Hugging Face's logo

OpenNLPLab
/
TransNormerLLM3-15B-Intermediate-Checkpoints

Text Generation
Transformers
English
Chinese
transnormer
TransNormerLLM
custom_code
Model card Files
xet
Community
2
OpenNLPLab commited on
Commit
d5582a7
·
verified ·
1 Parent(s): 60483f8

Upload 24 files

Browse files
Files changed (13) hide show
  1. modeling_transnormer.py +3 -2
  2. pytorch_model-00001-of-00011.bin +3 -0
  3. pytorch_model-00002-of-00011.bin +3 -0
  4. pytorch_model-00003-of-00011.bin +3 -0
  5. pytorch_model-00004-of-00011.bin +3 -0
  6. pytorch_model-00005-of-00011.bin +3 -0
  7. pytorch_model-00006-of-00011.bin +3 -0
  8. pytorch_model-00007-of-00011.bin +3 -0
  9. pytorch_model-00008-of-00011.bin +3 -0
  10. pytorch_model-00009-of-00011.bin +3 -0
  11. pytorch_model-00010-of-00011.bin +3 -0
  12. pytorch_model-00011-of-00011.bin +3 -0
  13. pytorch_model.bin.index.json +304 -0
modeling_transnormer.py CHANGED
@@ -346,8 +346,9 @@ class NormLinearAttention(nn.Module):
346
  k[:, :, i:i + 1],
347
  v[:, :, i:i + 1],
348
  )
349
- qkv = torch.einsum("... n e, ... e d -> ... n d",
350
- q[:, :, i:i + 1], kv)
 
351
  output.append(qkv)
352
  output = torch.concat(output, dim=-2)
353
 
 
346
  k[:, :, i:i + 1],
347
  v[:, :, i:i + 1],
348
  )
349
+ qkv = torch.einsum("... n e, ... e d -> ... n d", q[:, :,
350
+ i:i + 1],
351
+ kv.to(q.dtype))
352
  output.append(qkv)
353
  output = torch.concat(output, dim=-2)
354
 
pytorch_model-00001-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbbe5d3bb6c6f51f3e13eca34ecdfd771a613eecfda3ab8a668f8191b2ef7feb
3
+ size 2915304987
pytorch_model-00002-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd1150ec6cd150471c088cf4d3dca2bf7424d275677a094c7f975aafd67fcca6
3
+ size 2937333675
pytorch_model-00003-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20c72124cf3ac71f67320e38be1a6501ab1f460af5c40782f54cff7be1b8ac1c
3
+ size 2885232893
pytorch_model-00004-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb931907e95c1e3df04a7aa0767c71227daada8a5b4b5bbbeafca15b8a974c35
3
+ size 2884904601
pytorch_model-00005-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33453c8a55a981855674a927e5e7b56a797ca5da735bf92bb733db66bd4f7572
3
+ size 2884904601
pytorch_model-00006-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c9f43fe6f40ac4b29467a87ae6e0e0b4640ae2a233f606bb3416287ed2fea4e
3
+ size 2937333739
pytorch_model-00007-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a95d38a50b7633a0b8977e8fda8210691f67e78ec6ecc220104804cda5f41bde
3
+ size 2885232893
pytorch_model-00008-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df3b85bcab07611c6c115a5846c62ddc441b6501d520e06c868e1ea1b5bcbfba
3
+ size 2884904601
pytorch_model-00009-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928fe702bac43caa89a1aeaa12a917c3139cc1c4985988568c85b379297e82cc
3
+ size 2884904601
pytorch_model-00010-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16890bed8c61476a09a6bc32a0f4ad621594a2dc642d762afb26fc9fb8d39627
3
+ size 2937333739
pytorch_model-00011-of-00011.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f05c5ad092b5e0e2c5395b2fe016b72ba5f7d67cebd1bc8352af06f7d7b7dde
3
+ size 629475839
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,304 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 29666764800
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00001-of-00011.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00011.bin",
8
+ "model.layers.0.channel_mixer.l1.weight": "pytorch_model-00001-of-00011.bin",
9
+ "model.layers.0.channel_mixer.l2.weight": "pytorch_model-00001-of-00011.bin",
10
+ "model.layers.0.channel_mixer.l3.weight": "pytorch_model-00001-of-00011.bin",
