thamada
commited on
Commit
•
efd5d24
1
Parent(s):
b3a3cb6
add mp8
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- mp8/README.md +55 -0
- mp8/consolidated.00/consolidated-00001-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00002-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00003-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00004-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00005-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00006-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00007-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00008-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00009-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00010-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00011-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00012-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00013-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00014-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00015-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00016-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00017-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00018-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00019-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00020-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00021-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated-00022-of-00022.pth +3 -0
- mp8/consolidated.00/consolidated.pth.index.json +1144 -0
- mp8/consolidated.01/consolidated-00001-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00002-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00003-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00004-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00005-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00006-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00007-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00008-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00009-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00010-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00011-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00012-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00013-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00014-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00015-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00016-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00017-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00018-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00019-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00020-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00021-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated-00022-of-00022.pth +3 -0
- mp8/consolidated.01/consolidated.pth.index.json +1144 -0
- mp8/consolidated.02/consolidated-00001-of-00022.pth +3 -0
- mp8/consolidated.02/consolidated-00002-of-00022.pth +3 -0
- mp8/consolidated.02/consolidated-00003-of-00022.pth +3 -0
mp8/README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Addition from the Hugging Face team
|
2 |
+
|
3 |
+
> [!IMPORTANT]
|
4 |
+
>
|
5 |
+
> This repository corresponds to the original Llama format and codebase, not the transformers library
|
6 |
+
|
7 |
+
The weights were originally distributed in the following format:
|
8 |
+
|
9 |
+
```
|
10 |
+
weights/
|
11 |
+
consolidated.00.pth
|
12 |
+
consolidated.01.pth
|
13 |
+
...
|
14 |
+
```
|
15 |
+
|
16 |
+
Unfortunately, the files themselves were too large for the Hub to handle, so we had to shard them.
|
17 |
+
In order to keep the same structure that was originally given, the sharding is done as follows:
|
18 |
+
|
19 |
+
|
20 |
+
```
|
21 |
+
weights/
|
22 |
+
consolidated.00/
|
23 |
+
consolidated-00001-of-00011.pth
|
24 |
+
consolidated-00002-of-00011.pth
|
25 |
+
...
|
26 |
+
consolidated.01/
|
27 |
+
consolidated-00001-of-00011.pth
|
28 |
+
consolidated-00002-of-00011.pth
|
29 |
+
...
|
30 |
+
...
|
31 |
+
```
|
32 |
+
|
33 |
+
If trying to run the code that was given with the original weights, we recommend running this script to join the files together once again:
|
34 |
+
|
35 |
+
|
36 |
+
```py
|
37 |
+
import os
|
38 |
+
import torch
|
39 |
+
|
40 |
+
from pathlib import Path
|
41 |
+
|
42 |
+
path_to_files = Path('.../weights')
|
43 |
+
|
44 |
+
folders = [folder for folder in os.listdir(path_to_files) if os.path.isdir(path_to_files / folder) and folder.startswith('consolidated')]
|
45 |
+
for folder in folders:
|
46 |
+
state_dict = {}
|
47 |
+
files = [file for file in os.listdir(path_to_files / folder) if file.endswith(".pth")]
|
48 |
+
|
49 |
+
for file in files:
|
50 |
+
state_dict_partial = torch.load(path_to_files / folder / file, map_location="cpu")
|
51 |
+
for key, value in state_dict_partial.items():
|
52 |
+
state_dict[key]=value
|
53 |
+
|
54 |
+
torch.save(state_dict, path_to_files / f"{folder}.pth")
|
55 |
+
```
|
mp8/consolidated.00/consolidated-00001-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82a24725af2c501bd3f6eaef1317178dd1cf91b743d235b8aad4241f911ed73e
|
3 |
+
size 4870980313
|
mp8/consolidated.00/consolidated-00002-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84eefbc1e4af3dcc0bff6e6826f0faac3a7ddb6db8589229107be48f5a891089
|
3 |
+
size 4781917812
|
mp8/consolidated.00/consolidated-00003-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77e8d2c3b14116d3b7ed57faebe98e184a67e36727b3dddef50fe8734f7cc254
|
3 |
+
size 4781917876
|
mp8/consolidated.00/consolidated-00004-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21852544089ff9f59977d649a7e89e8c58ef27f3dff5b1f3c29d9f7569a74a9e
|
3 |
+
size 4781917876
|
mp8/consolidated.00/consolidated-00005-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6fa844698a04650c32073af9dd275beed5709420cd7b01250d8d7acba970f9a
|
3 |
+
size 4781917876
|
mp8/consolidated.00/consolidated-00006-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7a8379326f7edd6cad430b2825277be0f2832db4f41bbeb883060255465ae32
|
3 |
+
size 4781917876
|
mp8/consolidated.00/consolidated-00007-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:276ce60c24d09a455ca3b63b87d529c6d1cf96ba6818f3b03352e23f3239c7ff
|
3 |
+
size 4781917876
|
mp8/consolidated.00/consolidated-00008-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fb29ad62d70fcd3398ebe9e1d0f9543d040ce30423120a22a914fcdc8d34bd5
|
3 |
+
size 4781917876
|
mp8/consolidated.00/consolidated-00009-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0271f28e0655a3aee18fd7081ac84efd41cbf81a3f1d040c65653df7db5dd3de
|
3 |
+
size 4781917876
|
mp8/consolidated.00/consolidated-00010-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3cbf1e3b9ae8c552e8cb47908066a88af1a8ec91b9b06432338b65932105412f
|
3 |
+
size 4781917876
|
mp8/consolidated.00/consolidated-00011-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb369294f30262130ec04f9455b87502e99e4826fbac15d346b905858a3e72cb
|
3 |
+
size 4781917876
|
mp8/consolidated.00/consolidated-00012-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e938f8a6fbca2931db1003a7eb2dfd439c033396f7828e23ada11dc5de58d86
|
3 |
+
size 4781917876
|
mp8/consolidated.00/consolidated-00013-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29d625497096c62c74f1ced1b310316c2bfcc1ebbff61c52cec637cecafa27a0
|
3 |
+
size 4781917876
|
mp8/consolidated.00/consolidated-00014-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f8cfae88c9ba58b2a1ebdd1608c899af26ca35d6a279f5c06894953a01ef298
|
3 |
+
size 4781917876
|
mp8/consolidated.00/consolidated-00015-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07ec81131f61b758cec0a480bf3203361acc140b45e3b7abd759462b4cf90ce0
|
3 |
+
size 4781917876
|
mp8/consolidated.00/consolidated-00016-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1d7debe2480ce2ee37dfe49569f4ff3f39d75a89d0af64bebd37e0ad4e8d56a
|
3 |
+
size 4781917876
|
mp8/consolidated.00/consolidated-00017-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9bc5d9023afddd4025f9d648e5ebdcfe35f8b34f1e3e5dd921e134b8e085b28
|
3 |
+
size 4781917876
|
mp8/consolidated.00/consolidated-00018-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5e020419201c24c679ac12ec5753085d039e3811a7352d916e80b66f52f677a
|
3 |
+
size 4781917940
|
mp8/consolidated.00/consolidated-00019-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2490891133dda2a05ece4195532c9caf1f7f5a0cd0c7753f1a4bd145da442605
|
3 |
+
size 4781917940
|
mp8/consolidated.00/consolidated-00020-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eec43066f0ddf7dfc5218f6edb252575e24bfc6c0aea0f603a27b3999d2d1376
|
3 |
+
size 4781917940
|
mp8/consolidated.00/consolidated-00021-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2d0553a5241926349bc20d86fe91948c4e6f0c1f5521f3e97deead0d81f0a16
|
3 |
+
size 4781917940
|
mp8/consolidated.00/consolidated-00022-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:459bd4b1e50693ad120500b71ab361225ae6db2506a0da2cccf8a6dc5427df98
|
3 |
+
size 961645392
|
mp8/consolidated.00/consolidated.pth.index.json
ADDED
@@ -0,0 +1,1144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 101470601216
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"tok_embeddings.weight": "consolidated-00001-of-00022.pth",
|
7 |
+
"layers.0.attention.wq.weight": "consolidated-00001-of-00022.pth",
|
8 |
+
"layers.0.attention.wk.weight": "consolidated-00001-of-00022.pth",
|
9 |
+
"layers.0.attention.wv.weight": "consolidated-00001-of-00022.pth",
|
10 |
+
"layers.0.attention.wo.weight": "consolidated-00001-of-00022.pth",
|
11 |
+
"layers.0.feed_forward.w1.weight": "consolidated-00001-of-00022.pth",
|
12 |
+
"layers.0.feed_forward.w3.weight": "consolidated-00001-of-00022.pth",
|
13 |
+
"layers.0.feed_forward.w2.weight": "consolidated-00001-of-00022.pth",
|
14 |
+
"layers.0.attention_norm.weight": "consolidated-00001-of-00022.pth",
|
15 |
+
"layers.0.ffn_norm.weight": "consolidated-00001-of-00022.pth",
|
16 |
+
"layers.1.attention.wq.weight": "consolidated-00001-of-00022.pth",
|
17 |
+
"layers.1.attention.wk.weight": "consolidated-00001-of-00022.pth",
|
18 |
+
"layers.1.attention.wv.weight": "consolidated-00001-of-00022.pth",
|
19 |
+
"layers.1.attention.wo.weight": "consolidated-00001-of-00022.pth",
|
20 |
+
"layers.1.feed_forward.w1.weight": "consolidated-00001-of-00022.pth",
|
21 |
+
"layers.1.feed_forward.w3.weight": "consolidated-00001-of-00022.pth",
|
22 |
+
"layers.1.feed_forward.w2.weight": "consolidated-00001-of-00022.pth",
|
23 |
+
"layers.1.attention_norm.weight": "consolidated-00001-of-00022.pth",
|
24 |
+
"layers.1.ffn_norm.weight": "consolidated-00001-of-00022.pth",
|
25 |
+
"layers.2.attention.wq.weight": "consolidated-00001-of-00022.pth",
|
26 |
+
"layers.2.attention.wk.weight": "consolidated-00001-of-00022.pth",
|
27 |
+
"layers.2.attention.wv.weight": "consolidated-00001-of-00022.pth",
|
28 |
+
"layers.2.attention.wo.weight": "consolidated-00001-of-00022.pth",
|
29 |
+
"layers.2.feed_forward.w1.weight": "consolidated-00001-of-00022.pth",
|
30 |
+
"layers.2.feed_forward.w3.weight": "consolidated-00001-of-00022.pth",
|
31 |
+
"layers.2.feed_forward.w2.weight": "consolidated-00001-of-00022.pth",
|
32 |
+
"layers.2.attention_norm.weight": "consolidated-00001-of-00022.pth",
|
33 |
+
"layers.2.ffn_norm.weight": "consolidated-00001-of-00022.pth",
|
34 |
+
"layers.3.attention.wq.weight": "consolidated-00001-of-00022.pth",
|
35 |
+
"layers.3.attention.wk.weight": "consolidated-00001-of-00022.pth",
|
36 |
+
"layers.3.attention.wv.weight": "consolidated-00001-of-00022.pth",
|
37 |
+
"layers.3.attention.wo.weight": "consolidated-00001-of-00022.pth",
|
38 |
+
"layers.3.feed_forward.w1.weight": "consolidated-00001-of-00022.pth",
|
39 |
+
"layers.3.feed_forward.w3.weight": "consolidated-00001-of-00022.pth",
|
40 |
+
"layers.3.feed_forward.w2.weight": "consolidated-00001-of-00022.pth",
|
41 |
+
"layers.3.attention_norm.weight": "consolidated-00001-of-00022.pth",
|
42 |
+
"layers.3.ffn_norm.weight": "consolidated-00001-of-00022.pth",
|
43 |
+
"layers.4.attention.wq.weight": "consolidated-00001-of-00022.pth",
|
44 |
+
"layers.4.attention.wk.weight": "consolidated-00001-of-00022.pth",
|
45 |
+
"layers.4.attention.wv.weight": "consolidated-00001-of-00022.pth",
|
46 |
+
"layers.4.attention.wo.weight": "consolidated-00001-of-00022.pth",
|
47 |
+
"layers.4.feed_forward.w1.weight": "consolidated-00001-of-00022.pth",
|
48 |
+
"layers.4.feed_forward.w3.weight": "consolidated-00001-of-00022.pth",
|
49 |
+
"layers.4.feed_forward.w2.weight": "consolidated-00001-of-00022.pth",
|
50 |
+
"layers.4.attention_norm.weight": "consolidated-00001-of-00022.pth",
|
51 |
+
"layers.4.ffn_norm.weight": "consolidated-00001-of-00022.pth",
|
52 |
+
"layers.5.attention.wq.weight": "consolidated-00001-of-00022.pth",
|
53 |
+
"layers.5.attention.wk.weight": "consolidated-00001-of-00022.pth",
|
54 |
+
"layers.5.attention.wv.weight": "consolidated-00001-of-00022.pth",
|
55 |
+
"layers.5.attention.wo.weight": "consolidated-00001-of-00022.pth",
|
56 |
+
"layers.5.feed_forward.w1.weight": "consolidated-00001-of-00022.pth",
|
57 |
+
"layers.5.feed_forward.w3.weight": "consolidated-00002-of-00022.pth",
|
58 |
+
"layers.5.feed_forward.w2.weight": "consolidated-00002-of-00022.pth",
|
59 |
+
"layers.5.attention_norm.weight": "consolidated-00002-of-00022.pth",
|
60 |
+
"layers.5.ffn_norm.weight": "consolidated-00002-of-00022.pth",
|
61 |
+
"layers.6.attention.wq.weight": "consolidated-00002-of-00022.pth",
|
62 |
+
"layers.6.attention.wk.weight": "consolidated-00002-of-00022.pth",
|
63 |
+
"layers.6.attention.wv.weight": "consolidated-00002-of-00022.pth",
|
64 |
+
"layers.6.attention.wo.weight": "consolidated-00002-of-00022.pth",
|
65 |
+
"layers.6.feed_forward.w1.weight": "consolidated-00002-of-00022.pth",
|
66 |
+
"layers.6.feed_forward.w3.weight": "consolidated-00002-of-00022.pth",
|
67 |
+
"layers.6.feed_forward.w2.weight": "consolidated-00002-of-00022.pth",
|
68 |
+
"layers.6.attention_norm.weight": "consolidated-00002-of-00022.pth",
|
69 |
+
"layers.6.ffn_norm.weight": "consolidated-00002-of-00022.pth",
|
70 |
+
"layers.7.attention.wq.weight": "consolidated-00002-of-00022.pth",
|
71 |
+
"layers.7.attention.wk.weight": "consolidated-00002-of-00022.pth",
|
72 |
+
"layers.7.attention.wv.weight": "consolidated-00002-of-00022.pth",
|
73 |
+
"layers.7.attention.wo.weight": "consolidated-00002-of-00022.pth",
|
74 |
+
"layers.7.feed_forward.w1.weight": "consolidated-00002-of-00022.pth",
|
75 |
+
"layers.7.feed_forward.w3.weight": "consolidated-00002-of-00022.pth",
|
76 |
+
"layers.7.feed_forward.w2.weight": "consolidated-00002-of-00022.pth",
|
77 |
+
"layers.7.attention_norm.weight": "consolidated-00002-of-00022.pth",
|
78 |
+
"layers.7.ffn_norm.weight": "consolidated-00002-of-00022.pth",
|
79 |
+
"layers.8.attention.wq.weight": "consolidated-00002-of-00022.pth",
|
80 |
+
"layers.8.attention.wk.weight": "consolidated-00002-of-00022.pth",
|
81 |
+
"layers.8.attention.wv.weight": "consolidated-00002-of-00022.pth",
|
82 |
+
"layers.8.attention.wo.weight": "consolidated-00002-of-00022.pth",
|
83 |
+
"layers.8.feed_forward.w1.weight": "consolidated-00002-of-00022.pth",
|
84 |
+
"layers.8.feed_forward.w3.weight": "consolidated-00002-of-00022.pth",
|
85 |
+
"layers.8.feed_forward.w2.weight": "consolidated-00002-of-00022.pth",
|
86 |
+
"layers.8.attention_norm.weight": "consolidated-00002-of-00022.pth",
|
87 |
+
"layers.8.ffn_norm.weight": "consolidated-00002-of-00022.pth",
|
88 |
+
"layers.9.attention.wq.weight": "consolidated-00002-of-00022.pth",
|
89 |
+
"layers.9.attention.wk.weight": "consolidated-00002-of-00022.pth",
|
90 |
+
"layers.9.attention.wv.weight": "consolidated-00002-of-00022.pth",
|
91 |
+
"layers.9.attention.wo.weight": "consolidated-00002-of-00022.pth",
|
92 |
+
"layers.9.feed_forward.w1.weight": "consolidated-00002-of-00022.pth",
|
93 |
+
"layers.9.feed_forward.w3.weight": "consolidated-00002-of-00022.pth",
|
94 |
+
"layers.9.feed_forward.w2.weight": "consolidated-00002-of-00022.pth",
|
95 |
+
"layers.9.attention_norm.weight": "consolidated-00002-of-00022.pth",
|
96 |
+
"layers.9.ffn_norm.weight": "consolidated-00002-of-00022.pth",
