": "model-00012-of-00015.safetensors",
188
+ "transformer.h.27.attn.causal_mask": "model-00012-of-00015.safetensors",
189
+ "transformer.h.27.attn.out_proj.weight": "model-00013-of-00015.safetensors",
190
+ "transformer.h.27.attn.qkv_proj.weight": "model-00013-of-00015.safetensors",
191
+ "transformer.h.27.ln_1.bias": "model-00012-of-00015.safetensors",
192
+ "transformer.h.27.ln_1.weight": "model-00012-of-00015.safetensors",
193
+ "transformer.h.27.mlp.fc_in.bias": "model-00013-of-00015.safetensors",
194
+ "transformer.h.27.mlp.fc_in.weight": "model-00013-of-00015.safetensors",
195
+ "transformer.h.27.mlp.fc_out.bias": "model-00013-of-00015.safetensors",
196
+ "transformer.h.27.mlp.fc_out.weight": "model-00013-of-00015.safetensors",
197
+ "transformer.h.28.attn.causal_mask": "model-00013-of-00015.safetensors",
198
+ "transformer.h.28.attn.out_proj.weight": "model-00013-of-00015.safetensors",
199
+ "transformer.h.28.attn.qkv_proj.weight": "model-00013-of-00015.safetensors",
200
+ "transformer.h.28.ln_1.bias": "model-00013-of-00015.safetensors",
201
+ "transformer.h.28.ln_1.weight": "model-00013-of-00015.safetensors",
202
+ "transformer.h.28.mlp.fc_in.bias": "model-00013-of-00015.safetensors",
203
+ "transformer.h.28.mlp.fc_in.weight": "model-00013-of-00015.safetensors",
204
+ "transformer.h.28.mlp.fc_out.bias": "model-00013-of-00015.safetensors",
205
+ "transformer.h.28.mlp.fc_out.weight": "model-00013-of-00015.safetensors",
206
+ "transformer.h.29.attn.causal_mask": "model-00013-of-00015.safetensors",
207
+ "transformer.h.29.attn.out_proj.weight": "model-00013-of-00015.safetensors",
208
+ "transformer.h.29.attn.qkv_proj.weight": "model-00013-of-00015.safetensors",
209
+ "transformer.h.29.ln_1.bias": "model-00013-of-00015.safetensors",
210
+ "transformer.h.29.ln_1.weight": "model-00013-of-00015.safetensors",
211
+ "transformer.h.29.mlp.fc_in.bias": "model-00014-of-00015.safetensors",
212
+ "transformer.h.29.mlp.fc_in.weight": "model-00014-of-00015.safetensors",
213
+ "transformer.h.29.mlp.fc_out.bias": "model-00014-of-00015.safetensors",
214
+ "transformer.h.29.mlp.fc_out.weight": "model-00014-of-00015.safetensors",
215
+ "transformer.h.3.attn.causal_mask": "model-00002-of-00015.safetensors",
216
+ "transformer.h.3.attn.out_proj.weight": "model-00002-of-00015.safetensors",
217
+ "transformer.h.3.attn.qkv_proj.weight": "model-00002-of-00015.safetensors",
218
+ "transformer.h.3.ln_1.bias": "model-00002-of-00015.safetensors",
219
+ "transformer.h.3.ln_1.weight": "model-00002-of-00015.safetensors",
220
+ "transformer.h.3.mlp.fc_in.bias": "model-00002-of-00015.safetensors",
221
+ "transformer.h.3.mlp.fc_in.weight": "model-00002-of-00015.safetensors",
222
+ "transformer.h.3.mlp.fc_out.bias": "model-00003-of-00015.safetensors",
223
+ "transformer.h.3.mlp.fc_out.weight": "model-00003-of-00015.safetensors",
224
+ "transformer.h.30.attn.causal_mask": "model-00014-of-00015.safetensors",
225
+ "transformer.h.30.attn.out_proj.weight": "model-00014-of-00015.safetensors",
226
+ "transformer.h.30.attn.qkv_proj.weight": "model-00014-of-00015.safetensors",
227