11
+ "model.layers.0.token_mixer.lrpe.theta": "pytorch_model-00001-of-00011.bin",
12
+ "model.layers.0.token_mixer.out_proj.weight": "pytorch_model-00001-of-00011.bin",
13
+ "model.layers.0.token_mixer.output_gate.0.weight": "pytorch_model-00001-of-00011.bin",
14
+ "model.layers.0.token_mixer.output_gate.1.weight": "pytorch_model-00001-of-00011.bin",
15
+ "model.layers.0.token_mixer.qkv_proj.weight": "pytorch_model-00001-of-00011.bin",
16
+ "model.layers.1.channel_mixer.l1.weight": "pytorch_model-00001-of-00011.bin",
17
+ "model.layers.1.channel_mixer.l2.weight": "pytorch_model-00001-of-00011.bin",
18
+ "model.layers.1.channel_mixer.l3.weight": "pytorch_model-00001-of-00011.bin",
19
+ "model.layers.1.token_mixer.out_proj.weight": "pytorch_model-00001-of-00011.bin",
20
+ "model.layers.1.token_mixer.output_gate.0.weight": "pytorch_model-00001-of-00011.bin",
21
+ "model.layers.1.token_mixer.output_gate.1.weight": "pytorch_model-00001-of-00011.bin",
22
+ "model.layers.1.token_mixer.qkv_proj.weight": "pytorch_model-00001-of-00011.bin",
23
+ "model.layers.10.channel_mixer.l1.weight": "pytorch_model-00003-of-00011.bin",
24
+ "model.layers.10.channel_mixer.l2.weight": "pytorch_model-00003-of-00011.bin",
25
+ "model.layers.10.channel_mixer.l3.weight": "pytorch_model-00003-of-00011.bin",
26
+ "model.layers.10.token_mixer.out_proj.weight": "pytorch_model-00003-of-00011.bin",
27
+ "model.layers.10.token_mixer.output_gate.0.weight": "pytorch_model-00003-of-00011.bin",
28
+ "model.layers.10.token_mixer.output_gate.1.weight": "pytorch_model-00003-of-00011.bin",
29
+ "model.layers.10.token_mixer.qkv_proj.weight": "pytorch_model-00003-of-00011.bin",
30
+ "model.layers.11.channel_mixer.l1.weight": "pytorch_model-00004-of-00011.bin",
31
+ "model.layers.11.channel_mixer.l2.weight": "pytorch_model-00004-of-00011.bin",
32
+ "model.layers.11.channel_mixer.l3.weight": "pytorch_model-00004-of-00011.bin",
33
+ "model.layers.11.token_mixer.out_proj.weight": "pytorch_model-00003-of-00011.bin",
34
+ "model.layers.11.token_mixer.output_gate.0.weight": "pytorch_model-00003-of-00011.bin",
35
+ "model.layers.11.token_mixer.output_gate.1.weight": "pytorch_model-00003-of-00011.bin",
36
+ "model.layers.11.token_mixer.qkv_proj.weight": "pytorch_model-00003-of-00011.bin",
37
+ "model.layers.12.channel_mixer.l1.weight": "pytorch_model-00004-of-00011.bin",
38
+ "model.layers.12.channel_mixer.l2.weight": "pytorch_model-00004-of-00011.bin",
39
+ "model.layers.12.channel_mixer.l3.weight": "pytorch_model-00004-of-00011.bin",
40
+ "model.layers.12.token_mixer.out_proj.weight": "pytorch_model-00004-of-00011.bin",
41
+ "model.layers.12.token_mixer.output_gate.0.weight": "pytorch_model-00004-of-00011.bin",
42
+ "model.layers.12.token_mixer.output_gate.1.weight": "pytorch_model-00004-of-00011.bin",
43
+ "model.layers.12.token_mixer.qkv_proj.weight": "pytorch_model-00004-of-00011.bin",
44
+ "model.layers.13.channel_mixer.l1.weight": "pytorch_model-00004-of-00011.bin",
45
+ "model.layers.13.channel_mixer.l2.weight": "pytorch_model-00004-of-00011.bin",
46
+ "model.layers.13.channel_mixer.l3.weight": "pytorch_model-00004-of-00011.bin",
47
+ "model.layers.13.token_mixer.out_proj.weight": "pytorch_model-00004-of-00011.bin",
48
+ "model.layers.13.token_mixer.output_gate.0.weight": "pytorch_model-00004-of-00011.bin",
49
+ "model.layers.13.token_mixer.output_gate.1.weight": "pytorch_model-00004-of-00011.bin",
50
+ "model.layers.13.token_mixer.qkv_proj.weight": "pytorch_model-00004-of-00011.bin",
51
+ "model.layers.14.channel_mixer.l1.weight": "pytorch_model-00004-of-00011.bin",
52
+ "model.layers.14.channel_mixer.l2.weight": "pytorch_model-00004-of-00011.bin",
53