|
97 |
+
"layers.10.attention.wq.weight": "consolidated-00002-of-00022.pth",
|
98 |
+
"layers.10.attention.wk.weight": "consolidated-00002-of-00022.pth",
|
99 |
+
"layers.10.attention.wv.weight": "consolidated-00002-of-00022.pth",
|
100 |
+
"layers.10.attention.wo.weight": "consolidated-00002-of-00022.pth",
|
101 |
+
"layers.10.feed_forward.w1.weight": "consolidated-00002-of-00022.pth",
|
102 |
+
"layers.10.feed_forward.w3.weight": "consolidated-00002-of-00022.pth",
|
103 |
+
"layers.10.feed_forward.w2.weight": "consolidated-00002-of-00022.pth",
|
104 |
+
"layers.10.attention_norm.weight": "consolidated-00002-of-00022.pth",
|
105 |
+
"layers.10.ffn_norm.weight": "consolidated-00002-of-00022.pth",
|
106 |
+
"layers.11.attention.wq.weight": "consolidated-00002-of-00022.pth",
|
107 |
+
"layers.11.attention.wk.weight": "consolidated-00002-of-00022.pth",
|
108 |
+
"layers.11.attention.wv.weight": "consolidated-00002-of-00022.pth",
|
109 |
+
"layers.11.attention.wo.weight": "consolidated-00002-of-00022.pth",
|
110 |
+
"layers.11.feed_forward.w1.weight": "consolidated-00002-of-00022.pth",
|
111 |
+
"layers.11.feed_forward.w3.weight": "consolidated-00003-of-00022.pth",
|
112 |
+
"layers.11.feed_forward.w2.weight": "consolidated-00003-of-00022.pth",
|
113 |
+
"layers.11.attention_norm.weight": "consolidated-00003-of-00022.pth",
|
114 |
+
"layers.11.ffn_norm.weight": "consolidated-00003-of-00022.pth",
|
115 |
+
"layers.12.attention.wq.weight": "consolidated-00003-of-00022.pth",
|
116 |
+
"layers.12.attention.wk.weight": "consolidated-00003-of-00022.pth",
|
117 |
+
"layers.12.attention.wv.weight": "consolidated-00003-of-00022.pth",
|
118 |
+
"layers.12.attention.wo.weight": "consolidated-00003-of-00022.pth",
|
119 |
+
"layers.12.feed_forward.w1.weight": "consolidated-00003-of-00022.pth",
|
120 |
+
"layers.12.feed_forward.w3.weight": "consolidated-00003-of-00022.pth",
|
121 |
+
"layers.12.feed_forward.w2.weight": "consolidated-00003-of-00022.pth",
|
122 |
+
"layers.12.attention_norm.weight": "consolidated-00003-of-00022.pth",
|
123 |
+
"layers.12.ffn_norm.weight": "consolidated-00003-of-00022.pth",
|
124 |
+
"layers.13.attention.wq.weight": "consolidated-00003-of-00022.pth",
|
125 |
+
"layers.13.attention.wk.weight": "consolidated-00003-of-00022.pth",
|
126 |
+
"layers.13.attention.wv.weight": "consolidated-00003-of-00022.pth",
|
127 |
+
"layers.13.attention.wo.weight": "consolidated-00003-of-00022.pth",
|
128 |
+
"layers.13.feed_forward.w1.weight": "consolidated-00003-of-00022.pth",
|
129 |
+
"layers.13.feed_forward.w3.weight": "consolidated-00003-of-00022.pth",
|
130 |
+
"layers.13.feed_forward.w2.weight": "consolidated-00003-of-00022.pth",
|
131 |
+
"layers.13.attention_norm.weight": "consolidated-00003-of-00022.pth",
|
132 |
+
"layers.13.ffn_norm.weight": "consolidated-00003-of-00022.pth",
|
133 |
+
"layers.14.attention.wq.weight": "consolidated-00003-of-00022.pth",
|
134 |
+
"layers.14.attention.wk.weight": "consolidated-00003-of-00022.pth",
|
135 |
+
"layers.14.attention.wv.weight": "consolidated-00003-of-00022.pth",
|
136 |
+
"layers.14.attention.wo.weight": "consolidated-00003-of-00022.pth",
|
137 |
+
"layers.14.feed_forward.w1.weight": "consolidated-00003-of-00022.pth",
|
138 |
+
"layers.14.feed_forward.w3.weight": "consolidated-00003-of-00022.pth",
|
139 |
+
"layers.14.feed_forward.w2.weight": "consolidated-00003-of-00022.pth",
|
140 |
+
"layers.14.attention_norm.weight": "consolidated-00003-of-00022.pth",
|
141 |
+
"layers.14.ffn_norm.weight": "consolidated-00003-of-00022.pth",
|
142 |
+
"layers.15.attention.wq.weight": "consolidated-00003-of-00022.pth",
|
143 |
+
"layers.15.attention.wk.weight": "consolidated-00003-of-00022.pth",
|
144 |
+
"layers.15.attention.wv.weight": "consolidated-00003-of-00022.pth",
|
145 |
+
"layers.15.attention.wo.weight": "consolidated-00003-of-00022.pth",
|
146 |
+
"layers.15.feed_forward.w1.weight": "consolidated-00003-of-00022.pth",
|
147 |
+
"layers.15.feed_forward.w3.weight": "consolidated-00003-of-00022.pth",
|
148 |
+
"layers.15.feed_forward.w2.weight": "consolidated-00003-of-00022.pth",
|
149 |
+
"layers.15.attention_norm.weight": "consolidated-00003-of-00022.pth",
|
150 |
+
"layers.15.ffn_norm.weight": "consolidated-00003-of-00022.pth",
|
151 |
+
"layers.16.attention.wq.weight": "consolidated-00003-of-00022.pth",
|
152 |
+
"layers.16.attention.wk.weight": "consolidated-00003-of-00022.pth",
|
153 |
+
"layers.16.attention.wv.weight": "consolidated-00003-of-00022.pth",
|
154 |
+
"layers.16.attention.wo.weight": "consolidated-00003-of-00022.pth",
|
155 |
+
"layers.16.feed_forward.w1.weight": "consolidated-00003-of-00022.pth",
|
156 |
+
"layers.16.feed_forward.w3.weight": "consolidated-00003-of-00022.pth",
|
157 |
+
"layers.16.feed_forward.w2.weight": "consolidated-00003-of-00022.pth",
|
158 |
+
"layers.16.attention_norm.weight": "consolidated-00003-of-00022.pth",
|
159 |
+
"layers.16.ffn_norm.weight": "consolidated-00003-of-00022.pth",
|
160 |
+
"layers.17.attention.wq.weight": "consolidated-00003-of-00022.pth",
|
161 |
+
"layers.17.attention.wk.weight": "consolidated-00003-of-00022.pth",
|
162 |
+
"layers.17.attention.wv.weight": "consolidated-00003-of-00022.pth",
|
163 |
+
"layers.17.attention.wo.weight": "consolidated-00003-of-00022.pth",
|
164 |
+
"layers.17.feed_forward.w1.weight": "consolidated-00003-of-00022.pth",
|
165 |
+
"layers.17.feed_forward.w3.weight": "consolidated-00004-of-00022.pth",
|
166 |
+
"layers.17.feed_forward.w2.weight": "consolidated-00004-of-00022.pth",
|
167 |
+
"layers.17.attention_norm.weight": "consolidated-00004-of-00022.pth",
|
168 |
+
"layers.17.ffn_norm.weight": "consolidated-00004-of-00022.pth",
|
169 |
+
"layers.18.attention.wq.weight": "consolidated-00004-of-00022.pth",
|
170 |
+
"layers.18.attention.wk.weight": "consolidated-00004-of-00022.pth",
|
171 |
+
"layers.18.attention.wv.weight": "consolidated-00004-of-00022.pth",
|
172 |
+
"layers.18.attention.wo.weight": "consolidated-00004-of-00022.pth",
|
173 |
+
"layers.18.feed_forward.w1.weight": "consolidated-00004-of-00022.pth",
|
174 |
+
"layers.18.feed_forward.w3.weight": "consolidated-00004-of-00022.pth",
|
175 |
+
"layers.18.feed_forward.w2.weight": "consolidated-00004-of-00022.pth",
|
176 |
+
"layers.18.attention_norm.weight": "consolidated-00004-of-00022.pth",
|
177 |
+
"layers.18.ffn_norm.weight": "consolidated-00004-of-00022.pth",
|
178 |
+
"layers.19.attention.wq.weight": "consolidated-00004-of-00022.pth",
|
179 |
+
"layers.19.attention.wk.weight": "consolidated-00004-of-00022.pth",
|
180 |
+
"layers.19.attention.wv.weight": "consolidated-00004-of-00022.pth",
|
181 |
+
"layers.19.attention.wo.weight": "consolidated-00004-of-00022.pth",
|
182 |
+
"layers.19.feed_forward.w1.weight": "consolidated-00004-of-00022.pth",
|
183 |
+
"layers.19.feed_forward.w3.weight": "consolidated-00004-of-00022.pth",
|
184 |
+
"layers.19.feed_forward.w2.weight": "consolidated-00004-of-00022.pth",
|
185 |
+
"layers.19.attention_norm.weight": "consolidated-00004-of-00022.pth",
|
186 |
+
"layers.19.ffn_norm.weight": "consolidated-00004-of-00022.pth",
|
187 |
+
"layers.20.attention.wq.weight": "consolidated-00004-of-00022.pth",
|
188 |
+
"layers.20.attention.wk.weight": "consolidated-00004-of-00022.pth",
|
189 |
+
"layers.20.attention.wv.weight": "consolidated-00004-of-00022.pth",
|
190 |
+
"layers.20.attention.wo.weight": "consolidated-00004-of-00022.pth",
|
191 |
+
"layers.20.feed_forward.w1.weight": "consolidated-00004-of-00022.pth",
|
192 |
+
"layers.20.feed_forward.w3.weight": "consolidated-00004-of-00022.pth",
|
193 |
+
"layers.20.feed_forward.w2.weight": "consolidated-00004-of-00022.pth",
|
194 |
+
"layers.20.attention_norm.weight": "consolidated-00004-of-00022.pth",
|
195 |
+
"layers.20.ffn_norm.weight": "consolidated-00004-of-00022.pth",
|
196 |
+
"layers.21.attention.wq.weight": "consolidated-00004-of-00022.pth",
|
197 |
+
"layers.21.attention.wk.weight": "consolidated-00004-of-00022.pth",
|
198 |
+
"layers.21.attention.wv.weight": "consolidated-00004-of-00022.pth",
|
199 |
+
"layers.21.attention.wo.weight": "consolidated-00004-of-00022.pth",
|
200 |
+
"layers.21.feed_forward.w1.weight": "consolidated-00004-of-00022.pth",
|
201 |
+
"layers.21.feed_forward.w3.weight": "consolidated-00004-of-00022.pth",
|
202 |
+
"layers.21.feed_forward.w2.weight": "consolidated-00004-of-00022.pth",
|
203 |
+
"layers.21.attention_norm.weight": "consolidated-00004-of-00022.pth",
|
204 |
+
"layers.21.ffn_norm.weight": "consolidated-00004-of-00022.pth",
|
205 |
+
"layers.22.attention.wq.weight": "consolidated-00004-of-00022.pth",
|
206 |
+
"layers.22.attention.wk.weight": "consolidated-00004-of-00022.pth",
|
207 |
+
"layers.22.attention.wv.weight": "consolidated-00004-of-00022.pth",
|
208 |
+
"layers.22.attention.wo.weight": "consolidated-00004-of-00022.pth",
|
209 |
+
"layers.22.feed_forward.w1.weight": "consolidated-00004-of-00022.pth",
|
210 |
+
"layers.22.feed_forward.w3.weight": "consolidated-00004-of-00022.pth",
|
211 |
+
"layers.22.feed_forward.w2.weight": "consolidated-00004-of-00022.pth",
|
212 |
+
"layers.22.attention_norm.weight": "consolidated-00004-of-00022.pth",
|
213 |
+
"layers.22.ffn_norm.weight": "consolidated-00004-of-00022.pth",
|
214 |
+
"layers.23.attention.wq.weight": "consolidated-00004-of-00022.pth",
|
215 |
+
"layers.23.attention.wk.weight": "consolidated-00004-of-00022.pth",
|
216 |
+
"layers.23.attention.wv.weight": "consolidated-00004-of-00022.pth",
|
217 |
+
"layers.23.attention.wo.weight": "consolidated-00004-of-00022.pth",
|
218 |
+
"layers.23.feed_forward.w1.weight": "consolidated-00004-of-00022.pth",
|
219 |
+
"layers.23.feed_forward.w3.weight": "consolidated-00005-of-00022.pth",
|
220 |
+
"layers.23.feed_forward.w2.weight": "consolidated-00005-of-00022.pth",
|
221 |
+
"layers.23.attention_norm.weight": "consolidated-00005-of-00022.pth",
|
222 |
+
"layers.23.ffn_norm.weight": "consolidated-00005-of-00022.pth",
|
223 |
+
"layers.24.attention.wq.weight": "consolidated-00005-of-00022.pth",
|
224 |
+
"layers.24.attention.wk.weight": "consolidated-00005-of-00022.pth",
|
225 |
+
"layers.24.attention.wv.weight": "consolidated-00005-of-00022.pth",
|
226 |
+
"layers.24.attention.wo.weight": "consolidated-00005-of-00022.pth",
|
227 |
+
"layers.24.feed_forward.w1.weight": "consolidated-00005-of-00022.pth",
|
228 |
+
"layers.24.feed_forward.w3.weight": "consolidated-00005-of-00022.pth",
|
229 |
+
"layers.24.feed_forward.w2.weight": "consolidated-00005-of-00022.pth",
|
230 |
+
"layers.24.attention_norm.weight": "consolidated-00005-of-00022.pth",
|
231 |
+
"layers.24.ffn_norm.weight": "consolidated-00005-of-00022.pth",
|
232 |
+
"layers.25.attention.wq.weight": "consolidated-00005-of-00022.pth",
|
233 |
+
"layers.25.attention.wk.weight": "consolidated-00005-of-00022.pth",
|
234 |
+
"layers.25.attention.wv.weight": "consolidated-00005-of-00022.pth",
|
235 |
+
"layers.25.attention.wo.weight": "consolidated-00005-of-00022.pth",
|
236 |
+
"layers.25.feed_forward.w1.weight": "consolidated-00005-of-00022.pth",
|
237 |
+
"layers.25.feed_forward.w3.weight": "consolidated-00005-of-00022.pth",
|
238 |
+
"layers.25.feed_forward.w2.weight": "consolidated-00005-of-00022.pth",
|
239 |
+
"layers.25.attention_norm.weight": "consolidated-00005-of-00022.pth",
|
240 |
+
"layers.25.ffn_norm.weight": "consolidated-00005-of-00022.pth",
|
241 |
+
"layers.26.attention.wq.weight": "consolidated-00005-of-00022.pth",
|
242 |
+
"layers.26.attention.wk.weight": "consolidated-00005-of-00022.pth",
|
243 |
+
"layers.26.attention.wv.weight": "consolidated-00005-of-00022.pth",
|
244 |
+
"layers.26.attention.wo.weight": "consolidated-00005-of-00022.pth",
|
245 |
+
"layers.26.feed_forward.w1.weight": "consolidated-00005-of-00022.pth",
|
246 |
+
"layers.26.feed_forward.w3.weight": "consolidated-00005-of-00022.pth",
|
247 |
+
"layers.26.feed_forward.w2.weight": "consolidated-00005-of-00022.pth",
|
248 |
+
"layers.26.attention_norm.weight": "consolidated-00005-of-00022.pth",
|
249 |
+
"layers.26.ffn_norm.weight": "consolidated-00005-of-00022.pth",
|
250 |
+
"layers.27.attention.wq.weight": "consolidated-00005-of-00022.pth",
|
251 |
+
"layers.27.attention.wk.weight": "consolidated-00005-of-00022.pth",
|
252 |
+
"layers.27.attention.wv.weight": "consolidated-00005-of-00022.pth",
|
253 |
+
"layers.27.attention.wo.weight": "consolidated-00005-of-00022.pth",
|
254 |
+
"layers.27.feed_forward.w1.weight": "consolidated-00005-of-00022.pth",
|
255 |
+
"layers.27.feed_forward.w3.weight": "consolidated-00005-of-00022.pth",
|
256 |
+
"layers.27.feed_forward.w2.weight": "consolidated-00005-of-00022.pth",
|
257 |
+
"layers.27.attention_norm.weight": "consolidated-00005-of-00022.pth",
|
258 |
+
"layers.27.ffn_norm.weight": "consolidated-00005-of-00022.pth",
|
259 |
+
"layers.28.attention.wq.weight": "consolidated-00005-of-00022.pth",
|
260 |
+
"layers.28.attention.wk.weight": "consolidated-00005-of-00022.pth",
|
261 |
+
"layers.28.attention.wv.weight": "consolidated-00005-of-00022.pth",
|
262 |
+
"layers.28.attention.wo.weight": "consolidated-00005-of-00022.pth",
|
263 |
+
"layers.28.feed_forward.w1.weight": "consolidated-00005-of-00022.pth",
|
264 |
+
"layers.28.feed_forward.w3.weight": "consolidated-00005-of-00022.pth",
|
265 |
+
"layers.28.feed_forward.w2.weight": "consolidated-00005-of-00022.pth",
|
266 |
+
"layers.28.attention_norm.weight": "consolidated-00005-of-00022.pth",
|
267 |
+
"layers.28.ffn_norm.weight": "consolidated-00005-of-00022.pth",
|
268 |
+
"layers.29.attention.wq.weight": "consolidated-00005-of-00022.pth",
|
269 |
+
"layers.29.attention.wk.weight": "consolidated-00005-of-00022.pth",
|
270 |
+
"layers.29.attention.wv.weight": "consolidated-00005-of-00022.pth",
|
271 |
+
"layers.29.attention.wo.weight": "consolidated-00005-of-00022.pth",
|
272 |
+
"layers.29.feed_forward.w1.weight": "consolidated-00005-of-00022.pth",
|
273 |
+
"layers.29.feed_forward.w3.weight": "consolidated-00006-of-00022.pth",
|
274 |
+
"layers.29.feed_forward.w2.weight": "consolidated-00006-of-00022.pth",
|
275 |
+
"layers.29.attention_norm.weight": "consolidated-00006-of-00022.pth",
|
276 |
+
"layers.29.ffn_norm.weight": "consolidated-00006-of-00022.pth",
|
277 |
+
"layers.30.attention.wq.weight": "consolidated-00006-of-00022.pth",
|
278 |
+
"layers.30.attention.wk.weight": "consolidated-00006-of-00022.pth",
|
279 |
+
"layers.30.attention.wv.weight": "consolidated-00006-of-00022.pth",
|
280 |
+
"layers.30.attention.wo.weight": "consolidated-00006-of-00022.pth",
|
281 |
+
"layers.30.feed_forward.w1.weight": "consolidated-00006-of-00022.pth",
|
282 |
+
"layers.30.feed_forward.w3.weight": "consolidated-00006-of-00022.pth",
|
283 |
+
"layers.30.feed_forward.w2.weight": "consolidated-00006-of-00022.pth",
|
284 |
+
"layers.30.attention_norm.weight": "consolidated-00006-of-00022.pth",
|
285 |
+
"layers.30.ffn_norm.weight": "consolidated-00006-of-00022.pth",
|
286 |
+
"layers.31.attention.wq.weight": "consolidated-00006-of-00022.pth",
|
287 |
+
"layers.31.attention.wk.weight": "consolidated-00006-of-00022.pth",
|
288 |
+
"layers.31.attention.wv.weight": "consolidated-00006-of-00022.pth",
|
289 |
+
"layers.31.attention.wo.weight": "consolidated-00006-of-00022.pth",
|
290 |
+
"layers.31.feed_forward.w1.weight": "consolidated-00006-of-00022.pth",
|
291 |
+
"layers.31.feed_forward.w3.weight": "consolidated-00006-of-00022.pth",
|
292 |
+
"layers.31.feed_forward.w2.weight": "consolidated-00006-of-00022.pth",
|
293 |
+
"layers.31.attention_norm.weight": "consolidated-00006-of-00022.pth",
|
294 |
+
"layers.31.ffn_norm.weight": "consolidated-00006-of-00022.pth",
|
295 |
+
"layers.32.attention.wq.weight": "consolidated-00006-of-00022.pth",
|
296 |
+
"layers.32.attention.wk.weight": "consolidated-00006-of-00022.pth",
|
297 |
+
"layers.32.attention.wv.weight": "consolidated-00006-of-00022.pth",
|
298 |
+
"layers.32.attention.wo.weight": "consolidated-00006-of-00022.pth",
|
299 |
+
"layers.32.feed_forward.w1.weight": "consolidated-00006-of-00022.pth",
|
300 |
+
"layers.32.feed_forward.w3.weight": "consolidated-00006-of-00022.pth",
|
301 |
+
"layers.32.feed_forward.w2.weight": "consolidated-00006-of-00022.pth",