+ "transformer.h.30.ln_1.bias": "model-00014-of-00015.safetensors",
228
+ "transformer.h.30.ln_1.weight": "model-00014-of-00015.safetensors",
229
+ "transformer.h.30.mlp.fc_in.bias": "model-00014-of-00015.safetensors",
230
+ "transformer.h.30.mlp.fc_in.weight": "model-00014-of-00015.safetensors",
231
+ "transformer.h.30.mlp.fc_out.bias": "model-00014-of-00015.safetensors",
232
+ "transformer.h.30.mlp.fc_out.weight": "model-00014-of-00015.safetensors",
233
+ "transformer.h.31.attn.causal_mask": "model-00014-of-00015.safetensors",
234
+ "transformer.h.31.attn.out_proj.weight": "model-00014-of-00015.safetensors",
235
+ "transformer.h.31.attn.qkv_proj.weight": "model-00014-of-00015.safetensors",
236
+ "transformer.h.31.ln_1.bias": "model-00014-of-00015.safetensors",
237
+ "transformer.h.31.ln_1.weight": "model-00014-of-00015.safetensors",
238
+ "transformer.h.31.mlp.fc_in.bias": "model-00014-of-00015.safetensors",
239
+ "transformer.h.31.mlp.fc_in.weight": "model-00014-of-00015.safetensors",
240
+ "transformer.h.31.mlp.fc_out.bias": "model-00015-of-00015.safetensors",
241
+ "transformer.h.31.mlp.fc_out.weight": "model-00015-of-00015.safetensors",
242
+ "transformer.h.32.attn.causal_mask": "model-00015-of-00015.safetensors",
243
+ "transformer.h.32.attn.out_proj.weight": "model-00015-of-00015.safetensors",
244
+ "transformer.h.32.attn.qkv_proj.weight": "model-00015-of-00015.safetensors",
245
+ "transformer.h.32.ln_1.bias": "model-00015-of-00015.safetensors",
246
+ "transformer.h.32.ln_1.weight": "model-00015-of-00015.safetensors",
247
+ "transformer.h.32.mlp.fc_in.bias": "model-00015-of-00015.safetensors",
248
+ "transformer.h.32.mlp.fc_in.weight": "model-00015-of-00015.safetensors",
249
+ "transformer.h.32.mlp.fc_out.bias": "model-00015-of-00015.safetensors",
250
+ "transformer.h.32.mlp.fc_out.weight": "model-00015-of-00015.safetensors",
251
+ "transformer.h.4.attn.causal_mask": "model-00003-of-00015.safetensors",
252
+ "transformer.h.4.attn.out_proj.weight": "model-00003-of-00015.safetensors",
253
+ "transformer.h.4.attn.qkv_proj.weight": "model-00003-of-00015.safetensors",
254
+ "transformer.h.4.ln_1.bias": "model-00003-of-00015.safetensors",
255
+ "transformer.h.4.ln_1.weight": "model-00003-of-00015.safetensors",
256
+ "transformer.h.4.mlp.fc_in.bias": "model-00003-of-00015.safetensors",
257
+ "transformer.h.4.mlp.fc_in.weight": "model-00003-of-00015.safetensors",
258
+ "transformer.h.4.mlp.fc_out.bias": "model-00003-of-00015.safetensors",
259
+ "transformer.h.4.mlp.fc_out.weight": "model-00003-of-00015.safetensors",
260
+ "transformer.h.5.attn.causal_mask": "model-00003-of-00015.safetensors",
261
+ "transformer.h.5.attn.out_proj.weight": "model-00003-of-00015.safetensors",
262
+ "transformer.h.5.attn.qkv_proj.weight": "model-00003-of-00015.safetensors",
263
+ "transformer.h.5.ln_1.bias": "model-00003-of-00015.safetensors",
264
+ "transformer.h.5.ln_1.weight": "model-00003-of-00015.safetensors",
265
+ "transformer.h.5.mlp.fc_in.bias": "model-00003-of-00015.safetensors",
266
+ "transformer.h.5.mlp.fc_in.weight": "model-00003-of-00015.safetensors",
267