+ "model.layers.14.channel_mixer.l3.weight": "pytorch_model-00004-of-00011.bin",
54
+ "model.layers.14.token_mixer.out_proj.weight": "pytorch_model-00004-of-00011.bin",
55
+ "model.layers.14.token_mixer.output_gate.0.weight": "pytorch_model-00004-of-00011.bin",
56
+ "model.layers.14.token_mixer.output_gate.1.weight": "pytorch_model-00004-of-00011.bin",
57
+ "model.layers.14.token_mixer.qkv_proj.weight": "pytorch_model-00004-of-00011.bin",
58
+ "model.layers.15.channel_mixer.l1.weight": "pytorch_model-00004-of-00011.bin",
59
+ "model.layers.15.channel_mixer.l2.weight": "pytorch_model-00005-of-00011.bin",
60
+ "model.layers.15.channel_mixer.l3.weight": "pytorch_model-00005-of-00011.bin",
61
+ "model.layers.15.token_mixer.out_proj.weight": "pytorch_model-00004-of-00011.bin",
62
+ "model.layers.15.token_mixer.output_gate.0.weight": "pytorch_model-00004-of-00011.bin",
63
+ "model.layers.15.token_mixer.output_gate.1.weight": "pytorch_model-00004-of-00011.bin",
64
+ "model.layers.15.token_mixer.qkv_proj.weight": "pytorch_model-00004-of-00011.bin",
65
+ "model.layers.16.channel_mixer.l1.weight": "pytorch_model-00005-of-00011.bin",
66
+ "model.layers.16.channel_mixer.l2.weight": "pytorch_model-00005-of-00011.bin",
67
+ "model.layers.16.channel_mixer.l3.weight": "pytorch_model-00005-of-00011.bin",
68
+ "model.layers.16.token_mixer.out_proj.weight": "pytorch_model-00005-of-00011.bin",
69
+ "model.layers.16.token_mixer.output_gate.0.weight": "pytorch_model-00005-of-00011.bin",
70
+ "model.layers.16.token_mixer.output_gate.1.weight": "pytorch_model-00005-of-00011.bin",
71
+ "model.layers.16.token_mixer.qkv_proj.weight": "pytorch_model-00005-of-00011.bin",
72
+ "model.layers.17.channel_mixer.l1.weight": "pytorch_model-00005-of-00011.bin",
73
+ "model.layers.17.channel_mixer.l2.weight": "pytorch_model-00005-of-00011.bin",
74
+ "model.layers.17.channel_mixer.l3.weight": "pytorch_model-00005-of-00011.bin",
75
+ "model.layers.17.token_mixer.out_proj.weight": "pytorch_model-00005-of-00011.bin",
76
+ "model.layers.17.token_mixer.output_gate.0.weight": "pytorch_model-00005-of-00011.bin",
77
+ "model.layers.17.token_mixer.output_gate.1.weight": "pytorch_model-00005-of-00011.bin",
78
+ "model.layers.17.token_mixer.qkv_proj.weight": "pytorch_model-00005-of-00011.bin",
79
+ "model.layers.18.channel_mixer.l1.weight": "pytorch_model-00005-of-00011.bin",
80
+ "model.layers.18.channel_mixer.l2.weight": "pytorch_model-00005-of-00011.bin",
81
+ "model.layers.18.channel_mixer.l3.weight": "pytorch_model-00005-of-00011.bin",
82
+ "model.layers.18.token_mixer.out_proj.weight": "pytorch_model-00005-of-00011.bin",
83
+ "model.layers.18.token_mixer.output_gate.0.weight": "pytorch_model-00005-of-00011.bin",
84
+ "model.layers.18.token_mixer.output_gate.1.weight": "pytorch_model-00005-of-00011.bin",
85
+ "model.layers.18.token_mixer.qkv_proj.weight": "pytorch_model-00005-of-00011.bin",
86
+ "model.layers.19.channel_mixer.l1.weight": "pytorch_model-00005-of-00011.bin",
87
+ "model.layers.19.channel_mixer.l2.weight": "pytorch_model-00005-of-00011.bin",
88
+ "model.layers.19.channel_mixer.l3.weight": "pytorch_model-00006-of-00011.bin",
89
+ "model.layers.19.token_mixer.out_proj.weight": "pytorch_model-00005-of-00011.bin",
90
+ "model.layers.19.token_mixer.output_gate.0.weight": "pytorch_model-00005-of-00011.bin",
91
+ "model.layers.19.token_mixer.output_gate.1.weight": "pytorch_model-00005-of-00011.bin",
92
+ "model.layers.19.token_mixer.qkv_proj.weight": "pytorch_model-00005-of-00011.bin",
93
+ "model.layers.2.channel_mixer.l1.weight": "pytorch_model-00001-of-00011.bin",
94
+ "model.layers.2.channel_mixer.l2.weight": "pytorch_model-00001-of-00011.bin",
95