|
302 |
+
"layers.32.attention_norm.weight": "consolidated-00006-of-00022.pth",
|
303 |
+
"layers.32.ffn_norm.weight": "consolidated-00006-of-00022.pth",
|
304 |
+
"layers.33.attention.wq.weight": "consolidated-00006-of-00022.pth",
|
305 |
+
"layers.33.attention.wk.weight": "consolidated-00006-of-00022.pth",
|
306 |
+
"layers.33.attention.wv.weight": "consolidated-00006-of-00022.pth",
|
307 |
+
"layers.33.attention.wo.weight": "consolidated-00006-of-00022.pth",
|
308 |
+
"layers.33.feed_forward.w1.weight": "consolidated-00006-of-00022.pth",
|
309 |
+
"layers.33.feed_forward.w3.weight": "consolidated-00006-of-00022.pth",
|
310 |
+
"layers.33.feed_forward.w2.weight": "consolidated-00006-of-00022.pth",
|
311 |
+
"layers.33.attention_norm.weight": "consolidated-00006-of-00022.pth",
|
312 |
+
"layers.33.ffn_norm.weight": "consolidated-00006-of-00022.pth",
|
313 |
+
"layers.34.attention.wq.weight": "consolidated-00006-of-00022.pth",
|
314 |
+
"layers.34.attention.wk.weight": "consolidated-00006-of-00022.pth",
|
315 |
+
"layers.34.attention.wv.weight": "consolidated-00006-of-00022.pth",
|
316 |
+
"layers.34.attention.wo.weight": "consolidated-00006-of-00022.pth",
|
317 |
+
"layers.34.feed_forward.w1.weight": "consolidated-00006-of-00022.pth",
|
318 |
+
"layers.34.feed_forward.w3.weight": "consolidated-00006-of-00022.pth",
|
319 |
+
"layers.34.feed_forward.w2.weight": "consolidated-00006-of-00022.pth",
|
320 |
+
"layers.34.attention_norm.weight": "consolidated-00006-of-00022.pth",
|
321 |
+
"layers.34.ffn_norm.weight": "consolidated-00006-of-00022.pth",
|
322 |
+
"layers.35.attention.wq.weight": "consolidated-00006-of-00022.pth",
|
323 |
+
"layers.35.attention.wk.weight": "consolidated-00006-of-00022.pth",
|
324 |
+
"layers.35.attention.wv.weight": "consolidated-00006-of-00022.pth",
|
325 |
+
"layers.35.attention.wo.weight": "consolidated-00006-of-00022.pth",
|
326 |
+
"layers.35.feed_forward.w1.weight": "consolidated-00006-of-00022.pth",
|
327 |
+
"layers.35.feed_forward.w3.weight": "consolidated-00007-of-00022.pth",
|
328 |
+
"layers.35.feed_forward.w2.weight": "consolidated-00007-of-00022.pth",
|
329 |
+
"layers.35.attention_norm.weight": "consolidated-00007-of-00022.pth",
|
330 |
+
"layers.35.ffn_norm.weight": "consolidated-00007-of-00022.pth",
|
331 |
+
"layers.36.attention.wq.weight": "consolidated-00007-of-00022.pth",
|
332 |
+
"layers.36.attention.wk.weight": "consolidated-00007-of-00022.pth",
|
333 |
+
"layers.36.attention.wv.weight": "consolidated-00007-of-00022.pth",
|
334 |
+
"layers.36.attention.wo.weight": "consolidated-00007-of-00022.pth",
|
335 |
+
"layers.36.feed_forward.w1.weight": "consolidated-00007-of-00022.pth",
|
336 |
+
"layers.36.feed_forward.w3.weight": "consolidated-00007-of-00022.pth",
|
337 |
+
"layers.36.feed_forward.w2.weight": "consolidated-00007-of-00022.pth",
|
338 |
+
"layers.36.attention_norm.weight": "consolidated-00007-of-00022.pth",
|
339 |
+
"layers.36.ffn_norm.weight": "consolidated-00007-of-00022.pth",
|
340 |
+
"layers.37.attention.wq.weight": "consolidated-00007-of-00022.pth",
|
341 |
+
"layers.37.attention.wk.weight": "consolidated-00007-of-00022.pth",
|
342 |
+
"layers.37.attention.wv.weight": "consolidated-00007-of-00022.pth",
|
343 |
+
"layers.37.attention.wo.weight": "consolidated-00007-of-00022.pth",
|
344 |
+
"layers.37.feed_forward.w1.weight": "consolidated-00007-of-00022.pth",
|
345 |
+
"layers.37.feed_forward.w3.weight": "consolidated-00007-of-00022.pth",
|
346 |
+
"layers.37.feed_forward.w2.weight": "consolidated-00007-of-00022.pth",
|
347 |
+
"layers.37.attention_norm.weight": "consolidated-00007-of-00022.pth",
|
348 |
+
"layers.37.ffn_norm.weight": "consolidated-00007-of-00022.pth",
|
349 |
+
"layers.38.attention.wq.weight": "consolidated-00007-of-00022.pth",
|
350 |
+
"layers.38.attention.wk.weight": "consolidated-00007-of-00022.pth",
|
351 |
+
"layers.38.attention.wv.weight": "consolidated-00007-of-00022.pth",
|
352 |
+
"layers.38.attention.wo.weight": "consolidated-00007-of-00022.pth",
|
353 |
+
"layers.38.feed_forward.w1.weight": "consolidated-00007-of-00022.pth",
|
354 |
+
"layers.38.feed_forward.w3.weight": "consolidated-00007-of-00022.pth",
|
355 |
+
"layers.38.feed_forward.w2.weight": "consolidated-00007-of-00022.pth",
|
356 |
+
"layers.38.attention_norm.weight": "consolidated-00007-of-00022.pth",
|
357 |
+
"layers.38.ffn_norm.weight": "consolidated-00007-of-00022.pth",
|
358 |
+
"layers.39.attention.wq.weight": "consolidated-00007-of-00022.pth",
|
359 |
+
"layers.39.attention.wk.weight": "consolidated-00007-of-00022.pth",
|
360 |
+
"layers.39.attention.wv.weight": "consolidated-00007-of-00022.pth",
|
361 |
+
"layers.39.attention.wo.weight": "consolidated-00007-of-00022.pth",
|
362 |
+
"layers.39.feed_forward.w1.weight": "consolidated-00007-of-00022.pth",
|
363 |
+
"layers.39.feed_forward.w3.weight": "consolidated-00007-of-00022.pth",
|
364 |
+
"layers.39.feed_forward.w2.weight": "consolidated-00007-of-00022.pth",
|
365 |
+
"layers.39.attention_norm.weight": "consolidated-00007-of-00022.pth",
|
366 |
+
"layers.39.ffn_norm.weight": "consolidated-00007-of-00022.pth",
|
367 |
+
"layers.40.attention.wq.weight": "consolidated-00007-of-00022.pth",
|
368 |
+
"layers.40.attention.wk.weight": "consolidated-00007-of-00022.pth",
|
369 |
+
"layers.40.attention.wv.weight": "consolidated-00007-of-00022.pth",
|
370 |
+
"layers.40.attention.wo.weight": "consolidated-00007-of-00022.pth",
|
371 |
+
"layers.40.feed_forward.w1.weight": "consolidated-00007-of-00022.pth",
|
372 |
+
"layers.40.feed_forward.w3.weight": "consolidated-00007-of-00022.pth",
|
373 |
+
"layers.40.feed_forward.w2.weight": "consolidated-00007-of-00022.pth",
|
374 |
+
"layers.40.attention_norm.weight": "consolidated-00007-of-00022.pth",
|
375 |
+
"layers.40.ffn_norm.weight": "consolidated-00007-of-00022.pth",
|
376 |
+
"layers.41.attention.wq.weight": "consolidated-00007-of-00022.pth",
|
377 |
+
"layers.41.attention.wk.weight": "consolidated-00007-of-00022.pth",
|
378 |
+
"layers.41.attention.wv.weight": "consolidated-00007-of-00022.pth",
|
379 |
+
"layers.41.attention.wo.weight": "consolidated-00007-of-00022.pth",
|
380 |
+
"layers.41.feed_forward.w1.weight": "consolidated-00007-of-00022.pth",
|
381 |
+
"layers.41.feed_forward.w3.weight": "consolidated-00008-of-00022.pth",
|
382 |
+
"layers.41.feed_forward.w2.weight": "consolidated-00008-of-00022.pth",
|
383 |
+
"layers.41.attention_norm.weight": "consolidated-00008-of-00022.pth",
|
384 |
+
"layers.41.ffn_norm.weight": "consolidated-00008-of-00022.pth",
|
385 |
+
"layers.42.attention.wq.weight": "consolidated-00008-of-00022.pth",
|
386 |
+
"layers.42.attention.wk.weight": "consolidated-00008-of-00022.pth",
|
387 |
+
"layers.42.attention.wv.weight": "consolidated-00008-of-00022.pth",
|
388 |
+
"layers.42.attention.wo.weight": "consolidated-00008-of-00022.pth",
|
389 |
+
"layers.42.feed_forward.w1.weight": "consolidated-00008-of-00022.pth",
|
390 |
+
"layers.42.feed_forward.w3.weight": "consolidated-00008-of-00022.pth",
|
391 |
+
"layers.42.feed_forward.w2.weight": "consolidated-00008-of-00022.pth",
|
392 |
+
"layers.42.attention_norm.weight": "consolidated-00008-of-00022.pth",
|
393 |
+
"layers.42.ffn_norm.weight": "consolidated-00008-of-00022.pth",
|
394 |
+
"layers.43.attention.wq.weight": "consolidated-00008-of-00022.pth",
|
395 |
+
"layers.43.attention.wk.weight": "consolidated-00008-of-00022.pth",
|
396 |
+
"layers.43.attention.wv.weight": "consolidated-00008-of-00022.pth",
|
397 |
+
"layers.43.attention.wo.weight": "consolidated-00008-of-00022.pth",
|
398 |
+
"layers.43.feed_forward.w1.weight": "consolidated-00008-of-00022.pth",
|
399 |
+
"layers.43.feed_forward.w3.weight": "consolidated-00008-of-00022.pth",
|
400 |
+
"layers.43.feed_forward.w2.weight": "consolidated-00008-of-00022.pth",
|
401 |
+
"layers.43.attention_norm.weight": "consolidated-00008-of-00022.pth",
|
402 |
+
"layers.43.ffn_norm.weight": "consolidated-00008-of-00022.pth",
|
403 |
+
"layers.44.attention.wq.weight": "consolidated-00008-of-00022.pth",
|
404 |
+
"layers.44.attention.wk.weight": "consolidated-00008-of-00022.pth",
|
405 |
+
"layers.44.attention.wv.weight": "consolidated-00008-of-00022.pth",
|
406 |
+
"layers.44.attention.wo.weight": "consolidated-00008-of-00022.pth",
|
407 |
+
"layers.44.feed_forward.w1.weight": "consolidated-00008-of-00022.pth",
|
408 |
+
"layers.44.feed_forward.w3.weight": "consolidated-00008-of-00022.pth",
|
409 |
+
"layers.44.feed_forward.w2.weight": "consolidated-00008-of-00022.pth",
|
410 |
+
"layers.44.attention_norm.weight": "consolidated-00008-of-00022.pth",
|
411 |
+
"layers.44.ffn_norm.weight": "consolidated-00008-of-00022.pth",
|
412 |
+
"layers.45.attention.wq.weight": "consolidated-00008-of-00022.pth",
|
413 |
+
"layers.45.attention.wk.weight": "consolidated-00008-of-00022.pth",
|
414 |
+
"layers.45.attention.wv.weight": "consolidated-00008-of-00022.pth",
|
415 |
+
"layers.45.attention.wo.weight": "consolidated-00008-of-00022.pth",
|
416 |
+
"layers.45.feed_forward.w1.weight": "consolidated-00008-of-00022.pth",
|
417 |
+
"layers.45.feed_forward.w3.weight": "consolidated-00008-of-00022.pth",
|
418 |
+
"layers.45.feed_forward.w2.weight": "consolidated-00008-of-00022.pth",
|
419 |
+
"layers.45.attention_norm.weight": "consolidated-00008-of-00022.pth",
|
420 |
+
"layers.45.ffn_norm.weight": "consolidated-00008-of-00022.pth",
|
421 |
+
"layers.46.attention.wq.weight": "consolidated-00008-of-00022.pth",
|
422 |
+
"layers.46.attention.wk.weight": "consolidated-00008-of-00022.pth",
|
423 |
+
"layers.46.attention.wv.weight": "consolidated-00008-of-00022.pth",
|
424 |
+
"layers.46.attention.wo.weight": "consolidated-00008-of-00022.pth",
|
425 |
+
"layers.46.feed_forward.w1.weight": "consolidated-00008-of-00022.pth",
|
426 |
+
"layers.46.feed_forward.w3.weight": "consolidated-00008-of-00022.pth",
|
427 |
+
"layers.46.feed_forward.w2.weight": "consolidated-00008-of-00022.pth",
|
428 |
+
"layers.46.attention_norm.weight": "consolidated-00008-of-00022.pth",
|
429 |
+
"layers.46.ffn_norm.weight": "consolidated-00008-of-00022.pth",
|
430 |
+
"layers.47.attention.wq.weight": "consolidated-00008-of-00022.pth",
|
431 |
+
"layers.47.attention.wk.weight": "consolidated-00008-of-00022.pth",
|
432 |
+
"layers.47.attention.wv.weight": "consolidated-00008-of-00022.pth",
|
433 |
+
"layers.47.attention.wo.weight": "consolidated-00008-of-00022.pth",
|
434 |
+
"layers.47.feed_forward.w1.weight": "consolidated-00008-of-00022.pth",
|
435 |
+
"layers.47.feed_forward.w3.weight": "consolidated-00009-of-00022.pth",
|
436 |
+
"layers.47.feed_forward.w2.weight": "consolidated-00009-of-00022.pth",
|
437 |
+
"layers.47.attention_norm.weight": "consolidated-00009-of-00022.pth",
|
438 |
+
"layers.47.ffn_norm.weight": "consolidated-00009-of-00022.pth",
|
439 |
+
"layers.48.attention.wq.weight": "consolidated-00009-of-00022.pth",
|
440 |
+
"layers.48.attention.wk.weight": "consolidated-00009-of-00022.pth",
|
441 |
+
"layers.48.attention.wv.weight": "consolidated-00009-of-00022.pth",
|
442 |
+
"layers.48.attention.wo.weight": "consolidated-00009-of-00022.pth",
|
443 |
+
"layers.48.feed_forward.w1.weight": "consolidated-00009-of-00022.pth",
|
444 |
+
"layers.48.feed_forward.w3.weight": "consolidated-00009-of-00022.pth",
|
445 |
+
"layers.48.feed_forward.w2.weight": "consolidated-00009-of-00022.pth",
|
446 |
+
"layers.48.attention_norm.weight": "consolidated-00009-of-00022.pth",
|
447 |
+
"layers.48.ffn_norm.weight": "consolidated-00009-of-00022.pth",
|
448 |
+
"layers.49.attention.wq.weight": "consolidated-00009-of-00022.pth",
|
449 |
+
"layers.49.attention.wk.weight": "consolidated-00009-of-00022.pth",
|
450 |
+
"layers.49.attention.wv.weight": "consolidated-00009-of-00022.pth",
|
451 |
+
"layers.49.attention.wo.weight": "consolidated-00009-of-00022.pth",
|
452 |
+
"layers.49.feed_forward.w1.weight": "consolidated-00009-of-00022.pth",
|
453 |
+
"layers.49.feed_forward.w3.weight": "consolidated-00009-of-00022.pth",
|
454 |
+
"layers.49.feed_forward.w2.weight": "consolidated-00009-of-00022.pth",
|
455 |
+
"layers.49.attention_norm.weight": "consolidated-00009-of-00022.pth",
|
456 |
+
"layers.49.ffn_norm.weight": "consolidated-00009-of-00022.pth",
|
457 |
+
"layers.50.attention.wq.weight": "consolidated-00009-of-00022.pth",
|
458 |
+
"layers.50.attention.wk.weight": "consolidated-00009-of-00022.pth",
|
459 |
+
"layers.50.attention.wv.weight": "consolidated-00009-of-00022.pth",
|
460 |
+
"layers.50.attention.wo.weight": "consolidated-00009-of-00022.pth",
|
461 |
+
"layers.50.feed_forward.w1.weight": "consolidated-00009-of-00022.pth",
|
462 |
+
"layers.50.feed_forward.w3.weight": "consolidated-00009-of-00022.pth",
|
463 |
+
"layers.50.feed_forward.w2.weight": "consolidated-00009-of-00022.pth",
|
464 |
+
"layers.50.attention_norm.weight": "consolidated-00009-of-00022.pth",
|
465 |
+
"layers.50.ffn_norm.weight": "consolidated-00009-of-00022.pth",
|
466 |
+
"layers.51.attention.wq.weight": "consolidated-00009-of-00022.pth",
|
467 |
+
"layers.51.attention.wk.weight": "consolidated-00009-of-00022.pth",
|
468 |
+
"layers.51.attention.wv.weight": "consolidated-00009-of-00022.pth",
|
469 |
+
"layers.51.attention.wo.weight": "consolidated-00009-of-00022.pth",
|
470 |
+
"layers.51.feed_forward.w1.weight": "consolidated-00009-of-00022.pth",
|
471 |
+
"layers.51.feed_forward.w3.weight": "consolidated-00009-of-00022.pth",
|
472 |
+
"layers.51.feed_forward.w2.weight": "consolidated-00009-of-00022.pth",
|
473 |
+
"layers.51.attention_norm.weight": "consolidated-00009-of-00022.pth",
|
474 |
+
"layers.51.ffn_norm.weight": "consolidated-00009-of-00022.pth",
|
475 |
+
"layers.52.attention.wq.weight": "consolidated-00009-of-00022.pth",
|
476 |
+
"layers.52.attention.wk.weight": "consolidated-00009-of-00022.pth",
|
477 |
+
"layers.52.attention.wv.weight": "consolidated-00009-of-00022.pth",
|
478 |
+
"layers.52.attention.wo.weight": "consolidated-00009-of-00022.pth",
|
479 |
+
"layers.52.feed_forward.w1.weight": "consolidated-00009-of-00022.pth",
|
480 |
+
"layers.52.feed_forward.w3.weight": "consolidated-00009-of-00022.pth",
|
481 |
+
"layers.52.feed_forward.w2.weight": "consolidated-00009-of-00022.pth",
|
482 |
+
"layers.52.attention_norm.weight": "consolidated-00009-of-00022.pth",
|
483 |
+
"layers.52.ffn_norm.weight": "consolidated-00009-of-00022.pth",
|
484 |
+
"layers.53.attention.wq.weight": "consolidated-00009-of-00022.pth",
|
485 |
+
"layers.53.attention.wk.weight": "consolidated-00009-of-00022.pth",
|
486 |
+
"layers.53.attention.wv.weight": "consolidated-00009-of-00022.pth",
|
487 |
+
"layers.53.attention.wo.weight": "consolidated-00009-of-00022.pth",
|
488 |
+
"layers.53.feed_forward.w1.weight": "consolidated-00009-of-00022.pth",
|
489 |
+
"layers.53.feed_forward.w3.weight": "consolidated-00010-of-00022.pth",
|
490 |
+
"layers.53.feed_forward.w2.weight": "consolidated-00010-of-00022.pth",
|
491 |
+
"layers.53.attention_norm.weight": "consolidated-00010-of-00022.pth",
|
492 |
+
"layers.53.ffn_norm.weight": "consolidated-00010-of-00022.pth",
|
493 |
+
"layers.54.attention.wq.weight": "consolidated-00010-of-00022.pth",
|
494 |
+
"layers.54.attention.wk.weight": "consolidated-00010-of-00022.pth",
|
495 |
+
"layers.54.attention.wv.weight": "consolidated-00010-of-00022.pth",
|
496 |
+
"layers.54.attention.wo.weight": "consolidated-00010-of-00022.pth",
|
497 |
+
"layers.54.feed_forward.w1.weight": "consolidated-00010-of-00022.pth",
|
498 |
+
"layers.54.feed_forward.w3.weight": "consolidated-00010-of-00022.pth",
|
499 |
+
"layers.54.feed_forward.w2.weight": "consolidated-00010-of-00022.pth",
|
500 |
+
"layers.54.attention_norm.weight": "consolidated-00010-of-00022.pth",
|
501 |
+
"layers.54.ffn_norm.weight": "consolidated-00010-of-00022.pth",
|
502 |
+
"layers.55.attention.wq.weight": "consolidated-00010-of-00022.pth",
|
503 |
+
"layers.55.attention.wk.weight": "consolidated-00010-of-00022.pth",
|
504 |
+
"layers.55.attention.wv.weight": "consolidated-00010-of-00022.pth",
|
505 |
+
"layers.55.attention.wo.weight": "consolidated-00010-of-00022.pth",
|
506 |
+
"layers.55.feed_forward.w1.weight": "consolidated-00010-of-00022.pth",