+ "transformer.h.5.mlp.fc_out.bias": "model-00003-of-00015.safetensors",
268
+ "transformer.h.5.mlp.fc_out.weight": "model-00003-of-00015.safetensors",
269
+ "transformer.h.6.attn.causal_mask": "model-00003-of-00015.safetensors",
270
+ "transformer.h.6.attn.out_proj.weight": "model-00004-of-00015.safetensors",
271
+ "transformer.h.6.attn.qkv_proj.weight": "model-00004-of-00015.safetensors",
272
+ "transformer.h.6.ln_1.bias": "model-00003-of-00015.safetensors",
273
+ "transformer.h.6.ln_1.weight": "model-00003-of-00015.safetensors",
274
+ "transformer.h.6.mlp.fc_in.bias": "model-00004-of-00015.safetensors",
275
+ "transformer.h.6.mlp.fc_in.weight": "model-00004-of-00015.safetensors",
276
+ "transformer.h.6.mlp.fc_out.bias": "model-00004-of-00015.safetensors",
277
+ "transformer.h.6.mlp.fc_out.weight": "model-00004-of-00015.safetensors",
278
+ "transformer.h.7.attn.causal_mask": "model-00004-of-00015.safetensors",
279
+ "transformer.h.7.attn.out_proj.weight": "model-00004-of-00015.safetensors",
280
+ "transformer.h.7.attn.qkv_proj.weight": "model-00004-of-00015.safetensors",
281
+ "transformer.h.7.ln_1.bias": "model-00004-of-00015.safetensors",
282
+ "transformer.h.7.ln_1.weight": "model-00004-of-00015.safetensors",
283
+ "transformer.h.7.mlp.fc_in.bias": "model-00004-of-00015.safetensors",
284
+ "transformer.h.7.mlp.fc_in.weight": "model-00004-of-00015.safetensors",
285
+ "transformer.h.7.mlp.fc_out.bias": "model-00004-of-00015.safetensors",
286
+ "transformer.h.7.mlp.fc_out.weight": "model-00004-of-00015.safetensors",
287
+ "transformer.h.8.attn.causal_mask": "model-00004-of-00015.safetensors",
288
+ "transformer.h.8.attn.out_proj.weight": "model-00004-of-00015.safetensors",
289
+ "transformer.h.8.attn.qkv_proj.weight": "model-00004-of-00015.safetensors",
290
+ "transformer.h.8.ln_1.bias": "model-00004-of-00015.safetensors",
291
+ "transformer.h.8.ln_1.weight": "model-00004-of-00015.safetensors",
292
+ "transformer.h.8.mlp.fc_in.bias": "model-00005-of-00015.safetensors",
293
+ "transformer.h.8.mlp.fc_in.weight": "model-00005-of-00015.safetensors",
294
+ "transformer.h.8.mlp.fc_out.bias": "model-00005-of-00015.safetensors",
295
+ "transformer.h.8.mlp.fc_out.weight": "model-00005-of-00015.safetensors",
296
+ "transformer.h.9.attn.causal_mask": "model-00005-of-00015.safetensors",
297
+ "transformer.h.9.attn.out_proj.weight": "model-00005-of-00015.safetensors",
298
+ "transformer.h.9.attn.qkv_proj.weight": "model-00005-of-00015.safetensors",
299
+ "transformer.h.9.ln_1.bias": "model-00005-of-00015.safetensors",
300
+ "transformer.h.9.ln_1.weight": "model-00005-of-00015.safetensors",
301
+ "transformer.h.9.mlp.fc_in.bias": "model-00005-of-00015.safetensors",
302
+ "transformer.h.9.mlp.fc_in.weight": "model-00005-of-00015.safetensors",
303
+ "transformer.h.9.mlp.fc_out.bias": "model-00005-of-00015.safetensors",
304
+ "transformer.h.9.mlp.fc_out.weight": "model-00005-of-00015.safetensors",
305
+ "transformer.ln_f.bias": "model-00015-of-00015.safetensors",
306
+ "transformer.ln_f.weight": "model-00015-of-00015.safetensors",
307
+ "transformer.wte.weight": "model-00001-of-00015.safetensors"
308
+ }
309
+ }