+ "model.layers.2.channel_mixer.l3.weight": "pytorch_model-00002-of-00011.bin",
96
+ "model.layers.2.token_mixer.out_proj.weight": "pytorch_model-00001-of-00011.bin",
97
+ "model.layers.2.token_mixer.output_gate.0.weight": "pytorch_model-00001-of-00011.bin",
98
+ "model.layers.2.token_mixer.output_gate.1.weight": "pytorch_model-00001-of-00011.bin",
99
+ "model.layers.2.token_mixer.qkv_proj.weight": "pytorch_model-00001-of-00011.bin",
100
+ "model.layers.20.channel_mixer.l1.weight": "pytorch_model-00006-of-00011.bin",
101
+ "model.layers.20.channel_mixer.l2.weight": "pytorch_model-00006-of-00011.bin",
102
+ "model.layers.20.channel_mixer.l3.weight": "pytorch_model-00006-of-00011.bin",
103
+ "model.layers.20.token_mixer.out_proj.weight": "pytorch_model-00006-of-00011.bin",
104
+ "model.layers.20.token_mixer.output_gate.0.weight": "pytorch_model-00006-of-00011.bin",
105
+ "model.layers.20.token_mixer.output_gate.1.weight": "pytorch_model-00006-of-00011.bin",
106
+ "model.layers.20.token_mixer.qkv_proj.weight": "pytorch_model-00006-of-00011.bin",
107
+ "model.layers.21.channel_mixer.l1.weight": "pytorch_model-00006-of-00011.bin",
108
+ "model.layers.21.channel_mixer.l2.weight": "pytorch_model-00006-of-00011.bin",
109
+ "model.layers.21.channel_mixer.l3.weight": "pytorch_model-00006-of-00011.bin",
110
+ "model.layers.21.token_mixer.out_proj.weight": "pytorch_model-00006-of-00011.bin",
111
+ "model.layers.21.token_mixer.output_gate.0.weight": "pytorch_model-00006-of-00011.bin",
112
+ "model.layers.21.token_mixer.output_gate.1.weight": "pytorch_model-00006-of-00011.bin",
113
+ "model.layers.21.token_mixer.qkv_proj.weight": "pytorch_model-00006-of-00011.bin",
114
+ "model.layers.22.channel_mixer.l1.weight": "pytorch_model-00006-of-00011.bin",
115
+ "model.layers.22.channel_mixer.l2.weight": "pytorch_model-00006-of-00011.bin",
116
+ "model.layers.22.channel_mixer.l3.weight": "pytorch_model-00006-of-00011.bin",
117
+ "model.layers.22.token_mixer.out_proj.weight": "pytorch_model-00006-of-00011.bin",
118
+ "model.layers.22.token_mixer.output_gate.0.weight": "pytorch_model-00006-of-00011.bin",
119
+ "model.layers.22.token_mixer.output_gate.1.weight": "pytorch_model-00006-of-00011.bin",
120
+ "model.layers.22.token_mixer.qkv_proj.weight": "pytorch_model-00006-of-00011.bin",
121
+ "model.layers.23.channel_mixer.l1.weight": "pytorch_model-00006-of-00011.bin",
122
+ "model.layers.23.channel_mixer.l2.weight": "pytorch_model-00006-of-00011.bin",
123
+ "model.layers.23.channel_mixer.l3.weight": "pytorch_model-00006-of-00011.bin",
124
+ "model.layers.23.token_mixer.out_proj.weight": "pytorch_model-00006-of-00011.bin",
125
+ "model.layers.23.token_mixer.output_gate.0.weight": "pytorch_model-00006-of-00011.bin",
126
+ "model.layers.23.token_mixer.output_gate.1.weight": "pytorch_model-00006-of-00011.bin",
127
+ "model.layers.23.token_mixer.qkv_proj.weight": "pytorch_model-00006-of-00011.bin",
128
+ "model.layers.24.channel_mixer.l1.weight": "pytorch_model-00007-of-00011.bin",
129
+ "model.layers.24.channel_mixer.l2.weight": "pytorch_model-00007-of-00011.bin",
130
+ "model.layers.24.channel_mixer.l3.weight": "pytorch_model-00007-of-00011.bin",
131
+ "model.layers.24.token_mixer.out_proj.weight": "pytorch_model-00006-of-00011.bin",
132
+ "model.layers.24.token_mixer.output_gate.0.weight": "pytorch_model-00007-of-00011.bin",
133
+ "model.layers.24.token_mixer.output_gate.1.weight": "pytorch_model-00007-of-00011.bin",
134
+ "model.layers.24.token_mixer.qkv_proj.weight": "pytorch_model-00007-of-00011.bin",
135
+ "model.layers.25.channel_mixer.l1.weight": "pytorch_model-00007-of-00011.bin",
136
+ "model.layers.25.channel_mixer.l2.weight": "pytorch_model-00007-of-00011.bin",