|
507 |
+
"layers.55.feed_forward.w3.weight": "consolidated-00010-of-00022.pth",
|
508 |
+
"layers.55.feed_forward.w2.weight": "consolidated-00010-of-00022.pth",
|
509 |
+
"layers.55.attention_norm.weight": "consolidated-00010-of-00022.pth",
|
510 |
+
"layers.55.ffn_norm.weight": "consolidated-00010-of-00022.pth",
|
511 |
+
"layers.56.attention.wq.weight": "consolidated-00010-of-00022.pth",
|
512 |
+
"layers.56.attention.wk.weight": "consolidated-00010-of-00022.pth",
|
513 |
+
"layers.56.attention.wv.weight": "consolidated-00010-of-00022.pth",
|
514 |
+
"layers.56.attention.wo.weight": "consolidated-00010-of-00022.pth",
|
515 |
+
"layers.56.feed_forward.w1.weight": "consolidated-00010-of-00022.pth",
|
516 |
+
"layers.56.feed_forward.w3.weight": "consolidated-00010-of-00022.pth",
|
517 |
+
"layers.56.feed_forward.w2.weight": "consolidated-00010-of-00022.pth",
|
518 |
+
"layers.56.attention_norm.weight": "consolidated-00010-of-00022.pth",
|
519 |
+
"layers.56.ffn_norm.weight": "consolidated-00010-of-00022.pth",
|
520 |
+
"layers.57.attention.wq.weight": "consolidated-00010-of-00022.pth",
|
521 |
+
"layers.57.attention.wk.weight": "consolidated-00010-of-00022.pth",
|
522 |
+
"layers.57.attention.wv.weight": "consolidated-00010-of-00022.pth",
|
523 |
+
"layers.57.attention.wo.weight": "consolidated-00010-of-00022.pth",
|
524 |
+
"layers.57.feed_forward.w1.weight": "consolidated-00010-of-00022.pth",
|
525 |
+
"layers.57.feed_forward.w3.weight": "consolidated-00010-of-00022.pth",
|
526 |
+
"layers.57.feed_forward.w2.weight": "consolidated-00010-of-00022.pth",
|
527 |
+
"layers.57.attention_norm.weight": "consolidated-00010-of-00022.pth",
|
528 |
+
"layers.57.ffn_norm.weight": "consolidated-00010-of-00022.pth",
|
529 |
+
"layers.58.attention.wq.weight": "consolidated-00010-of-00022.pth",
|
530 |
+
"layers.58.attention.wk.weight": "consolidated-00010-of-00022.pth",
|
531 |
+
"layers.58.attention.wv.weight": "consolidated-00010-of-00022.pth",
|
532 |
+
"layers.58.attention.wo.weight": "consolidated-00010-of-00022.pth",
|
533 |
+
"layers.58.feed_forward.w1.weight": "consolidated-00010-of-00022.pth",
|
534 |
+
"layers.58.feed_forward.w3.weight": "consolidated-00010-of-00022.pth",
|
535 |
+
"layers.58.feed_forward.w2.weight": "consolidated-00010-of-00022.pth",
|
536 |
+
"layers.58.attention_norm.weight": "consolidated-00010-of-00022.pth",
|
537 |
+
"layers.58.ffn_norm.weight": "consolidated-00010-of-00022.pth",
|
538 |
+
"layers.59.attention.wq.weight": "consolidated-00010-of-00022.pth",
|
539 |
+
"layers.59.attention.wk.weight": "consolidated-00010-of-00022.pth",
|
540 |
+
"layers.59.attention.wv.weight": "consolidated-00010-of-00022.pth",
|
541 |
+
"layers.59.attention.wo.weight": "consolidated-00010-of-00022.pth",
|
542 |
+
"layers.59.feed_forward.w1.weight": "consolidated-00010-of-00022.pth",
|
543 |
+
"layers.59.feed_forward.w3.weight": "consolidated-00011-of-00022.pth",
|
544 |
+
"layers.59.feed_forward.w2.weight": "consolidated-00011-of-00022.pth",
|
545 |
+
"layers.59.attention_norm.weight": "consolidated-00011-of-00022.pth",
|
546 |
+
"layers.59.ffn_norm.weight": "consolidated-00011-of-00022.pth",
|
547 |
+
"layers.60.attention.wq.weight": "consolidated-00011-of-00022.pth",
|
548 |
+
"layers.60.attention.wk.weight": "consolidated-00011-of-00022.pth",
|
549 |
+
"layers.60.attention.wv.weight": "consolidated-00011-of-00022.pth",
|
550 |
+
"layers.60.attention.wo.weight": "consolidated-00011-of-00022.pth",
|
551 |
+
"layers.60.feed_forward.w1.weight": "consolidated-00011-of-00022.pth",
|
552 |
+
"layers.60.feed_forward.w3.weight": "consolidated-00011-of-00022.pth",
|
553 |
+
"layers.60.feed_forward.w2.weight": "consolidated-00011-of-00022.pth",
|
554 |
+
"layers.60.attention_norm.weight": "consolidated-00011-of-00022.pth",
|
555 |
+
"layers.60.ffn_norm.weight": "consolidated-00011-of-00022.pth",
|
556 |
+
"layers.61.attention.wq.weight": "consolidated-00011-of-00022.pth",
|
557 |
+
"layers.61.attention.wk.weight": "consolidated-00011-of-00022.pth",
|
558 |
+
"layers.61.attention.wv.weight": "consolidated-00011-of-00022.pth",
|
559 |
+
"layers.61.attention.wo.weight": "consolidated-00011-of-00022.pth",
|
560 |
+
"layers.61.feed_forward.w1.weight": "consolidated-00011-of-00022.pth",
|
561 |
+
"layers.61.feed_forward.w3.weight": "consolidated-00011-of-00022.pth",
|
562 |
+
"layers.61.feed_forward.w2.weight": "consolidated-00011-of-00022.pth",
|
563 |
+
"layers.61.attention_norm.weight": "consolidated-00011-of-00022.pth",
|
564 |
+
"layers.61.ffn_norm.weight": "consolidated-00011-of-00022.pth",
|
565 |
+
"layers.62.attention.wq.weight": "consolidated-00011-of-00022.pth",
|
566 |
+
"layers.62.attention.wk.weight": "consolidated-00011-of-00022.pth",
|
567 |
+
"layers.62.attention.wv.weight": "consolidated-00011-of-00022.pth",
|
568 |
+
"layers.62.attention.wo.weight": "consolidated-00011-of-00022.pth",
|
569 |
+
"layers.62.feed_forward.w1.weight": "consolidated-00011-of-00022.pth",
|
570 |
+
"layers.62.feed_forward.w3.weight": "consolidated-00011-of-00022.pth",
|
571 |
+
"layers.62.feed_forward.w2.weight": "consolidated-00011-of-00022.pth",
|
572 |
+
"layers.62.attention_norm.weight": "consolidated-00011-of-00022.pth",
|
573 |
+
"layers.62.ffn_norm.weight": "consolidated-00011-of-00022.pth",
|
574 |
+
"layers.63.attention.wq.weight": "consolidated-00011-of-00022.pth",
|
575 |
+
"layers.63.attention.wk.weight": "consolidated-00011-of-00022.pth",
|
576 |
+
"layers.63.attention.wv.weight": "consolidated-00011-of-00022.pth",
|
577 |
+
"layers.63.attention.wo.weight": "consolidated-00011-of-00022.pth",
|
578 |
+
"layers.63.feed_forward.w1.weight": "consolidated-00011-of-00022.pth",
|
579 |
+
"layers.63.feed_forward.w3.weight": "consolidated-00011-of-00022.pth",
|
580 |
+
"layers.63.feed_forward.w2.weight": "consolidated-00011-of-00022.pth",
|
581 |
+
"layers.63.attention_norm.weight": "consolidated-00011-of-00022.pth",
|
582 |
+
"layers.63.ffn_norm.weight": "consolidated-00011-of-00022.pth",
|
583 |
+
"layers.64.attention.wq.weight": "consolidated-00011-of-00022.pth",
|
584 |
+
"layers.64.attention.wk.weight": "consolidated-00011-of-00022.pth",
|
585 |
+
"layers.64.attention.wv.weight": "consolidated-00011-of-00022.pth",
|
586 |
+
"layers.64.attention.wo.weight": "consolidated-00011-of-00022.pth",
|
587 |
+
"layers.64.feed_forward.w1.weight": "consolidated-00011-of-00022.pth",
|
588 |
+
"layers.64.feed_forward.w3.weight": "consolidated-00011-of-00022.pth",
|
589 |
+
"layers.64.feed_forward.w2.weight": "consolidated-00011-of-00022.pth",
|
590 |
+
"layers.64.attention_norm.weight": "consolidated-00011-of-00022.pth",
|
591 |
+
"layers.64.ffn_norm.weight": "consolidated-00011-of-00022.pth",
|
592 |
+
"layers.65.attention.wq.weight": "consolidated-00011-of-00022.pth",
|
593 |
+
"layers.65.attention.wk.weight": "consolidated-00011-of-00022.pth",
|
594 |
+
"layers.65.attention.wv.weight": "consolidated-00011-of-00022.pth",
|
595 |
+
"layers.65.attention.wo.weight": "consolidated-00011-of-00022.pth",
|
596 |
+
"layers.65.feed_forward.w1.weight": "consolidated-00011-of-00022.pth",
|
597 |
+
"layers.65.feed_forward.w3.weight": "consolidated-00012-of-00022.pth",
|
598 |
+
"layers.65.feed_forward.w2.weight": "consolidated-00012-of-00022.pth",
|
599 |
+
"layers.65.attention_norm.weight": "consolidated-00012-of-00022.pth",
|
600 |
+
"layers.65.ffn_norm.weight": "consolidated-00012-of-00022.pth",
|
601 |
+
"layers.66.attention.wq.weight": "consolidated-00012-of-00022.pth",
|
602 |
+
"layers.66.attention.wk.weight": "consolidated-00012-of-00022.pth",
|
603 |
+
"layers.66.attention.wv.weight": "consolidated-00012-of-00022.pth",
|
604 |
+
"layers.66.attention.wo.weight": "consolidated-00012-of-00022.pth",
|
605 |
+
"layers.66.feed_forward.w1.weight": "consolidated-00012-of-00022.pth",
|
606 |
+
"layers.66.feed_forward.w3.weight": "consolidated-00012-of-00022.pth",
|
607 |
+
"layers.66.feed_forward.w2.weight": "consolidated-00012-of-00022.pth",
|
608 |
+
"layers.66.attention_norm.weight": "consolidated-00012-of-00022.pth",
|
609 |
+
"layers.66.ffn_norm.weight": "consolidated-00012-of-00022.pth",
|
610 |
+
"layers.67.attention.wq.weight": "consolidated-00012-of-00022.pth",
|
611 |
+
"layers.67.attention.wk.weight": "consolidated-00012-of-00022.pth",
|
612 |
+
"layers.67.attention.wv.weight": "consolidated-00012-of-00022.pth",
|
613 |
+
"layers.67.attention.wo.weight": "consolidated-00012-of-00022.pth",
|
614 |
+
"layers.67.feed_forward.w1.weight": "consolidated-00012-of-00022.pth",
|
615 |
+
"layers.67.feed_forward.w3.weight": "consolidated-00012-of-00022.pth",
|
616 |
+
"layers.67.feed_forward.w2.weight": "consolidated-00012-of-00022.pth",
|
617 |
+
"layers.67.attention_norm.weight": "consolidated-00012-of-00022.pth",
|
618 |
+
"layers.67.ffn_norm.weight": "consolidated-00012-of-00022.pth",
|
619 |
+
"layers.68.attention.wq.weight": "consolidated-00012-of-00022.pth",
|
620 |
+
"layers.68.attention.wk.weight": "consolidated-00012-of-00022.pth",
|
621 |
+
"layers.68.attention.wv.weight": "consolidated-00012-of-00022.pth",
|
622 |
+
"layers.68.attention.wo.weight": "consolidated-00012-of-00022.pth",
|
623 |
+
"layers.68.feed_forward.w1.weight": "consolidated-00012-of-00022.pth",
|
624 |
+
"layers.68.feed_forward.w3.weight": "consolidated-00012-of-00022.pth",
|
625 |
+
"layers.68.feed_forward.w2.weight": "consolidated-00012-of-00022.pth",
|
626 |
+
"layers.68.attention_norm.weight": "consolidated-00012-of-00022.pth",
|
627 |
+
"layers.68.ffn_norm.weight": "consolidated-00012-of-00022.pth",
|
628 |
+
"layers.69.attention.wq.weight": "consolidated-00012-of-00022.pth",
|
629 |
+
"layers.69.attention.wk.weight": "consolidated-00012-of-00022.pth",
|
630 |
+
"layers.69.attention.wv.weight": "consolidated-00012-of-00022.pth",
|
631 |
+
"layers.69.attention.wo.weight": "consolidated-00012-of-00022.pth",
|
632 |
+
"layers.69.feed_forward.w1.weight": "consolidated-00012-of-00022.pth",
|
633 |
+
"layers.69.feed_forward.w3.weight": "consolidated-00012-of-00022.pth",
|
634 |
+
"layers.69.feed_forward.w2.weight": "consolidated-00012-of-00022.pth",
|
635 |
+
"layers.69.attention_norm.weight": "consolidated-00012-of-00022.pth",
|
636 |
+
"layers.69.ffn_norm.weight": "consolidated-00012-of-00022.pth",
|
637 |
+
"layers.70.attention.wq.weight": "consolidated-00012-of-00022.pth",
|
638 |
+
"layers.70.attention.wk.weight": "consolidated-00012-of-00022.pth",
|
639 |
+
"layers.70.attention.wv.weight": "consolidated-00012-of-00022.pth",
|
640 |
+
"layers.70.attention.wo.weight": "consolidated-00012-of-00022.pth",
|
641 |
+
"layers.70.feed_forward.w1.weight": "consolidated-00012-of-00022.pth",
|
642 |
+
"layers.70.feed_forward.w3.weight": "consolidated-00012-of-00022.pth",
|
643 |
+
"layers.70.feed_forward.w2.weight": "consolidated-00012-of-00022.pth",
|
644 |
+
"layers.70.attention_norm.weight": "consolidated-00012-of-00022.pth",
|
645 |
+
"layers.70.ffn_norm.weight": "consolidated-00012-of-00022.pth",
|
646 |
+
"layers.71.attention.wq.weight": "consolidated-00012-of-00022.pth",
|
647 |
+
"layers.71.attention.wk.weight": "consolidated-00012-of-00022.pth",
|
648 |
+
"layers.71.attention.wv.weight": "consolidated-00012-of-00022.pth",
|
649 |
+
"layers.71.attention.wo.weight": "consolidated-00012-of-00022.pth",
|
650 |
+
"layers.71.feed_forward.w1.weight": "consolidated-00012-of-00022.pth",
|
651 |
+
"layers.71.feed_forward.w3.weight": "consolidated-00013-of-00022.pth",
|
652 |
+
"layers.71.feed_forward.w2.weight": "consolidated-00013-of-00022.pth",
|
653 |
+
"layers.71.attention_norm.weight": "consolidated-00013-of-00022.pth",
|
654 |
+
"layers.71.ffn_norm.weight": "consolidated-00013-of-00022.pth",
|
655 |
+
"layers.72.attention.wq.weight": "consolidated-00013-of-00022.pth",
|
656 |
+
"layers.72.attention.wk.weight": "consolidated-00013-of-00022.pth",
|
657 |
+
"layers.72.attention.wv.weight": "consolidated-00013-of-00022.pth",
|
658 |
+
"layers.72.attention.wo.weight": "consolidated-00013-of-00022.pth",
|
659 |
+
"layers.72.feed_forward.w1.weight": "consolidated-00013-of-00022.pth",
|
660 |
+
"layers.72.feed_forward.w3.weight": "consolidated-00013-of-00022.pth",
|
661 |
+
"layers.72.feed_forward.w2.weight": "consolidated-00013-of-00022.pth",
|
662 |
+
"layers.72.attention_norm.weight": "consolidated-00013-of-00022.pth",
|
663 |
+
"layers.72.ffn_norm.weight": "consolidated-00013-of-00022.pth",
|
664 |
+
"layers.73.attention.wq.weight": "consolidated-00013-of-00022.pth",
|
665 |
+
"layers.73.attention.wk.weight": "consolidated-00013-of-00022.pth",
|
666 |
+
"layers.73.attention.wv.weight": "consolidated-00013-of-00022.pth",
|
667 |
+
"layers.73.attention.wo.weight": "consolidated-00013-of-00022.pth",
|
668 |
+
"layers.73.feed_forward.w1.weight": "consolidated-00013-of-00022.pth",
|
669 |
+
"layers.73.feed_forward.w3.weight": "consolidated-00013-of-00022.pth",
|
670 |
+
"layers.73.feed_forward.w2.weight": "consolidated-00013-of-00022.pth",
|
671 |
+
"layers.73.attention_norm.weight": "consolidated-00013-of-00022.pth",
|
672 |
+
"layers.73.ffn_norm.weight": "consolidated-00013-of-00022.pth",
|
673 |
+
"layers.74.attention.wq.weight": "consolidated-00013-of-00022.pth",
|
674 |
+
"layers.74.attention.wk.weight": "consolidated-00013-of-00022.pth",
|
675 |
+
"layers.74.attention.wv.weight": "consolidated-00013-of-00022.pth",
|
676 |
+
"layers.74.attention.wo.weight": "consolidated-00013-of-00022.pth",
|
677 |
+
"layers.74.feed_forward.w1.weight": "consolidated-00013-of-00022.pth",
|
678 |
+
"layers.74.feed_forward.w3.weight": "consolidated-00013-of-00022.pth",
|
679 |
+
"layers.74.feed_forward.w2.weight": "consolidated-00013-of-00022.pth",
|
680 |
+
"layers.74.attention_norm.weight": "consolidated-00013-of-00022.pth",
|
681 |
+
"layers.74.ffn_norm.weight": "consolidated-00013-of-00022.pth",
|
682 |
+
"layers.75.attention.wq.weight": "consolidated-00013-of-00022.pth",
|
683 |
+
"layers.75.attention.wk.weight": "consolidated-00013-of-00022.pth",
|
684 |
+
"layers.75.attention.wv.weight": "consolidated-00013-of-00022.pth",
|
685 |
+
"layers.75.attention.wo.weight": "consolidated-00013-of-00022.pth",
|
686 |
+
"layers.75.feed_forward.w1.weight": "consolidated-00013-of-00022.pth",
|
687 |
+
"layers.75.feed_forward.w3.weight": "consolidated-00013-of-00022.pth",
|
688 |
+
"layers.75.feed_forward.w2.weight": "consolidated-00013-of-00022.pth",
|
689 |
+
"layers.75.attention_norm.weight": "consolidated-00013-of-00022.pth",
|
690 |
+
"layers.75.ffn_norm.weight": "consolidated-00013-of-00022.pth",
|
691 |
+
"layers.76.attention.wq.weight": "consolidated-00013-of-00022.pth",
|
692 |
+
"layers.76.attention.wk.weight": "consolidated-00013-of-00022.pth",
|
693 |
+
"layers.76.attention.wv.weight": "consolidated-00013-of-00022.pth",
|
694 |
+
"layers.76.attention.wo.weight": "consolidated-00013-of-00022.pth",
|
695 |
+
"layers.76.feed_forward.w1.weight": "consolidated-00013-of-00022.pth",
|
696 |
+
"layers.76.feed_forward.w3.weight": "consolidated-00013-of-00022.pth",
|
697 |
+
"layers.76.feed_forward.w2.weight": "consolidated-00013-of-00022.pth",
|
698 |
+
"layers.76.attention_norm.weight": "consolidated-00013-of-00022.pth",
|
699 |
+
"layers.76.ffn_norm.weight": "consolidated-00013-of-00022.pth",
|
700 |
+
"layers.77.attention.wq.weight": "consolidated-00013-of-00022.pth",
|
701 |
+
"layers.77.attention.wk.weight": "consolidated-00013-of-00022.pth",
|
702 |
+
"layers.77.attention.wv.weight": "consolidated-00013-of-00022.pth",
|
703 |
+
"layers.77.attention.wo.weight": "consolidated-00013-of-00022.pth",
|
704 |
+
"layers.77.feed_forward.w1.weight": "consolidated-00013-of-00022.pth",
|
705 |
+
"layers.77.feed_forward.w3.weight": "consolidated-00014-of-00022.pth",
|
706 |
+
"layers.77.feed_forward.w2.weight": "consolidated-00014-of-00022.pth",
|
707 |
+
"layers.77.attention_norm.weight": "consolidated-00014-of-00022.pth",
|
708 |
+
"layers.77.ffn_norm.weight": "consolidated-00014-of-00022.pth",
|
709 |
+
"layers.78.attention.wq.weight": "consolidated-00014-of-00022.pth",
|
710 |
+
"layers.78.attention.wk.weight": "consolidated-00014-of-00022.pth",
|
711 |
+
"layers.78.attention.wv.weight": "consolidated-00014-of-00022.pth",