137
+ "model.layers.25.channel_mixer.l3.weight": "pytorch_model-00007-of-00011.bin",
138
+ "model.layers.25.token_mixer.out_proj.weight": "pytorch_model-00007-of-00011.bin",
139
+ "model.layers.25.token_mixer.output_gate.0.weight": "pytorch_model-00007-of-00011.bin",
140
+ "model.layers.25.token_mixer.output_gate.1.weight": "pytorch_model-00007-of-00011.bin",
141
+ "model.layers.25.token_mixer.qkv_proj.weight": "pytorch_model-00007-of-00011.bin",
142
+ "model.layers.26.channel_mixer.l1.weight": "pytorch_model-00007-of-00011.bin",
143
+ "model.layers.26.channel_mixer.l2.weight": "pytorch_model-00007-of-00011.bin",
144
+ "model.layers.26.channel_mixer.l3.weight": "pytorch_model-00007-of-00011.bin",
145
+ "model.layers.26.token_mixer.out_proj.weight": "pytorch_model-00007-of-00011.bin",
146
+ "model.layers.26.token_mixer.output_gate.0.weight": "pytorch_model-00007-of-00011.bin",
147
+ "model.layers.26.token_mixer.output_gate.1.weight": "pytorch_model-00007-of-00011.bin",
148
+ "model.layers.26.token_mixer.qkv_proj.weight": "pytorch_model-00007-of-00011.bin",
149
+ "model.layers.27.channel_mixer.l1.weight": "pytorch_model-00007-of-00011.bin",
150
+ "model.layers.27.channel_mixer.l2.weight": "pytorch_model-00007-of-00011.bin",
151
+ "model.layers.27.channel_mixer.l3.weight": "pytorch_model-00007-of-00011.bin",
152
+ "model.layers.27.token_mixer.out_proj.weight": "pytorch_model-00007-of-00011.bin",
153
+ "model.layers.27.token_mixer.output_gate.0.weight": "pytorch_model-00007-of-00011.bin",
154
+ "model.layers.27.token_mixer.output_gate.1.weight": "pytorch_model-00007-of-00011.bin",
155
+ "model.layers.27.token_mixer.qkv_proj.weight": "pytorch_model-00007-of-00011.bin",
156
+ "model.layers.28.channel_mixer.l1.weight": "pytorch_model-00008-of-00011.bin",
157
+ "model.layers.28.channel_mixer.l2.weight": "pytorch_model-00008-of-00011.bin",
158
+ "model.layers.28.channel_mixer.l3.weight": "pytorch_model-00008-of-00011.bin",
159
+ "model.layers.28.token_mixer.out_proj.weight": "pytorch_model-00007-of-00011.bin",
160
+ "model.layers.28.token_mixer.output_gate.0.weight": "pytorch_model-00007-of-00011.bin",
161
+ "model.layers.28.token_mixer.output_gate.1.weight": "pytorch_model-00007-of-00011.bin",
162
+ "model.layers.28.token_mixer.qkv_proj.weight": "pytorch_model-00007-of-00011.bin",
163
+ "model.layers.29.channel_mixer.l1.weight": "pytorch_model-00008-of-00011.bin",
164
+ "model.layers.29.channel_mixer.l2.weight": "pytorch_model-00008-of-00011.bin",
165
+ "model.layers.29.channel_mixer.l3.weight": "pytorch_model-00008-of-00011.bin",
166
+ "model.layers.29.token_mixer.out_proj.weight": "pytorch_model-00008-of-00011.bin",
167
+ "model.layers.29.token_mixer.output_gate.0.weight": "pytorch_model-00008-of-00011.bin",
168
+ "model.layers.29.token_mixer.output_gate.1.weight": "pytorch_model-00008-of-00011.bin",
169
+ "model.layers.29.token_mixer.qkv_proj.weight": "pytorch_model-00008-of-00011.bin",
170
+ "model.layers.3.channel_mixer.l1.weight": "pytorch_model-00002-of-00011.bin",
171
+ "model.layers.3.channel_mixer.l2.weight": "pytorch_model-00002-of-00011.bin",
172
+ "model.layers.3.channel_mixer.l3.weight": "pytorch_model-00002-of-00011.bin",
173
+ "model.layers.3.token_mixer.out_proj.weight": "pytorch_model-00002-of-00011.bin",
174
+ "model.layers.3.token_mixer.output_gate.0.weight": "pytorch_model-00002-of-00011.bin",
175
+ "model.layers.3.token_mixer.output_gate.1.weight": "pytorch_model-00002-of-00011.bin",
176
+ "model.layers.3.token_mixer.qkv_proj.weight": "pytorch_model-00002-of-00011.bin",
177
+ "model.layers.30.channel_mixer.l1.weight": "pytorch_model-00008-of-00011.bin",
178
+ "model.layers.30.channel_mixer.l2.weight": "pytorch_model-00008-of-00011.bin",
179
+ "model.layers.30.channel_mixer.l3.weight": "pytorch_model-00008-of-00011.bin",
180
+ "model.layers.30.token_mixer.out_proj.weight": "pytorch_model-00008-of-00011.bin",
181
+ "model.layers.30.token_mixer.output_gate.0.weight": "pytorch_model-00008-of-00011.bin",
182
+ "model.layers.30.token_mixer.output_gate.1.weight": "pytorch_model-00008-of-00011.bin",
183
+ "model.layers.30.token_mixer.qkv_proj.weight": "pytorch_model-00008-of-00011.bin",
184
+ "model.layers.31.channel_mixer.l1.weight": "pytorch_model-00008-of-00011.bin",
185
+ "model.layers.31.channel_mixer.l2.weight": "pytorch_model-00008-of-00011.bin",
186
+ "model.layers.31.channel_mixer.l3.weight": "pytorch_model-00008-of-00011.bin",
187
+ "model.layers.31.token_mixer.out_proj.weight": "pytorch_model-00008-of-00011.bin",
188
+ "model.layers.31.token_mixer.output_gate.0.weight": "pytorch_model-00008-of-00011.bin",
189
+ "model.layers.31.token_mixer.output_gate.1.weight": "pytorch_model-00008-of-00011.bin",
190
+ "model.layers.31.token_mixer.qkv_proj.weight": "pytorch_model-00008-of-00011.bin",
191
+ "model.layers.32.channel_mixer.l1.weight": "pytorch_model-00008-of-00011.bin",
192
+ "model.layers.32.channel_mixer.l2.weight": "pytorch_model-00009-of-00011.bin",
193
+ "model.layers.32.channel_mixer.l3.weight": "pytorch_model-00009-of-00011.bin",
194
+ "model.layers.32.token_mixer.out_proj.weight": "pytorch_model-00008-of-00011.bin",
195
+ "model.layers.32.token_mixer.output_gate.0.weight": "pytorch_model-00008-of-00011.bin",
196
+ "model.layers.32.token_mixer.output_gate.1.weight": "pytorch_model-00008-of-00011.bin",
197
+ "model.layers.32.token_mixer.qkv_proj.weight": "pytorch_model-00008-of-00011.bin",
198
+ "model.layers.33.channel_mixer.l1.weight": "pytorch_model-00009-of-00011.bin",
199
+ "model.layers.33.channel_mixer.l2.weight": "pytorch_model-00009-of-00011.bin",
200
+ "model.layers.33.channel_mixer.l3.weight": "pytorch_model-00009-of-00011.bin",
201
+ "model.layers.33.token_mixer.out_proj.weight": "pytorch_model-00009-of-00011.bin",
202
+ "model.layers.33.token_mixer.output_gate.0.weight": "pytorch_model-00009-of-00011.bin",
203
+ "model.layers.33.token_mixer.output_gate.1.weight": "pytorch_model-00009-of-00011.bin",
204
+ "model.layers.33.token_mixer.qkv_proj.weight": "pytorch_model-00009-of-00011.bin",
205
+ "model.layers.34.channel_mixer.l1.weight": "pytorch_model-00009-of-00011.bin",
206
+ "model.layers.34.channel_mixer.l2.weight": "pytorch_model-00009-of-00011.bin",
207
+ "model.layers.34.channel_mixer.l3.weight": "pytorch_model-00009-of-00011.bin",
208
+ "model.layers.34.token_mixer.out_proj.weight": "pytorch_model-00009-of-00011.bin",
209
+ "model.layers.34.token_mixer.output_gate.0.weight": "pytorch_model-00009-of-00011.bin",
210
+ "model.layers.34.token_mixer.output_gate.1.weight": "pytorch_model-00009-of-00011.bin",
211
+ "model.layers.34.token_mixer.qkv_proj.weight": "pytorch_model-00009-of-00011.bin",
212
+ "model.layers.35.channel_mixer.l1.weight": "pytorch_model-00009-of-00011.bin",
213
+ "model.layers.35.channel_mixer.l2.weight": "pytorch_model-00009-of-00011.bin",
214
+ "model.layers.35.channel_mixer.l3.weight": "pytorch_model-00009-of-00011.bin",
215
+ "model.layers.35.token_mixer.out_proj.weight": "pytorch_model-00009-of-00011.bin",
216
+ "model.layers.35.token_mixer.output_gate.0.weight": "pytorch_model-00009-of-00011.bin",
217
+ "model.layers.35.token_mixer.output_gate.1.weight": "pytorch_model-00009-of-00011.bin",
218
+ "model.layers.35.token_mixer.qkv_proj.weight": "pytorch_model-00009-of-00011.bin",
219
+ "model.layers.36.channel_mixer.l1.weight": "pytorch_model-00009-of-00011.bin",