|
712 |
+
"layers.78.attention.wo.weight": "consolidated-00014-of-00022.pth",
|
713 |
+
"layers.78.feed_forward.w1.weight": "consolidated-00014-of-00022.pth",
|
714 |
+
"layers.78.feed_forward.w3.weight": "consolidated-00014-of-00022.pth",
|
715 |
+
"layers.78.feed_forward.w2.weight": "consolidated-00014-of-00022.pth",
|
716 |
+
"layers.78.attention_norm.weight": "consolidated-00014-of-00022.pth",
|
717 |
+
"layers.78.ffn_norm.weight": "consolidated-00014-of-00022.pth",
|
718 |
+
"layers.79.attention.wq.weight": "consolidated-00014-of-00022.pth",
|
719 |
+
"layers.79.attention.wk.weight": "consolidated-00014-of-00022.pth",
|
720 |
+
"layers.79.attention.wv.weight": "consolidated-00014-of-00022.pth",
|
721 |
+
"layers.79.attention.wo.weight": "consolidated-00014-of-00022.pth",
|
722 |
+
"layers.79.feed_forward.w1.weight": "consolidated-00014-of-00022.pth",
|
723 |
+
"layers.79.feed_forward.w3.weight": "consolidated-00014-of-00022.pth",
|
724 |
+
"layers.79.feed_forward.w2.weight": "consolidated-00014-of-00022.pth",
|
725 |
+
"layers.79.attention_norm.weight": "consolidated-00014-of-00022.pth",
|
726 |
+
"layers.79.ffn_norm.weight": "consolidated-00014-of-00022.pth",
|
727 |
+
"layers.80.attention.wq.weight": "consolidated-00014-of-00022.pth",
|
728 |
+
"layers.80.attention.wk.weight": "consolidated-00014-of-00022.pth",
|
729 |
+
"layers.80.attention.wv.weight": "consolidated-00014-of-00022.pth",
|
730 |
+
"layers.80.attention.wo.weight": "consolidated-00014-of-00022.pth",
|
731 |
+
"layers.80.feed_forward.w1.weight": "consolidated-00014-of-00022.pth",
|
732 |
+
"layers.80.feed_forward.w3.weight": "consolidated-00014-of-00022.pth",
|
733 |
+
"layers.80.feed_forward.w2.weight": "consolidated-00014-of-00022.pth",
|
734 |
+
"layers.80.attention_norm.weight": "consolidated-00014-of-00022.pth",
|
735 |
+
"layers.80.ffn_norm.weight": "consolidated-00014-of-00022.pth",
|
736 |
+
"layers.81.attention.wq.weight": "consolidated-00014-of-00022.pth",
|
737 |
+
"layers.81.attention.wk.weight": "consolidated-00014-of-00022.pth",
|
738 |
+
"layers.81.attention.wv.weight": "consolidated-00014-of-00022.pth",
|
739 |
+
"layers.81.attention.wo.weight": "consolidated-00014-of-00022.pth",
|
740 |
+
"layers.81.feed_forward.w1.weight": "consolidated-00014-of-00022.pth",
|
741 |
+
"layers.81.feed_forward.w3.weight": "consolidated-00014-of-00022.pth",
|
742 |
+
"layers.81.feed_forward.w2.weight": "consolidated-00014-of-00022.pth",
|
743 |
+
"layers.81.attention_norm.weight": "consolidated-00014-of-00022.pth",
|
744 |
+
"layers.81.ffn_norm.weight": "consolidated-00014-of-00022.pth",
|
745 |
+
"layers.82.attention.wq.weight": "consolidated-00014-of-00022.pth",
|
746 |
+
"layers.82.attention.wk.weight": "consolidated-00014-of-00022.pth",
|
747 |
+
"layers.82.attention.wv.weight": "consolidated-00014-of-00022.pth",
|
748 |
+
"layers.82.attention.wo.weight": "consolidated-00014-of-00022.pth",
|
749 |
+
"layers.82.feed_forward.w1.weight": "consolidated-00014-of-00022.pth",
|
750 |
+
"layers.82.feed_forward.w3.weight": "consolidated-00014-of-00022.pth",
|
751 |
+
"layers.82.feed_forward.w2.weight": "consolidated-00014-of-00022.pth",
|
752 |
+
"layers.82.attention_norm.weight": "consolidated-00014-of-00022.pth",
|
753 |
+
"layers.82.ffn_norm.weight": "consolidated-00014-of-00022.pth",
|
754 |
+
"layers.83.attention.wq.weight": "consolidated-00014-of-00022.pth",
|
755 |
+
"layers.83.attention.wk.weight": "consolidated-00014-of-00022.pth",
|
756 |
+
"layers.83.attention.wv.weight": "consolidated-00014-of-00022.pth",
|
757 |
+
"layers.83.attention.wo.weight": "consolidated-00014-of-00022.pth",
|
758 |
+
"layers.83.feed_forward.w1.weight": "consolidated-00014-of-00022.pth",
|
759 |
+
"layers.83.feed_forward.w3.weight": "consolidated-00015-of-00022.pth",
|
760 |
+
"layers.83.feed_forward.w2.weight": "consolidated-00015-of-00022.pth",
|
761 |
+
"layers.83.attention_norm.weight": "consolidated-00015-of-00022.pth",
|
762 |
+
"layers.83.ffn_norm.weight": "consolidated-00015-of-00022.pth",
|
763 |
+
"layers.84.attention.wq.weight": "consolidated-00015-of-00022.pth",
|
764 |
+
"layers.84.attention.wk.weight": "consolidated-00015-of-00022.pth",
|
765 |
+
"layers.84.attention.wv.weight": "consolidated-00015-of-00022.pth",
|
766 |
+
"layers.84.attention.wo.weight": "consolidated-00015-of-00022.pth",
|
767 |
+
"layers.84.feed_forward.w1.weight": "consolidated-00015-of-00022.pth",
|
768 |
+
"layers.84.feed_forward.w3.weight": "consolidated-00015-of-00022.pth",
|
769 |
+
"layers.84.feed_forward.w2.weight": "consolidated-00015-of-00022.pth",
|
770 |
+
"layers.84.attention_norm.weight": "consolidated-00015-of-00022.pth",
|
771 |
+
"layers.84.ffn_norm.weight": "consolidated-00015-of-00022.pth",
|
772 |
+
"layers.85.attention.wq.weight": "consolidated-00015-of-00022.pth",
|
773 |
+
"layers.85.attention.wk.weight": "consolidated-00015-of-00022.pth",
|
774 |
+
"layers.85.attention.wv.weight": "consolidated-00015-of-00022.pth",
|
775 |
+
"layers.85.attention.wo.weight": "consolidated-00015-of-00022.pth",
|
776 |
+
"layers.85.feed_forward.w1.weight": "consolidated-00015-of-00022.pth",
|
777 |
+
"layers.85.feed_forward.w3.weight": "consolidated-00015-of-00022.pth",
|
778 |
+
"layers.85.feed_forward.w2.weight": "consolidated-00015-of-00022.pth",
|
779 |
+
"layers.85.attention_norm.weight": "consolidated-00015-of-00022.pth",
|
780 |
+
"layers.85.ffn_norm.weight": "consolidated-00015-of-00022.pth",
|
781 |
+
"layers.86.attention.wq.weight": "consolidated-00015-of-00022.pth",
|
782 |
+
"layers.86.attention.wk.weight": "consolidated-00015-of-00022.pth",
|
783 |
+
"layers.86.attention.wv.weight": "consolidated-00015-of-00022.pth",
|
784 |
+
"layers.86.attention.wo.weight": "consolidated-00015-of-00022.pth",
|
785 |
+
"layers.86.feed_forward.w1.weight": "consolidated-00015-of-00022.pth",
|
786 |
+
"layers.86.feed_forward.w3.weight": "consolidated-00015-of-00022.pth",
|
787 |
+
"layers.86.feed_forward.w2.weight": "consolidated-00015-of-00022.pth",
|
788 |
+
"layers.86.attention_norm.weight": "consolidated-00015-of-00022.pth",
|
789 |
+
"layers.86.ffn_norm.weight": "consolidated-00015-of-00022.pth",
|
790 |
+
"layers.87.attention.wq.weight": "consolidated-00015-of-00022.pth",
|
791 |
+
"layers.87.attention.wk.weight": "consolidated-00015-of-00022.pth",
|
792 |
+
"layers.87.attention.wv.weight": "consolidated-00015-of-00022.pth",
|
793 |
+
"layers.87.attention.wo.weight": "consolidated-00015-of-00022.pth",
|
794 |
+
"layers.87.feed_forward.w1.weight": "consolidated-00015-of-00022.pth",
|
795 |
+
"layers.87.feed_forward.w3.weight": "consolidated-00015-of-00022.pth",
|
796 |
+
"layers.87.feed_forward.w2.weight": "consolidated-00015-of-00022.pth",
|
797 |
+
"layers.87.attention_norm.weight": "consolidated-00015-of-00022.pth",
|
798 |
+
"layers.87.ffn_norm.weight": "consolidated-00015-of-00022.pth",
|
799 |
+
"layers.88.attention.wq.weight": "consolidated-00015-of-00022.pth",
|
800 |
+
"layers.88.attention.wk.weight": "consolidated-00015-of-00022.pth",
|
801 |
+
"layers.88.attention.wv.weight": "consolidated-00015-of-00022.pth",
|
802 |
+
"layers.88.attention.wo.weight": "consolidated-00015-of-00022.pth",
|
803 |
+
"layers.88.feed_forward.w1.weight": "consolidated-00015-of-00022.pth",
|
804 |
+
"layers.88.feed_forward.w3.weight": "consolidated-00015-of-00022.pth",
|
805 |
+
"layers.88.feed_forward.w2.weight": "consolidated-00015-of-00022.pth",
|
806 |
+
"layers.88.attention_norm.weight": "consolidated-00015-of-00022.pth",
|
807 |
+
"layers.88.ffn_norm.weight": "consolidated-00015-of-00022.pth",
|
808 |
+
"layers.89.attention.wq.weight": "consolidated-00015-of-00022.pth",
|
809 |
+
"layers.89.attention.wk.weight": "consolidated-00015-of-00022.pth",
|
810 |
+
"layers.89.attention.wv.weight": "consolidated-00015-of-00022.pth",
|
811 |
+
"layers.89.attention.wo.weight": "consolidated-00015-of-00022.pth",
|
812 |
+
"layers.89.feed_forward.w1.weight": "consolidated-00015-of-00022.pth",
|
813 |
+
"layers.89.feed_forward.w3.weight": "consolidated-00016-of-00022.pth",
|
814 |
+
"layers.89.feed_forward.w2.weight": "consolidated-00016-of-00022.pth",
|
815 |
+
"layers.89.attention_norm.weight": "consolidated-00016-of-00022.pth",
|
816 |
+
"layers.89.ffn_norm.weight": "consolidated-00016-of-00022.pth",
|
817 |
+
"layers.90.attention.wq.weight": "consolidated-00016-of-00022.pth",
|
818 |
+
"layers.90.attention.wk.weight": "consolidated-00016-of-00022.pth",
|
819 |
+
"layers.90.attention.wv.weight": "consolidated-00016-of-00022.pth",
|
820 |
+
"layers.90.attention.wo.weight": "consolidated-00016-of-00022.pth",
|
821 |
+
"layers.90.feed_forward.w1.weight": "consolidated-00016-of-00022.pth",
|
822 |
+
"layers.90.feed_forward.w3.weight": "consolidated-00016-of-00022.pth",
|
823 |
+
"layers.90.feed_forward.w2.weight": "consolidated-00016-of-00022.pth",
|
824 |
+
"layers.90.attention_norm.weight": "consolidated-00016-of-00022.pth",
|
825 |
+
"layers.90.ffn_norm.weight": "consolidated-00016-of-00022.pth",
|
826 |
+
"layers.91.attention.wq.weight": "consolidated-00016-of-00022.pth",
|
827 |
+
"layers.91.attention.wk.weight": "consolidated-00016-of-00022.pth",
|
828 |
+
"layers.91.attention.wv.weight": "consolidated-00016-of-00022.pth",
|
829 |
+
"layers.91.attention.wo.weight": "consolidated-00016-of-00022.pth",
|
830 |
+
"layers.91.feed_forward.w1.weight": "consolidated-00016-of-00022.pth",
|
831 |
+
"layers.91.feed_forward.w3.weight": "consolidated-00016-of-00022.pth",
|
832 |
+
"layers.91.feed_forward.w2.weight": "consolidated-00016-of-00022.pth",
|
833 |
+
"layers.91.attention_norm.weight": "consolidated-00016-of-00022.pth",
|
834 |
+
"layers.91.ffn_norm.weight": "consolidated-00016-of-00022.pth",
|
835 |
+
"layers.92.attention.wq.weight": "consolidated-00016-of-00022.pth",
|
836 |
+
"layers.92.attention.wk.weight": "consolidated-00016-of-00022.pth",
|
837 |
+
"layers.92.attention.wv.weight": "consolidated-00016-of-00022.pth",
|
838 |
+
"layers.92.attention.wo.weight": "consolidated-00016-of-00022.pth",
|
839 |
+
"layers.92.feed_forward.w1.weight": "consolidated-00016-of-00022.pth",
|
840 |
+
"layers.92.feed_forward.w3.weight": "consolidated-00016-of-00022.pth",
|
841 |
+
"layers.92.feed_forward.w2.weight": "consolidated-00016-of-00022.pth",
|
842 |
+
"layers.92.attention_norm.weight": "consolidated-00016-of-00022.pth",
|
843 |
+
"layers.92.ffn_norm.weight": "consolidated-00016-of-00022.pth",
|
844 |
+
"layers.93.attention.wq.weight": "consolidated-00016-of-00022.pth",
|
845 |
+
"layers.93.attention.wk.weight": "consolidated-00016-of-00022.pth",
|
846 |
+
"layers.93.attention.wv.weight": "consolidated-00016-of-00022.pth",
|
847 |
+
"layers.93.attention.wo.weight": "consolidated-00016-of-00022.pth",
|
848 |
+
"layers.93.feed_forward.w1.weight": "consolidated-00016-of-00022.pth",
|
849 |
+
"layers.93.feed_forward.w3.weight": "consolidated-00016-of-00022.pth",
|
850 |
+
"layers.93.feed_forward.w2.weight": "consolidated-00016-of-00022.pth",
|
851 |
+
"layers.93.attention_norm.weight": "consolidated-00016-of-00022.pth",
|
852 |
+
"layers.93.ffn_norm.weight": "consolidated-00016-of-00022.pth",
|
853 |
+
"layers.94.attention.wq.weight": "consolidated-00016-of-00022.pth",
|
854 |
+
"layers.94.attention.wk.weight": "consolidated-00016-of-00022.pth",
|
855 |
+
"layers.94.attention.wv.weight": "consolidated-00016-of-00022.pth",
|
856 |
+
"layers.94.attention.wo.weight": "consolidated-00016-of-00022.pth",
|
857 |
+
"layers.94.feed_forward.w1.weight": "consolidated-00016-of-00022.pth",
|
858 |
+
"layers.94.feed_forward.w3.weight": "consolidated-00016-of-00022.pth",
|
859 |
+
"layers.94.feed_forward.w2.weight": "consolidated-00016-of-00022.pth",
|
860 |
+
"layers.94.attention_norm.weight": "consolidated-00016-of-00022.pth",
|
861 |
+
"layers.94.ffn_norm.weight": "consolidated-00016-of-00022.pth",
|
862 |
+
"layers.95.attention.wq.weight": "consolidated-00016-of-00022.pth",
|
863 |
+
"layers.95.attention.wk.weight": "consolidated-00016-of-00022.pth",
|
864 |
+
"layers.95.attention.wv.weight": "consolidated-00016-of-00022.pth",
|
865 |
+
"layers.95.attention.wo.weight": "consolidated-00016-of-00022.pth",
|
866 |
+
"layers.95.feed_forward.w1.weight": "consolidated-00016-of-00022.pth",
|
867 |
+
"layers.95.feed_forward.w3.weight": "consolidated-00017-of-00022.pth",
|
868 |
+
"layers.95.feed_forward.w2.weight": "consolidated-00017-of-00022.pth",
|
869 |
+
"layers.95.attention_norm.weight": "consolidated-00017-of-00022.pth",
|
870 |
+
"layers.95.ffn_norm.weight": "consolidated-00017-of-00022.pth",
|
871 |
+
"layers.96.attention.wq.weight": "consolidated-00017-of-00022.pth",
|
872 |
+
"layers.96.attention.wk.weight": "consolidated-00017-of-00022.pth",
|
873 |
+
"layers.96.attention.wv.weight": "consolidated-00017-of-00022.pth",
|
874 |
+
"layers.96.attention.wo.weight": "consolidated-00017-of-00022.pth",
|
875 |
+
"layers.96.feed_forward.w1.weight": "consolidated-00017-of-00022.pth",
|
876 |
+
"layers.96.feed_forward.w3.weight": "consolidated-00017-of-00022.pth",
|
877 |
+
"layers.96.feed_forward.w2.weight": "consolidated-00017-of-00022.pth",
|
878 |
+
"layers.96.attention_norm.weight": "consolidated-00017-of-00022.pth",
|
879 |
+
"layers.96.ffn_norm.weight": "consolidated-00017-of-00022.pth",
|
880 |
+
"layers.97.attention.wq.weight": "consolidated-00017-of-00022.pth",
|
881 |
+
"layers.97.attention.wk.weight": "consolidated-00017-of-00022.pth",
|
882 |
+
"layers.97.attention.wv.weight": "consolidated-00017-of-00022.pth",
|
883 |
+
"layers.97.attention.wo.weight": "consolidated-00017-of-00022.pth",
|
884 |
+
"layers.97.feed_forward.w1.weight": "consolidated-00017-of-00022.pth",
|
885 |
+
"layers.97.feed_forward.w3.weight": "consolidated-00017-of-00022.pth",
|
886 |
+
"layers.97.feed_forward.w2.weight": "consolidated-00017-of-00022.pth",
|
887 |
+
"layers.97.attention_norm.weight": "consolidated-00017-of-00022.pth",
|
888 |
+
"layers.97.ffn_norm.weight": "consolidated-00017-of-00022.pth",
|
889 |
+
"layers.98.attention.wq.weight": "consolidated-00017-of-00022.pth",
|
890 |
+
"layers.98.attention.wk.weight": "consolidated-00017-of-00022.pth",
|
891 |
+
"layers.98.attention.wv.weight": "consolidated-00017-of-00022.pth",
|
892 |
+
"layers.98.attention.wo.weight": "consolidated-00017-of-00022.pth",
|
893 |
+
"layers.98.feed_forward.w1.weight": "consolidated-00017-of-00022.pth",
|
894 |
+
"layers.98.feed_forward.w3.weight": "consolidated-00017-of-00022.pth",
|
895 |
+
"layers.98.feed_forward.w2.weight": "consolidated-00017-of-00022.pth",
|
896 |
+
"layers.98.attention_norm.weight": "consolidated-00017-of-00022.pth",
|
897 |
+
"layers.98.ffn_norm.weight": "consolidated-00017-of-00022.pth",
|
898 |
+
"layers.99.attention.wq.weight": "consolidated-00017-of-00022.pth",
|
899 |
+
"layers.99.attention.wk.weight": "consolidated-00017-of-00022.pth",
|
900 |
+
"layers.99.attention.wv.weight": "consolidated-00017-of-00022.pth",
|
901 |
+
"layers.99.attention.wo.weight": "consolidated-00017-of-00022.pth",
|
902 |
+
"layers.99.feed_forward.w1.weight": "consolidated-00017-of-00022.pth",
|
903 |
+
"layers.99.feed_forward.w3.weight": "consolidated-00017-of-00022.pth",
|
904 |
+
"layers.99.feed_forward.w2.weight": "consolidated-00017-of-00022.pth",
|
905 |
+
"layers.99.attention_norm.weight": "consolidated-00017-of-00022.pth",
|
906 |
+
"layers.99.ffn_norm.weight": "consolidated-00017-of-00022.pth",
|
907 |
+
"layers.100.attention.wq.weight": "consolidated-00017-of-00022.pth",
|
908 |
+
"layers.100.attention.wk.weight": "consolidated-00017-of-00022.pth",
|
909 |
+
"layers.100.attention.wv.weight": "consolidated-00017-of-00022.pth",
|
910 |
+
"layers.100.attention.wo.weight": "consolidated-00017-of-00022.pth",
|
911 |
+
"layers.100.feed_forward.w1.weight": "consolidated-00017-of-00022.pth",
|
912 |
+
"layers.100.feed_forward.w3.weight": "consolidated-00017-of-00022.pth",
|
913 |
+
"layers.100.feed_forward.w2.weight": "consolidated-00017-of-00022.pth",
|
914 |
+
"layers.100.attention_norm.weight": "consolidated-00017-of-00022.pth",
|
915 |
+
"layers.100.ffn_norm.weight": "consolidated-00017-of-00022.pth",
|
916 |
+