220
+ "model.layers.36.channel_mixer.l2.weight": "pytorch_model-00009-of-00011.bin",
221
+ "model.layers.36.channel_mixer.l3.weight": "pytorch_model-00010-of-00011.bin",
222
+ "model.layers.36.token_mixer.out_proj.weight": "pytorch_model-00009-of-00011.bin",
223
+ "model.layers.36.token_mixer.output_gate.0.weight": "pytorch_model-00009-of-00011.bin",
224
+ "model.layers.36.token_mixer.output_gate.1.weight": "pytorch_model-00009-of-00011.bin",
225
+ "model.layers.36.token_mixer.qkv_proj.weight": "pytorch_model-00009-of-00011.bin",
226
+ "model.layers.37.channel_mixer.l1.weight": "pytorch_model-00010-of-00011.bin",
227
+ "model.layers.37.channel_mixer.l2.weight": "pytorch_model-00010-of-00011.bin",
228
+ "model.layers.37.channel_mixer.l3.weight": "pytorch_model-00010-of-00011.bin",
229
+ "model.layers.37.token_mixer.out_proj.weight": "pytorch_model-00010-of-00011.bin",
230
+ "model.layers.37.token_mixer.output_gate.0.weight": "pytorch_model-00010-of-00011.bin",
231
+ "model.layers.37.token_mixer.output_gate.1.weight": "pytorch_model-00010-of-00011.bin",
232
+ "model.layers.37.token_mixer.qkv_proj.weight": "pytorch_model-00010-of-00011.bin",
233
+ "model.layers.38.channel_mixer.l1.weight": "pytorch_model-00010-of-00011.bin",
234
+ "model.layers.38.channel_mixer.l2.weight": "pytorch_model-00010-of-00011.bin",
235
+ "model.layers.38.channel_mixer.l3.weight": "pytorch_model-00010-of-00011.bin",
236
+ "model.layers.38.token_mixer.out_proj.weight": "pytorch_model-00010-of-00011.bin",
237
+ "model.layers.38.token_mixer.output_gate.0.weight": "pytorch_model-00010-of-00011.bin",
238
+ "model.layers.38.token_mixer.output_gate.1.weight": "pytorch_model-00010-of-00011.bin",
239
+ "model.layers.38.token_mixer.qkv_proj.weight": "pytorch_model-00010-of-00011.bin",
240
+ "model.layers.39.channel_mixer.l1.weight": "pytorch_model-00010-of-00011.bin",
241
+ "model.layers.39.channel_mixer.l2.weight": "pytorch_model-00010-of-00011.bin",
242
+ "model.layers.39.channel_mixer.l3.weight": "pytorch_model-00010-of-00011.bin",
243
+ "model.layers.39.token_mixer.out_proj.weight": "pytorch_model-00010-of-00011.bin",
244
+ "model.layers.39.token_mixer.output_gate.0.weight": "pytorch_model-00010-of-00011.bin",
245
+ "model.layers.39.token_mixer.output_gate.1.weight": "pytorch_model-00010-of-00011.bin",
246
+ "model.layers.39.token_mixer.qkv_proj.weight": "pytorch_model-00010-of-00011.bin",
247
+ "model.layers.4.channel_mixer.l1.weight": "pytorch_model-00002-of-00011.bin",
248
+ "model.layers.4.channel_mixer.l2.weight": "pytorch_model-00002-of-00011.bin",
249
+ "model.layers.4.channel_mixer.l3.weight": "pytorch_model-00002-of-00011.bin",
250
+ "model.layers.4.token_mixer.out_proj.weight": "pytorch_model-00002-of-00011.bin",
251
+ "model.layers.4.token_mixer.output_gate.0.weight": "pytorch_model-00002-of-00011.bin",
252
+ "model.layers.4.token_mixer.output_gate.1.weight": "pytorch_model-00002-of-00011.bin",
253
+ "model.layers.4.token_mixer.qkv_proj.weight": "pytorch_model-00002-of-00011.bin",
254
+ "model.layers.40.channel_mixer.l1.weight": "pytorch_model-00010-of-00011.bin",
255
+ "model.layers.40.channel_mixer.l2.weight": "pytorch_model-00010-of-00011.bin",
256
+ "model.layers.40.channel_mixer.l3.weight": "pytorch_model-00010-of-00011.bin",
257
+ "model.layers.40.token_mixer.out_proj.weight": "pytorch_model-00010-of-00011.bin",
258
+ "model.layers.40.token_mixer.output_gate.0.weight": "pytorch_model-00010-of-00011.bin",
259
+ "model.layers.40.token_mixer.output_gate.1.weight": "pytorch_model-00010-of-00011.bin",
260
+ "model.layers.40.token_mixer.qkv_proj.weight": "pytorch_model-00010-of-00011.bin",
261