"layers.101.attention.wq.weight": "consolidated-00017-of-00022.pth",
|
917 |
+
"layers.101.attention.wk.weight": "consolidated-00017-of-00022.pth",
|
918 |
+
"layers.101.attention.wv.weight": "consolidated-00017-of-00022.pth",
|
919 |
+
"layers.101.attention.wo.weight": "consolidated-00017-of-00022.pth",
|
920 |
+
"layers.101.feed_forward.w1.weight": "consolidated-00017-of-00022.pth",
|
921 |
+
"layers.101.feed_forward.w3.weight": "consolidated-00018-of-00022.pth",
|
922 |
+
"layers.101.feed_forward.w2.weight": "consolidated-00018-of-00022.pth",
|
923 |
+
"layers.101.attention_norm.weight": "consolidated-00018-of-00022.pth",
|
924 |
+
"layers.101.ffn_norm.weight": "consolidated-00018-of-00022.pth",
|
925 |
+
"layers.102.attention.wq.weight": "consolidated-00018-of-00022.pth",
|
926 |
+
"layers.102.attention.wk.weight": "consolidated-00018-of-00022.pth",
|
927 |
+
"layers.102.attention.wv.weight": "consolidated-00018-of-00022.pth",
|
928 |
+
"layers.102.attention.wo.weight": "consolidated-00018-of-00022.pth",
|
929 |
+
"layers.102.feed_forward.w1.weight": "consolidated-00018-of-00022.pth",
|
930 |
+
"layers.102.feed_forward.w3.weight": "consolidated-00018-of-00022.pth",
|
931 |
+
"layers.102.feed_forward.w2.weight": "consolidated-00018-of-00022.pth",
|
932 |
+
"layers.102.attention_norm.weight": "consolidated-00018-of-00022.pth",
|
933 |
+
"layers.102.ffn_norm.weight": "consolidated-00018-of-00022.pth",
|
934 |
+
"layers.103.attention.wq.weight": "consolidated-00018-of-00022.pth",
|
935 |
+
"layers.103.attention.wk.weight": "consolidated-00018-of-00022.pth",
|
936 |
+
"layers.103.attention.wv.weight": "consolidated-00018-of-00022.pth",
|
937 |
+
"layers.103.attention.wo.weight": "consolidated-00018-of-00022.pth",
|
938 |
+
"layers.103.feed_forward.w1.weight": "consolidated-00018-of-00022.pth",
|
939 |
+
"layers.103.feed_forward.w3.weight": "consolidated-00018-of-00022.pth",
|
940 |
+
"layers.103.feed_forward.w2.weight": "consolidated-00018-of-00022.pth",
|
941 |
+
"layers.103.attention_norm.weight": "consolidated-00018-of-00022.pth",
|
942 |
+
"layers.103.ffn_norm.weight": "consolidated-00018-of-00022.pth",
|
943 |
+
"layers.104.attention.wq.weight": "consolidated-00018-of-00022.pth",
|
944 |
+
"layers.104.attention.wk.weight": "consolidated-00018-of-00022.pth",
|
945 |
+
"layers.104.attention.wv.weight": "consolidated-00018-of-00022.pth",
|
946 |
+
"layers.104.attention.wo.weight": "consolidated-00018-of-00022.pth",
|
947 |
+
"layers.104.feed_forward.w1.weight": "consolidated-00018-of-00022.pth",
|
948 |
+
"layers.104.feed_forward.w3.weight": "consolidated-00018-of-00022.pth",
|
949 |
+
"layers.104.feed_forward.w2.weight": "consolidated-00018-of-00022.pth",
|
950 |
+
"layers.104.attention_norm.weight": "consolidated-00018-of-00022.pth",
|
951 |
+
"layers.104.ffn_norm.weight": "consolidated-00018-of-00022.pth",
|
952 |
+
"layers.105.attention.wq.weight": "consolidated-00018-of-00022.pth",
|
953 |
+
"layers.105.attention.wk.weight": "consolidated-00018-of-00022.pth",
|
954 |
+
"layers.105.attention.wv.weight": "consolidated-00018-of-00022.pth",
|
955 |
+
"layers.105.attention.wo.weight": "consolidated-00018-of-00022.pth",
|
956 |
+
"layers.105.feed_forward.w1.weight": "consolidated-00018-of-00022.pth",
|
957 |
+
"layers.105.feed_forward.w3.weight": "consolidated-00018-of-00022.pth",
|
958 |
+
"layers.105.feed_forward.w2.weight": "consolidated-00018-of-00022.pth",
|
959 |
+
"layers.105.attention_norm.weight": "consolidated-00018-of-00022.pth",
|
960 |
+
"layers.105.ffn_norm.weight": "consolidated-00018-of-00022.pth",
|
961 |
+
"layers.106.attention.wq.weight": "consolidated-00018-of-00022.pth",
|
962 |
+
"layers.106.attention.wk.weight": "consolidated-00018-of-00022.pth",
|
963 |
+
"layers.106.attention.wv.weight": "consolidated-00018-of-00022.pth",
|
964 |
+
"layers.106.attention.wo.weight": "consolidated-00018-of-00022.pth",
|
965 |
+
"layers.106.feed_forward.w1.weight": "consolidated-00018-of-00022.pth",
|
966 |
+
"layers.106.feed_forward.w3.weight": "consolidated-00018-of-00022.pth",
|
967 |
+
"layers.106.feed_forward.w2.weight": "consolidated-00018-of-00022.pth",
|
968 |
+
"layers.106.attention_norm.weight": "consolidated-00018-of-00022.pth",
|
969 |
+
"layers.106.ffn_norm.weight": "consolidated-00018-of-00022.pth",
|
970 |
+
"layers.107.attention.wq.weight": "consolidated-00018-of-00022.pth",
|
971 |
+
"layers.107.attention.wk.weight": "consolidated-00018-of-00022.pth",
|
972 |
+
"layers.107.attention.wv.weight": "consolidated-00018-of-00022.pth",
|
973 |
+
"layers.107.attention.wo.weight": "consolidated-00018-of-00022.pth",
|
974 |
+
"layers.107.feed_forward.w1.weight": "consolidated-00018-of-00022.pth",
|
975 |
+
"layers.107.feed_forward.w3.weight": "consolidated-00019-of-00022.pth",
|
976 |
+
"layers.107.feed_forward.w2.weight": "consolidated-00019-of-00022.pth",
|
977 |
+
"layers.107.attention_norm.weight": "consolidated-00019-of-00022.pth",
|
978 |
+
"layers.107.ffn_norm.weight": "consolidated-00019-of-00022.pth",
|
979 |
+
"layers.108.attention.wq.weight": "consolidated-00019-of-00022.pth",
|
980 |
+
"layers.108.attention.wk.weight": "consolidated-00019-of-00022.pth",
|
981 |
+
"layers.108.attention.wv.weight": "consolidated-00019-of-00022.pth",
|
982 |
+
"layers.108.attention.wo.weight": "consolidated-00019-of-00022.pth",
|
983 |
+
"layers.108.feed_forward.w1.weight": "consolidated-00019-of-00022.pth",
|
984 |
+
"layers.108.feed_forward.w3.weight": "consolidated-00019-of-00022.pth",
|
985 |
+
"layers.108.feed_forward.w2.weight": "consolidated-00019-of-00022.pth",
|
986 |
+
"layers.108.attention_norm.weight": "consolidated-00019-of-00022.pth",
|
987 |
+
"layers.108.ffn_norm.weight": "consolidated-00019-of-00022.pth",
|
988 |
+
"layers.109.attention.wq.weight": "consolidated-00019-of-00022.pth",
|
989 |
+
"layers.109.attention.wk.weight": "consolidated-00019-of-00022.pth",
|
990 |
+
"layers.109.attention.wv.weight": "consolidated-00019-of-00022.pth",
|
991 |
+
"layers.109.attention.wo.weight": "consolidated-00019-of-00022.pth",
|
992 |
+
"layers.109.feed_forward.w1.weight": "consolidated-00019-of-00022.pth",
|
993 |
+
"layers.109.feed_forward.w3.weight": "consolidated-00019-of-00022.pth",
|
994 |
+
"layers.109.feed_forward.w2.weight": "consolidated-00019-of-00022.pth",
|
995 |
+
"layers.109.attention_norm.weight": "consolidated-00019-of-00022.pth",
|
996 |
+
"layers.109.ffn_norm.weight": "consolidated-00019-of-00022.pth",
|
997 |
+
"layers.110.attention.wq.weight": "consolidated-00019-of-00022.pth",
|
998 |
+
"layers.110.attention.wk.weight": "consolidated-00019-of-00022.pth",
|
999 |
+
"layers.110.attention.wv.weight": "consolidated-00019-of-00022.pth",
|
1000 |
+
"layers.110.attention.wo.weight": "consolidated-00019-of-00022.pth",
|
1001 |
+
"layers.110.feed_forward.w1.weight": "consolidated-00019-of-00022.pth",
|
1002 |
+
"layers.110.feed_forward.w3.weight": "consolidated-00019-of-00022.pth",
|
1003 |
+
"layers.110.feed_forward.w2.weight": "consolidated-00019-of-00022.pth",
|
1004 |
+
"layers.110.attention_norm.weight": "consolidated-00019-of-00022.pth",
|
1005 |
+
"layers.110.ffn_norm.weight": "consolidated-00019-of-00022.pth",
|
1006 |
+
"layers.111.attention.wq.weight": "consolidated-00019-of-00022.pth",
|
1007 |
+
"layers.111.attention.wk.weight": "consolidated-00019-of-00022.pth",
|
1008 |
+
"layers.111.attention.wv.weight": "consolidated-00019-of-00022.pth",
|
1009 |
+
"layers.111.attention.wo.weight": "consolidated-00019-of-00022.pth",
|
1010 |
+
"layers.111.feed_forward.w1.weight": "consolidated-00019-of-00022.pth",
|
1011 |
+
"layers.111.feed_forward.w3.weight": "consolidated-00019-of-00022.pth",
|
1012 |
+
"layers.111.feed_forward.w2.weight": "consolidated-00019-of-00022.pth",
|
1013 |
+
"layers.111.attention_norm.weight": "consolidated-00019-of-00022.pth",
|
1014 |
+
"layers.111.ffn_norm.weight": "consolidated-00019-of-00022.pth",
|
1015 |
+
"layers.112.attention.wq.weight": "consolidated-00019-of-00022.pth",
|
1016 |
+
"layers.112.attention.wk.weight": "consolidated-00019-of-00022.pth",
|
1017 |
+
"layers.112.attention.wv.weight": "consolidated-00019-of-00022.pth",
|
1018 |
+
"layers.112.attention.wo.weight": "consolidated-00019-of-00022.pth",
|
1019 |
+
"layers.112.feed_forward.w1.weight": "consolidated-00019-of-00022.pth",
|
1020 |
+
"layers.112.feed_forward.w3.weight": "consolidated-00019-of-00022.pth",
|
1021 |
+
"layers.112.feed_forward.w2.weight": "consolidated-00019-of-00022.pth",
|
1022 |
+
"layers.112.attention_norm.weight": "consolidated-00019-of-00022.pth",
|
1023 |
+
"layers.112.ffn_norm.weight": "consolidated-00019-of-00022.pth",
|
1024 |
+
"layers.113.attention.wq.weight": "consolidated-00019-of-00022.pth",
|
1025 |
+
"layers.113.attention.wk.weight": "consolidated-00019-of-00022.pth",
|
1026 |
+
"layers.113.attention.wv.weight": "consolidated-00019-of-00022.pth",
|
1027 |
+
"layers.113.attention.wo.weight": "consolidated-00019-of-00022.pth",
|
1028 |
+
"layers.113.feed_forward.w1.weight": "consolidated-00019-of-00022.pth",
|
1029 |
+
"layers.113.feed_forward.w3.weight": "consolidated-00020-of-00022.pth",
|
1030 |
+
"layers.113.feed_forward.w2.weight": "consolidated-00020-of-00022.pth",
|
1031 |
+
"layers.113.attention_norm.weight": "consolidated-00020-of-00022.pth",
|
1032 |
+
"layers.113.ffn_norm.weight": "consolidated-00020-of-00022.pth",
|
1033 |
+
"layers.114.attention.wq.weight": "consolidated-00020-of-00022.pth",
|
1034 |
+
"layers.114.attention.wk.weight": "consolidated-00020-of-00022.pth",
|
1035 |
+
"layers.114.attention.wv.weight": "consolidated-00020-of-00022.pth",
|
1036 |
+
"layers.114.attention.wo.weight": "consolidated-00020-of-00022.pth",
|
1037 |
+
"layers.114.feed_forward.w1.weight": "consolidated-00020-of-00022.pth",
|
1038 |
+
"layers.114.feed_forward.w3.weight": "consolidated-00020-of-00022.pth",
|
1039 |
+
"layers.114.feed_forward.w2.weight": "consolidated-00020-of-00022.pth",
|
1040 |
+
"layers.114.attention_norm.weight": "consolidated-00020-of-00022.pth",
|
1041 |
+
"layers.114.ffn_norm.weight": "consolidated-00020-of-00022.pth",
|
1042 |
+
"layers.115.attention.wq.weight": "consolidated-00020-of-00022.pth",
|
1043 |
+
"layers.115.attention.wk.weight": "consolidated-00020-of-00022.pth",
|
1044 |
+
"layers.115.attention.wv.weight": "consolidated-00020-of-00022.pth",
|
1045 |
+
"layers.115.attention.wo.weight": "consolidated-00020-of-00022.pth",
|
1046 |
+
"layers.115.feed_forward.w1.weight": "consolidated-00020-of-00022.pth",
|
1047 |
+
"layers.115.feed_forward.w3.weight": "consolidated-00020-of-00022.pth",
|
1048 |
+
"layers.115.feed_forward.w2.weight": "consolidated-00020-of-00022.pth",
|
1049 |
+
"layers.115.attention_norm.weight": "consolidated-00020-of-00022.pth",
|
1050 |
+
"layers.115.ffn_norm.weight": "consolidated-00020-of-00022.pth",
|
1051 |
+
"layers.116.attention.wq.weight": "consolidated-00020-of-00022.pth",
|
1052 |
+
"layers.116.attention.wk.weight": "consolidated-00020-of-00022.pth",
|
1053 |
+
"layers.116.attention.wv.weight": "consolidated-00020-of-00022.pth",
|
1054 |
+
"layers.116.attention.wo.weight": "consolidated-00020-of-00022.pth",
|
1055 |
+
"layers.116.feed_forward.w1.weight": "consolidated-00020-of-00022.pth",
|
1056 |
+
"layers.116.feed_forward.w3.weight": "consolidated-00020-of-00022.pth",
|
1057 |
+
"layers.116.feed_forward.w2.weight": "consolidated-00020-of-00022.pth",
|
1058 |
+
"layers.116.attention_norm.weight": "consolidated-00020-of-00022.pth",
|
1059 |
+
"layers.116.ffn_norm.weight": "consolidated-00020-of-00022.pth",
|
1060 |
+
"layers.117.attention.wq.weight": "consolidated-00020-of-00022.pth",
|
1061 |
+
"layers.117.attention.wk.weight": "consolidated-00020-of-00022.pth",
|
1062 |
+
"layers.117.attention.wv.weight": "consolidated-00020-of-00022.pth",
|
1063 |
+
"layers.117.attention.wo.weight": "consolidated-00020-of-00022.pth",
|
1064 |
+
"layers.117.feed_forward.w1.weight": "consolidated-00020-of-00022.pth",
|
1065 |
+
"layers.117.feed_forward.w3.weight": "consolidated-00020-of-00022.pth",
|
1066 |
+
"layers.117.feed_forward.w2.weight": "consolidated-00020-of-00022.pth",
|
1067 |
+
"layers.117.attention_norm.weight": "consolidated-00020-of-00022.pth",
|
1068 |
+
"layers.117.ffn_norm.weight": "consolidated-00020-of-00022.pth",
|
1069 |
+
"layers.118.attention.wq.weight": "consolidated-00020-of-00022.pth",
|
1070 |
+
"layers.118.attention.wk.weight": "consolidated-00020-of-00022.pth",
|
1071 |
+
"layers.118.attention.wv.weight": "consolidated-00020-of-00022.pth",
|
1072 |
+
"layers.118.attention.wo.weight": "consolidated-00020-of-00022.pth",
|
1073 |
+
"layers.118.feed_forward.w1.weight": "consolidated-00020-of-00022.pth",
|
1074 |
+
"layers.118.feed_forward.w3.weight": "consolidated-00020-of-00022.pth",
|
1075 |
+
"layers.118.feed_forward.w2.weight": "consolidated-00020-of-00022.pth",
|
1076 |
+
"layers.118.attention_norm.weight": "consolidated-00020-of-00022.pth",
|
1077 |
+
"layers.118.ffn_norm.weight": "consolidated-00020-of-00022.pth",
|
1078 |
+
"layers.119.attention.wq.weight": "consolidated-00020-of-00022.pth",
|
1079 |
+
"layers.119.attention.wk.weight": "consolidated-00020-of-00022.pth",
|
1080 |
+
"layers.119.attention.wv.weight": "consolidated-00020-of-00022.pth",
|
1081 |
+
"layers.119.attention.wo.weight": "consolidated-00020-of-00022.pth",
|
1082 |
+
"layers.119.feed_forward.w1.weight": "consolidated-00020-of-00022.pth",
|
1083 |
+
"layers.119.feed_forward.w3.weight": "consolidated-00021-of-00022.pth",
|
1084 |
+
"layers.119.feed_forward.w2.weight": "consolidated-00021-of-00022.pth",
|
1085 |
+
"layers.119.attention_norm.weight": "consolidated-00021-of-00022.pth",
|
1086 |
+
"layers.119.ffn_norm.weight": "consolidated-00021-of-00022.pth",
|
1087 |
+
"layers.120.attention.wq.weight": "consolidated-00021-of-00022.pth",
|
1088 |
+
"layers.120.attention.wk.weight": "consolidated-00021-of-00022.pth",
|
1089 |
+
"layers.120.attention.wv.weight": "consolidated-00021-of-00022.pth",
|
1090 |
+
"layers.120.attention.wo.weight": "consolidated-00021-of-00022.pth",
|
1091 |
+
"layers.120.feed_forward.w1.weight": "consolidated-00021-of-00022.pth",
|
1092 |
+
"layers.120.feed_forward.w3.weight": "consolidated-00021-of-00022.pth",
|
1093 |
+
"layers.120.feed_forward.w2.weight": "consolidated-00021-of-00022.pth",
|
1094 |
+
"layers.120.attention_norm.weight": "consolidated-00021-of-00022.pth",
|
1095 |
+
"layers.120.ffn_norm.weight": "consolidated-00021-of-00022.pth",
|
1096 |
+
"layers.121.attention.wq.weight": "consolidated-00021-of-00022.pth",
|
1097 |
+
"layers.121.attention.wk.weight": "consolidated-00021-of-00022.pth",
|
1098 |
+
"layers.121.attention.wv.weight": "consolidated-00021-of-00022.pth",
|
1099 |
+
"layers.121.attention.wo.weight": "consolidated-00021-of-00022.pth",
|
1100 |
+
"layers.121.feed_forward.w1.weight": "consolidated-00021-of-00022.pth",
|
1101 |
+
"layers.121.feed_forward.w3.weight": "consolidated-00021-of-00022.pth",
|
1102 |
+
"layers.121.feed_forward.w2.weight": "consolidated-00021-of-00022.pth",
|
1103 |
+
"layers.121.attention_norm.weight": "consolidated-00021-of-00022.pth",
|
1104 |
+
"layers.121.ffn_norm.weight": "consolidated-00021-of-00022.pth",
|
1105 |
+
"layers.122.attention.wq.weight": "consolidated-00021-of-00022.pth",
|
1106 |
+
"layers.122.attention.wk.weight": "consolidated-00021-of-00022.pth",
|
1107 |
+
"layers.122.attention.wv.weight": "consolidated-00021-of-00022.pth",
|
1108 |
+
"layers.122.attention.wo.weight": "consolidated-00021-of-00022.pth",
|
1109 |
+
"layers.122.feed_forward.w1.weight": "consolidated-00021-of-00022.pth",
|
1110 |
+
"layers.122.feed_forward.w3.weight": "consolidated-00021-of-00022.pth",
|
1111 |
+
"layers.122.feed_forward.w2.weight": "consolidated-00021-of-00022.pth",
|
1112 |
+
"layers.122.attention_norm.weight": "consolidated-00021-of-00022.pth",
|
1113 |
+
"layers.122.ffn_norm.weight": "consolidated-00021-of-00022.pth",
|
1114 |
+
"layers.123.attention.wq.weight": "consolidated-00021-of-00022.pth",
|
1115 |
+
"layers.123.attention.wk.weight": "consolidated-00021-of-00022.pth",
|
1116 |
+
"layers.123.attention.wv.weight": "consolidated-00021-of-00022.pth",
|
1117 |
+