+ "model.layers.41.channel_mixer.l1.weight": "pytorch_model-00011-of-00011.bin",
262
+ "model.layers.41.channel_mixer.l2.weight": "pytorch_model-00011-of-00011.bin",
263
+ "model.layers.41.channel_mixer.l3.weight": "pytorch_model-00011-of-00011.bin",
264
+ "model.layers.41.token_mixer.out_proj.weight": "pytorch_model-00010-of-00011.bin",
265
+ "model.layers.41.token_mixer.output_gate.0.weight": "pytorch_model-00011-of-00011.bin",
266
+ "model.layers.41.token_mixer.output_gate.1.weight": "pytorch_model-00011-of-00011.bin",
267
+ "model.layers.41.token_mixer.qkv_proj.weight": "pytorch_model-00011-of-00011.bin",
268
+ "model.layers.5.channel_mixer.l1.weight": "pytorch_model-00002-of-00011.bin",
269
+ "model.layers.5.channel_mixer.l2.weight": "pytorch_model-00002-of-00011.bin",
270
+ "model.layers.5.channel_mixer.l3.weight": "pytorch_model-00002-of-00011.bin",
271
+ "model.layers.5.token_mixer.out_proj.weight": "pytorch_model-00002-of-00011.bin",
272
+ "model.layers.5.token_mixer.output_gate.0.weight": "pytorch_model-00002-of-00011.bin",
273
+ "model.layers.5.token_mixer.output_gate.1.weight": "pytorch_model-00002-of-00011.bin",
274
+ "model.layers.5.token_mixer.qkv_proj.weight": "pytorch_model-00002-of-00011.bin",
275
+ "model.layers.6.channel_mixer.l1.weight": "pytorch_model-00002-of-00011.bin",
276
+ "model.layers.6.channel_mixer.l2.weight": "pytorch_model-00002-of-00011.bin",
277
+ "model.layers.6.channel_mixer.l3.weight": "pytorch_model-00002-of-00011.bin",
278
+ "model.layers.6.token_mixer.out_proj.weight": "pytorch_model-00002-of-00011.bin",
279
+ "model.layers.6.token_mixer.output_gate.0.weight": "pytorch_model-00002-of-00011.bin",
280
+ "model.layers.6.token_mixer.output_gate.1.weight": "pytorch_model-00002-of-00011.bin",
281
+ "model.layers.6.token_mixer.qkv_proj.weight": "pytorch_model-00002-of-00011.bin",
282
+ "model.layers.7.channel_mixer.l1.weight": "pytorch_model-00003-of-00011.bin",
283
+ "model.layers.7.channel_mixer.l2.weight": "pytorch_model-00003-of-00011.bin",
284
+ "model.layers.7.channel_mixer.l3.weight": "pytorch_model-00003-of-00011.bin",
285
+ "model.layers.7.token_mixer.out_proj.weight": "pytorch_model-00002-of-00011.bin",
286
+ "model.layers.7.token_mixer.output_gate.0.weight": "pytorch_model-00003-of-00011.bin",
287
+ "model.layers.7.token_mixer.output_gate.1.weight": "pytorch_model-00003-of-00011.bin",
288
+ "model.layers.7.token_mixer.qkv_proj.weight": "pytorch_model-00003-of-00011.bin",
289
+ "model.layers.8.channel_mixer.l1.weight": "pytorch_model-00003-of-00011.bin",
290
+ "model.layers.8.channel_mixer.l2.weight": "pytorch_model-00003-of-00011.bin",
291
+ "model.layers.8.channel_mixer.l3.weight": "pytorch_model-00003-of-00011.bin",
292
+ "model.layers.8.token_mixer.out_proj.weight": "pytorch_model-00003-of-00011.bin",
293
+ "model.layers.8.token_mixer.output_gate.0.weight": "pytorch_model-00003-of-00011.bin",
294
+ "model.layers.8.token_mixer.output_gate.1.weight": "pytorch_model-00003-of-00011.bin",
295
+ "model.layers.8.token_mixer.qkv_proj.weight": "pytorch_model-00003-of-00011.bin",
296
+ "model.layers.9.channel_mixer.l1.weight": "pytorch_model-00003-of-00011.bin",
297
+ "model.layers.9.channel_mixer.l2.weight": "pytorch_model-00003-of-00011.bin",
298
+ "model.layers.9.channel_mixer.l3.weight": "pytorch_model-00003-of-00011.bin",
299
+ "model.layers.9.token_mixer.out_proj.weight": "pytorch_model-00003-of-00011.bin",
300
+ "model.layers.9.token_mixer.output_gate.0.weight": "pytorch_model-00003-of-00011.bin",
301
+ "model.layers.9.token_mixer.output_gate.1.weight": "pytorch_model-00003-of-00011.bin",
302
+ "model.layers.9.token_mixer.qkv_proj.weight": "pytorch_model-00003-of-00011.bin"
303
+ }
304
+ }