"layers.123.attention.wo.weight": "consolidated-00021-of-00022.pth",
|
1118 |
+
"layers.123.feed_forward.w1.weight": "consolidated-00021-of-00022.pth",
|
1119 |
+
"layers.123.feed_forward.w3.weight": "consolidated-00021-of-00022.pth",
|
1120 |
+
"layers.123.feed_forward.w2.weight": "consolidated-00021-of-00022.pth",
|
1121 |
+
"layers.123.attention_norm.weight": "consolidated-00021-of-00022.pth",
|
1122 |
+
"layers.123.ffn_norm.weight": "consolidated-00021-of-00022.pth",
|
1123 |
+
"layers.124.attention.wq.weight": "consolidated-00021-of-00022.pth",
|
1124 |
+
"layers.124.attention.wk.weight": "consolidated-00021-of-00022.pth",
|
1125 |
+
"layers.124.attention.wv.weight": "consolidated-00021-of-00022.pth",
|
1126 |
+
"layers.124.attention.wo.weight": "consolidated-00021-of-00022.pth",
|
1127 |
+
"layers.124.feed_forward.w1.weight": "consolidated-00021-of-00022.pth",
|
1128 |
+
"layers.124.feed_forward.w3.weight": "consolidated-00021-of-00022.pth",
|
1129 |
+
"layers.124.feed_forward.w2.weight": "consolidated-00021-of-00022.pth",
|
1130 |
+
"layers.124.attention_norm.weight": "consolidated-00021-of-00022.pth",
|
1131 |
+
"layers.124.ffn_norm.weight": "consolidated-00021-of-00022.pth",
|
1132 |
+
"layers.125.attention.wq.weight": "consolidated-00021-of-00022.pth",
|
1133 |
+
"layers.125.attention.wk.weight": "consolidated-00021-of-00022.pth",
|
1134 |
+
"layers.125.attention.wv.weight": "consolidated-00021-of-00022.pth",
|
1135 |
+
"layers.125.attention.wo.weight": "consolidated-00021-of-00022.pth",
|
1136 |
+
"layers.125.feed_forward.w1.weight": "consolidated-00021-of-00022.pth",
|
1137 |
+
"layers.125.feed_forward.w3.weight": "consolidated-00022-of-00022.pth",
|
1138 |
+
"layers.125.feed_forward.w2.weight": "consolidated-00022-of-00022.pth",
|
1139 |
+
"layers.125.attention_norm.weight": "consolidated-00022-of-00022.pth",
|
1140 |
+
"layers.125.ffn_norm.weight": "consolidated-00022-of-00022.pth",
|
1141 |
+
"norm.weight": "consolidated-00022-of-00022.pth",
|
1142 |
+
"output.weight": "consolidated-00022-of-00022.pth"
|
1143 |
+
}
|
1144 |
+
}
|
mp8/consolidated.01/consolidated-00001-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43b8ed18e98b6f7c89e658fb8b621130dfc6c3f14edbe4db358bd208531f35a8
|
3 |
+
size 4870980313
|
mp8/consolidated.01/consolidated-00002-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c1df5fe20eee3c697c148881613e00e2081494afec233caf38e3bb54fc6511c
|
3 |
+
size 4781917812
|
mp8/consolidated.01/consolidated-00003-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a201321342f264778eef1fdc59a5c7b88cc2fcb67e11ce6641ca72479afce91
|
3 |
+
size 4781917876
|
mp8/consolidated.01/consolidated-00004-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4c80392b2bb693076a9e02bb6f1a1ace8f57dd814b473d2adb8c9ae34661575
|
3 |
+
size 4781917876
|
mp8/consolidated.01/consolidated-00005-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e49539bfb3b19024ba153e12573b389920921497c0687ff14b9941fdaecffa38
|
3 |
+
size 4781917876
|
mp8/consolidated.01/consolidated-00006-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1221a187cc2d4e4ff7f93bc8ff67332e0f8f3be744f0329f25029f1df464e6bb
|
3 |
+
size 4781917876
|
mp8/consolidated.01/consolidated-00007-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33bf1b298d08b30e2809cfc8f347b8baf017b9b0b607f4626ae99f9d39b0fd46
|
3 |
+
size 4781917876
|
mp8/consolidated.01/consolidated-00008-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5986e4fafcee216c764a57c4d804aa78f9df741d3ba418a6c9fb2a3f088ea563
|
3 |
+
size 4781917876
|
mp8/consolidated.01/consolidated-00009-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6a634319106e14cc7ab901db880eeaa144d0834fcc4241b64bf5448e9b94366
|
3 |
+
size 4781917876
|
mp8/consolidated.01/consolidated-00010-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3b299dac7e7cdcba57f57c9aeedd435bd8eee047eff455b510dfa120136b19a
|
3 |
+
size 4781917876
|
mp8/consolidated.01/consolidated-00011-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e42ee90016b0c3dcbca38251a09d486872110a7b4ea0f75183d473f4c500228
|
3 |
+
size 4781917876
|
mp8/consolidated.01/consolidated-00012-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef9e647d3c4f9a7187c89ccb27d4193d0525f1048c77a414ee95f84bd2199bf6
|
3 |
+
size 4781917876
|
mp8/consolidated.01/consolidated-00013-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0fecf04787997fe38665672feb4d47609c51d29b7b78e3c3b767d88f48df886a
|
3 |
+
size 4781917876
|
mp8/consolidated.01/consolidated-00014-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96313c3901d234e556059f60a6901d2f299e347380467eda38aa227acd425b8b
|
3 |
+
size 4781917876
|
mp8/consolidated.01/consolidated-00015-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9c3f9b5dbac9bae7257b272ab1abcd1dd1155529e6f8faf1f7a9607fc08588b
|
3 |
+
size 4781917876
|
mp8/consolidated.01/consolidated-00016-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d7a1e03121865bafde2cb3c5fa24c0ea701cd24f024bf63f9c6eef7a2d9474e
|
3 |
+
size 4781917876
|
mp8/consolidated.01/consolidated-00017-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87ea70c86c6fb777c370e4a6a96b63c4a1c55e77a3e2d16f5701f0ce52a3d002
|
3 |
+
size 4781917876
|
mp8/consolidated.01/consolidated-00018-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d1d004153f11e21398f3e792df15109700069c80fea3d0d5cba4500ba032a52
|
3 |
+
size 4781917940
|
mp8/consolidated.01/consolidated-00019-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9f6538fabaf05f5c9b38038f273c87e222052cb599bbd7957c09738de90d186
|
3 |
+
size 4781917940
|
mp8/consolidated.01/consolidated-00020-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e07fff1b27685c5b4817bd434e91e56ebbf15002858e662640c82d6deccd35ef
|
3 |
+
size 4781917940
|
mp8/consolidated.01/consolidated-00021-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bef0f8aa540ebe150c0448ba0a46378f4ede0f63bb141f99752723348b7eecf
|
3 |
+
size 4781917940
|
mp8/consolidated.01/consolidated-00022-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21924772fa394ee7270e99afbefad33c18276900201595696e4c988d8b5a0e96
|
3 |
+
size 961645392
|
mp8/consolidated.01/consolidated.pth.index.json
ADDED
@@ -0,0 +1,1144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 101470601216
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"tok_embeddings.weight": "consolidated-00001-of-00022.pth",
|
7 |
+
"layers.0.attention.wq.weight": "consolidated-00001-of-00022.pth",
|
8 |
+
"layers.0.attention.wk.weight": "consolidated-00001-of-00022.pth",
|
9 |
+
"layers.0.attention.wv.weight": "consolidated-00001-of-00022.pth",
|
10 |
+
"layers.0.attention.wo.weight": "consolidated-00001-of-00022.pth",
|
11 |
+
"layers.0.feed_forward.w1.weight": "consolidated-00001-of-00022.pth",
|
12 |
+
"layers.0.feed_forward.w3.weight": "consolidated-00001-of-00022.pth",
|
13 |
+
"layers.0.feed_forward.w2.weight": "consolidated-00001-of-00022.pth",
|
14 |
+
"layers.0.attention_norm.weight": "consolidated-00001-of-00022.pth",
|
15 |
+
"layers.0.ffn_norm.weight": "consolidated-00001-of-00022.pth",
|
16 |
+
"layers.1.attention.wq.weight": "consolidated-00001-of-00022.pth",
|
17 |
+
"layers.1.attention.wk.weight": "consolidated-00001-of-00022.pth",
|
18 |
+
"layers.1.attention.wv.weight": "consolidated-00001-of-00022.pth",
|
19 |
+
"layers.1.attention.wo.weight": "consolidated-00001-of-00022.pth",
|
20 |
+
"layers.1.feed_forward.w1.weight": "consolidated-00001-of-00022.pth",
|
21 |
+
"layers.1.feed_forward.w3.weight": "consolidated-00001-of-00022.pth",
|
22 |
+
"layers.1.feed_forward.w2.weight": "consolidated-00001-of-00022.pth",
|
23 |
+
"layers.1.attention_norm.weight": "consolidated-00001-of-00022.pth",
|
24 |
+
"layers.1.ffn_norm.weight": "consolidated-00001-of-00022.pth",
|
25 |
+
"layers.2.attention.wq.weight": "consolidated-00001-of-00022.pth",
|
26 |
+
"layers.2.attention.wk.weight": "consolidated-00001-of-00022.pth",
|
27 |
+
"layers.2.attention.wv.weight": "consolidated-00001-of-00022.pth",
|
28 |
+
"layers.2.attention.wo.weight": "consolidated-00001-of-00022.pth",
|
29 |
+
"layers.2.feed_forward.w1.weight": "consolidated-00001-of-00022.pth",
|
30 |
+
"layers.2.feed_forward.w3.weight": "consolidated-00001-of-00022.pth",
|
31 |
+
"layers.2.feed_forward.w2.weight": "consolidated-00001-of-00022.pth",
|
32 |
+
"layers.2.attention_norm.weight": "consolidated-00001-of-00022.pth",
|
33 |
+
"layers.2.ffn_norm.weight": "consolidated-00001-of-00022.pth",
|
34 |
+
"layers.3.attention.wq.weight": "consolidated-00001-of-00022.pth",
|
35 |
+
"layers.3.attention.wk.weight": "consolidated-00001-of-00022.pth",
|
36 |
+
"layers.3.attention.wv.weight": "consolidated-00001-of-00022.pth",
|
37 |
+
"layers.3.attention.wo.weight": "consolidated-00001-of-00022.pth",
|
38 |
+
"layers.3.feed_forward.w1.weight": "consolidated-00001-of-00022.pth",
|
39 |
+
"layers.3.feed_forward.w3.weight": "consolidated-00001-of-00022.pth",
|
40 |
+
"layers.3.feed_forward.w2.weight": "consolidated-00001-of-00022.pth",
|
41 |
+
"layers.3.attention_norm.weight": "consolidated-00001-of-00022.pth",
|
42 |
+
"layers.3.ffn_norm.weight": "consolidated-00001-of-00022.pth",
|
43 |
+
"layers.4.attention.wq.weight": "consolidated-00001-of-00022.pth",
|
44 |
+
"layers.4.attention.wk.weight": "consolidated-00001-of-00022.pth",
|
45 |
+
"layers.4.attention.wv.weight": "consolidated-00001-of-00022.pth",
|
46 |
+
"layers.4.attention.wo.weight": "consolidated-00001-of-00022.pth",
|
47 |
+
"layers.4.feed_forward.w1.weight": "consolidated-00001-of-00022.pth",
|
48 |
+
"layers.4.feed_forward.w3.weight": "consolidated-00001-of-00022.pth",
|
49 |
+
"layers.4.feed_forward.w2.weight": "consolidated-00001-of-00022.pth",
|
50 |
+
"layers.4.attention_norm.weight": "consolidated-00001-of-00022.pth",
|
51 |
+
"layers.4.ffn_norm.weight": "consolidated-00001-of-00022.pth",
|
52 |
+
"layers.5.attention.wq.weight": "consolidated-00001-of-00022.pth",
|
53 |
+
"layers.5.attention.wk.weight": "consolidated-00001-of-00022.pth",
|
54 |
+
"layers.5.attention.wv.weight": "consolidated-00001-of-00022.pth",
|
55 |
+
"layers.5.attention.wo.weight": "consolidated-00001-of-00022.pth",
|
56 |
+
"layers.5.feed_forward.w1.weight": "consolidated-00001-of-00022.pth",
|
57 |
+
"layers.5.feed_forward.w3.weight": "consolidated-00002-of-00022.pth",
|
58 |
+
"layers.5.feed_forward.w2.weight": "consolidated-00002-of-00022.pth",
|
59 |
+
"layers.5.attention_norm.weight": "consolidated-00002-of-00022.pth",
|
60 |
+
"layers.5.ffn_norm.weight": "consolidated-00002-of-00022.pth",
|
61 |
+
"layers.6.attention.wq.weight": "consolidated-00002-of-00022.pth",
|
62 |
+
"layers.6.attention.wk.weight": "consolidated-00002-of-00022.pth",
|
63 |
+
"layers.6.attention.wv.weight": "consolidated-00002-of-00022.pth",
|
64 |
+
"layers.6.attention.wo.weight": "consolidated-00002-of-00022.pth",
|
65 |
+
"layers.6.feed_forward.w1.weight": "consolidated-00002-of-00022.pth",
|
66 |
+
"layers.6.feed_forward.w3.weight": "consolidated-00002-of-00022.pth",
|
67 |
+
"layers.6.feed_forward.w2.weight": "consolidated-00002-of-00022.pth",
|
68 |
+
"layers.6.attention_norm.weight": "consolidated-00002-of-00022.pth",
|
69 |
+
"layers.6.ffn_norm.weight": "consolidated-00002-of-00022.pth",
|
70 |
+
"layers.7.attention.wq.weight": "consolidated-00002-of-00022.pth",
|
71 |
+
"layers.7.attention.wk.weight": "consolidated-00002-of-00022.pth",
|
72 |
+
"layers.7.attention.wv.weight": "consolidated-00002-of-00022.pth",
|
73 |
+
"layers.7.attention.wo.weight": "consolidated-00002-of-00022.pth",
|
74 |
+
"layers.7.feed_forward.w1.weight": "consolidated-00002-of-00022.pth",
|
75 |
+
"layers.7.feed_forward.w3.weight": "consolidated-00002-of-00022.pth",
|
76 |
+
"layers.7.feed_forward.w2.weight": "consolidated-00002-of-00022.pth",
|
77 |
+
"layers.7.attention_norm.weight": "consolidated-00002-of-00022.pth",
|
78 |
+
"layers.7.ffn_norm.weight": "consolidated-00002-of-00022.pth",
|
79 |
+
"layers.8.attention.wq.weight": "consolidated-00002-of-00022.pth",
|
80 |
+
"layers.8.attention.wk.weight": "consolidated-00002-of-00022.pth",
|
81 |
+
"layers.8.attention.wv.weight": "consolidated-00002-of-00022.pth",
|
82 |
+
"layers.8.attention.wo.weight": "consolidated-00002-of-00022.pth",
|
83 |
+
"layers.8.feed_forward.w1.weight": "consolidated-00002-of-00022.pth",
|
84 |
+
"layers.8.feed_forward.w3.weight": "consolidated-00002-of-00022.pth",
|
85 |
+
"layers.8.feed_forward.w2.weight": "consolidated-00002-of-00022.pth",
|
86 |
+
"layers.8.attention_norm.weight": "consolidated-00002-of-00022.pth",
|
87 |
+
"layers.8.ffn_norm.weight": "consolidated-00002-of-00022.pth",
|
88 |
+
"layers.9.attention.wq.weight": "consolidated-00002-of-00022.pth",
|
89 |
+
"layers.9.attention.wk.weight": "consolidated-00002-of-00022.pth",
|
90 |
+
"layers.9.attention.wv.weight": "consolidated-00002-of-00022.pth",
|
91 |
+
"layers.9.attention.wo.weight": "consolidated-00002-of-00022.pth",
|
92 |
+
"layers.9.feed_forward.w1.weight": "consolidated-00002-of-00022.pth",
|
93 |
+
"layers.9.feed_forward.w3.weight": "consolidated-00002-of-00022.pth",
|
94 |
+
"layers.9.feed_forward.w2.weight": "consolidated-00002-of-00022.pth",
|
95 |
+
"layers.9.attention_norm.weight": "consolidated-00002-of-00022.pth",
|
96 |
+
"layers.9.ffn_norm.weight": "consolidated-00002-of-00022.pth",
|
97 |
+
"layers.10.attention.wq.weight": "consolidated-00002-of-00022.pth",
|
98 |
+
"layers.10.attention.wk.weight": "consolidated-00002-of-00022.pth",
|
99 |
+
"layers.10.attention.wv.weight": "consolidated-00002-of-00022.pth",
|
100 |
+
"layers.10.attention.wo.weight": "consolidated-00002-of-00022.pth",
|
101 |
+
"layers.10.feed_forward.w1.weight": "consolidated-00002-of-00022.pth",
|
102 |
+
"layers.10.feed_forward.w3.weight": "consolidated-00002-of-00022.pth",
|
103 |
+
"layers.10.feed_forward.w2.weight": "consolidated-00002-of-00022.pth",
|
104 |
+
"layers.10.attention_norm.weight": "consolidated-00002-of-00022.pth",
|
105 |
+
"layers.10.ffn_norm.weight": "consolidated-00002-of-00022.pth",
|
106 |
+
"layers.11.attention.wq.weight": "consolidated-00002-of-00022.pth",
|
107 |
+
"layers.11.attention.wk.weight": "consolidated-00002-of-00022.pth",
|
108 |
+
"layers.11.attention.wv.weight": "consolidated-00002-of-00022.pth",
|
109 |
+
"layers.11.attention.wo.weight": "consolidated-00002-of-00022.pth",
|
110 |
+
"layers.11.feed_forward.w1.weight": "consolidated-00002-of-00022.pth",
|
111 |
+
"layers.11.feed_forward.w3.weight": "consolidated-00003-of-00022.pth",
|
112 |
+
"layers.11.feed_forward.w2.weight": "consolidated-00003-of-00022.pth",
|
113 |
+
"layers.11.attention_norm.weight": "consolidated-00003-of-00022.pth",
|
114 |
+
"layers.11.ffn_norm.weight": "consolidated-00003-of-00022.pth",
|
115 |
+
"layers.12.attention.wq.weight": "consolidated-00003-of-00022.pth",
|
116 |
+
"layers.12.attention.wk.weight": "consolidated-00003-of-00022.pth",
|
117 |
+
"layers.12.attention.wv.weight": "consolidated-00003-of-00022.pth",
|
118 |
+
"layers.12.attention.wo.weight": "consolidated-00003-of-00022.pth",
|
119 |
+
"layers.12.feed_forward.w1.weight": "consolidated-00003-of-00022.pth",
|
120 |
+
"layers.12.feed_forward.w3.weight": "consolidated-00003-of-00022.pth",
|
121 |
+
"layers.12.feed_forward.w2.weight": "consolidated-00003-of-00022.pth",
|
122 |
+
"layers.12.attention_norm.weight": "consolidated-00003-of-00022.pth",
|
123 |
+
"layers.12.ffn_norm.weight": "consolidated-00003-of-00022.pth",
|
124 |
+
"layers.13.attention.wq.weight": "consolidated-00003-of-00022.pth",
|
125 |
+
"layers.13.attention.wk.weight": "consolidated-00003-of-00022.pth",
|
126 |
+
"layers.13.attention.wv.weight": "consolidated-00003-of-00022.pth",
|
127 |
+
"layers.13.attention.wo.weight": "consolidated-00003-of-00022.pth",
|
128 |
+
"layers.13.feed_forward.w1.weight": "consolidated-00003-of-00022.pth",
|
129 |
+
"layers.13.feed_forward.w3.weight": "consolidated-00003-of-00022.pth",
|
130 |
+
"layers.13.feed_forward.w2.weight": "consolidated-00003-of-00022.pth",
|
131 |
+
"layers.13.attention_norm.weight": "consolidated-00003-of-00022.pth",
|
132 |
+
"layers.13.ffn_norm.weight": "consolidated-00003-of-00022.pth",
|
133 |
+
"layers.14.attention.wq.weight": "consolidated-00003-of-00022.pth",
|
134 |
+
"layers.14.attention.wk.weight": "consolidated-00003-of-00022.pth",
|
135 |
+
"layers.14.attention.wv.weight": "consolidated-00003-of-00022.pth",
|
136 |
+
"layers.14.attention.wo.weight": "consolidated-00003-of-00022.pth",
|
137 |
+
"layers.14.feed_forward.w1.weight": "consolidated-00003-of-00022.pth",
|
138 |
+
"layers.14.feed_forward.w3.weight": "consolidated-00003-of-00022.pth",
|
139 |
+
"layers.14.feed_forward.w2.weight": "consolidated-00003-of-00022.pth",
|
140 |
+
"layers.14.attention_norm.weight": "consolidated-00003-of-00022.pth",
|
141 |
+
"layers.14.ffn_norm.weight": "consolidated-00003-of-00022.pth",
|
142 |
+
"layers.15.attention.wq.weight": "consolidated-00003-of-00022.pth",
|
143 |
+
"layers.15.attention.wk.weight": "consolidated-00003-of-00022.pth",
|
144 |
+
"layers.15.attention.wv.weight": "consolidated-00003-of-00022.pth",
|
145 |
+
"layers.15.attention.wo.weight": "consolidated-00003-of-00022.pth",
|
146 |
+
"layers.15.feed_forward.w1.weight": "consolidated-00003-of-00022.pth",
|
147 |
+
"layers.15.feed_forward.w3.weight": "consolidated-00003-of-00022.pth",
|
148 |
+
"layers.15.feed_forward.w2.weight": "consolidated-00003-of-00022.pth",
|
149 |
+
"layers.15.attention_norm.weight": "consolidated-00003-of-00022.pth",
|
150 |
+
"layers.15.ffn_norm.weight": "consolidated-00003-of-00022.pth",
|
151 |
+
"layers.16.attention.wq.weight": "consolidated-00003-of-00022.pth",
|
152 |
+
"layers.16.attention.wk.weight": "consolidated-00003-of-00022.pth",
|
153 |
+
"layers.16.attention.wv.weight": "consolidated-00003-of-00022.pth",
|
154 |
+
"layers.16.attention.wo.weight": "consolidated-00003-of-00022.pth",
|
155 |
+
"layers.16.feed_forward.w1.weight": "consolidated-00003-of-00022.pth",
|
156 |
+
"layers.16.feed_forward.w3.weight": "consolidated-00003-of-00022.pth",
|
157 |
+
"layers.16.feed_forward.w2.weight": "consolidated-00003-of-00022.pth",
|
158 |
+
"layers.16.attention_norm.weight": "consolidated-00003-of-00022.pth",
|
159 |
+
"layers.16.ffn_norm.weight": "consolidated-00003-of-00022.pth",
|
160 |
+
"layers.17.attention.wq.weight": "consolidated-00003-of-00022.pth",
|
161 |
+
"layers.17.attention.wk.weight": "consolidated-00003-of-00022.pth",
|
162 |
+
"layers.17.attention.wv.weight": "consolidated-00003-of-00022.pth",
|
163 |
+
"layers.17.attention.wo.weight": "consolidated-00003-of-00022.pth",
|
164 |
+
"layers.17.feed_forward.w1.weight": "consolidated-00003-of-00022.pth",
|
165 |
+
"layers.17.feed_forward.w3.weight": "consolidated-00004-of-00022.pth",
|
166 |
+
"layers.17.feed_forward.w2.weight": "consolidated-00004-of-00022.pth",
|
167 |
+
"layers.17.attention_norm.weight": "consolidated-00004-of-00022.pth",
|
168 |
+
"layers.17.ffn_norm.weight": "consolidated-00004-of-00022.pth",
|
169 |
+
"layers.18.attention.wq.weight": "consolidated-00004-of-00022.pth",
|
170 |
+
"layers.18.attention.wk.weight": "consolidated-00004-of-00022.pth",
|
171 |
+
"layers.18.attention.wv.weight": "consolidated-00004-of-00022.pth",
|
172 |
+
"layers.18.attention.wo.weight": "consolidated-00004-of-00022.pth",
|
173 |
+
"layers.18.feed_forward.w1.weight": "consolidated-00004-of-00022.pth",
|
174 |
+
"layers.18.feed_forward.w3.weight": "consolidated-00004-of-00022.pth",
|
175 |
+
"layers.18.feed_forward.w2.weight": "consolidated-00004-of-00022.pth",
|
176 |
+
"layers.18.attention_norm.weight": "consolidated-00004-of-00022.pth",
|
177 |
+
"layers.18.ffn_norm.weight": "consolidated-00004-of-00022.pth",
|
178 |
+
"layers.19.attention.wq.weight": "consolidated-00004-of-00022.pth",
|
179 |
+
"layers.19.attention.wk.weight": "consolidated-00004-of-00022.pth",
|
180 |
+
"layers.19.attention.wv.weight": "consolidated-00004-of-00022.pth",
|
181 |
+
"layers.19.attention.wo.weight": "consolidated-00004-of-00022.pth",
|
182 |
+
"layers.19.feed_forward.w1.weight": "consolidated-00004-of-00022.pth",
|
183 |
+
"layers.19.feed_forward.w3.weight": "consolidated-00004-of-00022.pth",
|
184 |
+
"layers.19.feed_forward.w2.weight": "consolidated-00004-of-00022.pth",
|
185 |
+
"layers.19.attention_norm.weight": "consolidated-00004-of-00022.pth",
|
186 |
+
"layers.19.ffn_norm.weight": "consolidated-00004-of-00022.pth",
|
187 |
+
"layers.20.attention.wq.weight": "consolidated-00004-of-00022.pth",
|
188 |
+
"layers.20.attention.wk.weight": "consolidated-00004-of-00022.pth",
|
189 |
+
"layers.20.attention.wv.weight": "consolidated-00004-of-00022.pth",
|
190 |
+
"layers.20.attention.wo.weight": "consolidated-00004-of-00022.pth",
|
191 |
+
"layers.20.feed_forward.w1.weight": "consolidated-00004-of-00022.pth",
|
192 |
+
"layers.20.feed_forward.w3.weight": "consolidated-00004-of-00022.pth",
|
193 |
+
"layers.20.feed_forward.w2.weight": "consolidated-00004-of-00022.pth",
|
194 |
+
"layers.20.attention_norm.weight": "consolidated-00004-of-00022.pth",
|
195 |
+
"layers.20.ffn_norm.weight": "consolidated-00004-of-00022.pth",
|
196 |
+
"layers.21.attention.wq.weight": "consolidated-00004-of-00022.pth",
|
197 |
+
"layers.21.attention.wk.weight": "consolidated-00004-of-00022.pth",
|
198 |
+
"layers.21.attention.wv.weight": "consolidated-00004-of-00022.pth",
|
199 |
+
"layers.21.attention.wo.weight": "consolidated-00004-of-00022.pth",
|
200 |
+
"layers.21.feed_forward.w1.weight": "consolidated-00004-of-00022.pth",
|
201 |
+
"layers.21.feed_forward.w3.weight": "consolidated-00004-of-00022.pth",
|
202 |
+
"layers.21.feed_forward.w2.weight": "consolidated-00004-of-00022.pth",
|
203 |
+
"layers.21.attention_norm.weight": "consolidated-00004-of-00022.pth",
|
204 |
+
"layers.21.ffn_norm.weight": "consolidated-00004-of-00022.pth",
|
205 |
+
"layers.22.attention.wq.weight": "consolidated-00004-of-00022.pth",
|
206 |
+
"layers.22.attention.wk.weight": "consolidated-00004-of-00022.pth",
|
207 |
+
"layers.22.attention.wv.weight": "consolidated-00004-of-00022.pth",
|
208 |
+
"layers.22.attention.wo.weight": "consolidated-00004-of-00022.pth",
|
209 |
+
"layers.22.feed_forward.w1.weight": "consolidated-00004-of-00022.pth",
|
210 |
+
"layers.22.feed_forward.w3.weight": "consolidated-00004-of-00022.pth",
|
211 |
+
"layers.22.feed_forward.w2.weight": "consolidated-00004-of-00022.pth",
|
212 |
+
"layers.22.attention_norm.weight": "consolidated-00004-of-00022.pth",
|
213 |
+
"layers.22.ffn_norm.weight": "consolidated-00004-of-00022.pth",
|
214 |
+
"layers.23.attention.wq.weight": "consolidated-00004-of-00022.pth",
|
215 |
+
"layers.23.attention.wk.weight": "consolidated-00004-of-00022.pth",
|
216 |
+
"layers.23.attention.wv.weight": "consolidated-00004-of-00022.pth",
|
217 |
+
"layers.23.attention.wo.weight": "consolidated-00004-of-00022.pth",
|
218 |
+
"layers.23.feed_forward.w1.weight": "consolidated-00004-of-00022.pth",
|
219 |
+
"layers.23.feed_forward.w3.weight": "consolidated-00005-of-00022.pth",
|
220 |
+
"layers.23.feed_forward.w2.weight": "consolidated-00005-of-00022.pth",
|
221 |
+
"layers.23.attention_norm.weight": "consolidated-00005-of-00022.pth",
|
222 |
+
"layers.23.ffn_norm.weight": "consolidated-00005-of-00022.pth",
|
223 |
+
"layers.24.attention.wq.weight": "consolidated-00005-of-00022.pth",
|
224 |
+
"layers.24.attention.wk.weight": "consolidated-00005-of-00022.pth",
|
225 |
+
"layers.24.attention.wv.weight": "consolidated-00005-of-00022.pth",
|
226 |
+
"layers.24.attention.wo.weight": "consolidated-00005-of-00022.pth",
|
227 |
+
"layers.24.feed_forward.w1.weight": "consolidated-00005-of-00022.pth",
|
228 |
+
"layers.24.feed_forward.w3.weight": "consolidated-00005-of-00022.pth",
|
229 |
+
"layers.24.feed_forward.w2.weight": "consolidated-00005-of-00022.pth",
|
230 |
+
"layers.24.attention_norm.weight": "consolidated-00005-of-00022.pth",
|
231 |
+
"layers.24.ffn_norm.weight": "consolidated-00005-of-00022.pth",
|
232 |
+
"layers.25.attention.wq.weight": "consolidated-00005-of-00022.pth",
|
233 |
+
"layers.25.attention.wk.weight": "consolidated-00005-of-00022.pth",
|
234 |
+
"layers.25.attention.wv.weight": "consolidated-00005-of-00022.pth",
|
235 |
+
"layers.25.attention.wo.weight": "consolidated-00005-of-00022.pth",
|
236 |
+
"layers.25.feed_forward.w1.weight": "consolidated-00005-of-00022.pth",
|
237 |
+
"layers.25.feed_forward.w3.weight": "consolidated-00005-of-00022.pth",
|
238 |
+
"layers.25.feed_forward.w2.weight": "consolidated-00005-of-00022.pth",
|
239 |
+
"layers.25.attention_norm.weight": "consolidated-00005-of-00022.pth",
|
240 |
+
"layers.25.ffn_norm.weight": "consolidated-00005-of-00022.pth",
|
241 |
+
"layers.26.attention.wq.weight": "consolidated-00005-of-00022.pth",
|
242 |
+
"layers.26.attention.wk.weight": "consolidated-00005-of-00022.pth",
|
243 |
+
"layers.26.attention.wv.weight": "consolidated-00005-of-00022.pth",
|
244 |
+
"layers.26.attention.wo.weight": "consolidated-00005-of-00022.pth",
|
245 |
+
"layers.26.feed_forward.w1.weight": "consolidated-00005-of-00022.pth",
|
246 |
+
"layers.26.feed_forward.w3.weight": "consolidated-00005-of-00022.pth",
|
247 |
+
"layers.26.feed_forward.w2.weight": "consolidated-00005-of-00022.pth",
|
248 |
+
"layers.26.attention_norm.weight": "consolidated-00005-of-00022.pth",
|
249 |
+
"layers.26.ffn_norm.weight": "consolidated-00005-of-00022.pth",
|
250 |
+
"layers.27.attention.wq.weight": "consolidated-00005-of-00022.pth",
|
251 |
+
"layers.27.attention.wk.weight": "consolidated-00005-of-00022.pth",
|
252 |
+
"layers.27.attention.wv.weight": "consolidated-00005-of-00022.pth",
|
253 |
+
"layers.27.attention.wo.weight": "consolidated-00005-of-00022.pth",
|
254 |
+
"layers.27.feed_forward.w1.weight": "consolidated-00005-of-00022.pth",
|
255 |
+
"layers.27.feed_forward.w3.weight": "consolidated-00005-of-00022.pth",
|
256 |
+
"layers.27.feed_forward.w2.weight": "consolidated-00005-of-00022.pth",
|
257 |
+
"layers.27.attention_norm.weight": "consolidated-00005-of-00022.pth",
|
258 |
+
"layers.27.ffn_norm.weight": "consolidated-00005-of-00022.pth",
|
259 |
+
"layers.28.attention.wq.weight": "consolidated-00005-of-00022.pth",
|
260 |
+
"layers.28.attention.wk.weight": "consolidated-00005-of-00022.pth",
|
261 |
+
"layers.28.attention.wv.weight": "consolidated-00005-of-00022.pth",
|
262 |
+
"layers.28.attention.wo.weight": "consolidated-00005-of-00022.pth",
|
263 |
+
"layers.28.feed_forward.w1.weight": "consolidated-00005-of-00022.pth",
|
264 |
+
"layers.28.feed_forward.w3.weight": "consolidated-00005-of-00022.pth",
|
265 |
+
"layers.28.feed_forward.w2.weight": "consolidated-00005-of-00022.pth",
|
266 |
+
"layers.28.attention_norm.weight": "consolidated-00005-of-00022.pth",
|
267 |
+
"layers.28.ffn_norm.weight": "consolidated-00005-of-00022.pth",
|
268 |
+
"layers.29.attention.wq.weight": "consolidated-00005-of-00022.pth",
|
269 |
+
"layers.29.attention.wk.weight": "consolidated-00005-of-00022.pth",
|
270 |
+
"layers.29.attention.wv.weight": "consolidated-00005-of-00022.pth",
|
271 |
+
"layers.29.attention.wo.weight": "consolidated-00005-of-00022.pth",
|
272 |
+
"layers.29.feed_forward.w1.weight": "consolidated-00005-of-00022.pth",
|
273 |
+
"layers.29.feed_forward.w3.weight": "consolidated-00006-of-00022.pth",
|
274 |
+
"layers.29.feed_forward.w2.weight": "consolidated-00006-of-00022.pth",
|
275 |
+
"layers.29.attention_norm.weight": "consolidated-00006-of-00022.pth",
|
276 |
+
"layers.29.ffn_norm.weight": "consolidated-00006-of-00022.pth",
|
277 |
+
"layers.30.attention.wq.weight": "consolidated-00006-of-00022.pth",
|
278 |
+
"layers.30.attention.wk.weight": "consolidated-00006-of-00022.pth",
|
279 |
+
"layers.30.attention.wv.weight": "consolidated-00006-of-00022.pth",
|
280 |
+
"layers.30.attention.wo.weight": "consolidated-00006-of-00022.pth",
|
281 |
+
"layers.30.feed_forward.w1.weight": "consolidated-00006-of-00022.pth",
|
282 |
+
"layers.30.feed_forward.w3.weight": "consolidated-00006-of-00022.pth",
|
283 |
+
"layers.30.feed_forward.w2.weight": "consolidated-00006-of-00022.pth",
|
284 |
+
"layers.30.attention_norm.weight": "consolidated-00006-of-00022.pth",
|
285 |
+
"layers.30.ffn_norm.weight": "consolidated-00006-of-00022.pth",
|
286 |
+
"layers.31.attention.wq.weight": "consolidated-00006-of-00022.pth",
|
287 |
+
"layers.31.attention.wk.weight": "consolidated-00006-of-00022.pth",
|
288 |
+
"layers.31.attention.wv.weight": "consolidated-00006-of-00022.pth",
|
289 |
+
"layers.31.attention.wo.weight": "consolidated-00006-of-00022.pth",
|
290 |
+
"layers.31.feed_forward.w1.weight": "consolidated-00006-of-00022.pth",
|
291 |
+
"layers.31.feed_forward.w3.weight": "consolidated-00006-of-00022.pth",
|
292 |
+
"layers.31.feed_forward.w2.weight": "consolidated-00006-of-00022.pth",
|
293 |
+
"layers.31.attention_norm.weight": "consolidated-00006-of-00022.pth",
|
294 |
+
"layers.31.ffn_norm.weight": "consolidated-00006-of-00022.pth",
|
295 |
+
"layers.32.attention.wq.weight": "consolidated-00006-of-00022.pth",
|
296 |
+
"layers.32.attention.wk.weight": "consolidated-00006-of-00022.pth",
|
297 |
+
"layers.32.attention.wv.weight": "consolidated-00006-of-00022.pth",
|
298 |
+
"layers.32.attention.wo.weight": "consolidated-00006-of-00022.pth",
|
299 |
+
"layers.32.feed_forward.w1.weight": "consolidated-00006-of-00022.pth",
|
300 |
+
"layers.32.feed_forward.w3.weight": "consolidated-00006-of-00022.pth",
|
301 |
+
"layers.32.feed_forward.w2.weight": "consolidated-00006-of-00022.pth",
|
302 |
+
"layers.32.attention_norm.weight": "consolidated-00006-of-00022.pth",
|
303 |
+
"layers.32.ffn_norm.weight": "consolidated-00006-of-00022.pth",
|
304 |
+
"layers.33.attention.wq.weight": "consolidated-00006-of-00022.pth",
|
305 |
+
"layers.33.attention.wk.weight": "consolidated-00006-of-00022.pth",
|
306 |
+
"layers.33.attention.wv.weight": "consolidated-00006-of-00022.pth",
|
307 |
+
"layers.33.attention.wo.weight": "consolidated-00006-of-00022.pth",
|
308 |
+
"layers.33.feed_forward.w1.weight": "consolidated-00006-of-00022.pth",
|
309 |
+
"layers.33.feed_forward.w3.weight": "consolidated-00006-of-00022.pth",
|
310 |
+
"layers.33.feed_forward.w2.weight": "consolidated-00006-of-00022.pth",
|
311 |
+
"layers.33.attention_norm.weight": "consolidated-00006-of-00022.pth",
|
312 |
+
"layers.33.ffn_norm.weight": "consolidated-00006-of-00022.pth",
|
313 |
+
"layers.34.attention.wq.weight": "consolidated-00006-of-00022.pth",
|
314 |
+
"layers.34.attention.wk.weight": "consolidated-00006-of-00022.pth",
|
315 |
+
"layers.34.attention.wv.weight": "consolidated-00006-of-00022.pth",
|
316 |
+
"layers.34.attention.wo.weight": "consolidated-00006-of-00022.pth",
|
317 |
+
"layers.34.feed_forward.w1.weight": "consolidated-00006-of-00022.pth",
|
318 |
+
"layers.34.feed_forward.w3.weight": "consolidated-00006-of-00022.pth",
|
319 |
+
"layers.34.feed_forward.w2.weight": "consolidated-00006-of-00022.pth",
|
320 |
+
"layers.34.attention_norm.weight": "consolidated-00006-of-00022.pth",
|
321 |
+
"layers.34.ffn_norm.weight": "consolidated-00006-of-00022.pth",
|
322 |
+
"layers.35.attention.wq.weight": "consolidated-00006-of-00022.pth",
|
323 |
+
"layers.35.attention.wk.weight": "consolidated-00006-of-00022.pth",
|
324 |
+
"layers.35.attention.wv.weight": "consolidated-00006-of-00022.pth",
|
325 |
+
"layers.35.attention.wo.weight": "consolidated-00006-of-00022.pth",
|
326 |
+
"layers.35.feed_forward.w1.weight": "consolidated-00006-of-00022.pth",
|
327 |
+
"layers.35.feed_forward.w3.weight": "consolidated-00007-of-00022.pth",
|
328 |
+
"layers.35.feed_forward.w2.weight": "consolidated-00007-of-00022.pth",
|
329 |
+
"layers.35.attention_norm.weight": "consolidated-00007-of-00022.pth",
|
330 |
+
"layers.35.ffn_norm.weight": "consolidated-00007-of-00022.pth",
|
331 |
+
"layers.36.attention.wq.weight": "consolidated-00007-of-00022.pth",
|
332 |
+
"layers.36.attention.wk.weight": "consolidated-00007-of-00022.pth",
|
333 |
+
"layers.36.attention.wv.weight": "consolidated-00007-of-00022.pth",
|
334 |
+
"layers.36.attention.wo.weight": "consolidated-00007-of-00022.pth",
|
335 |
+
"layers.36.feed_forward.w1.weight": "consolidated-00007-of-00022.pth",
|
336 |
+
"layers.36.feed_forward.w3.weight": "consolidated-00007-of-00022.pth",
|
337 |
+
"layers.36.feed_forward.w2.weight": "consolidated-00007-of-00022.pth",
|
338 |
+
"layers.36.attention_norm.weight": "consolidated-00007-of-00022.pth",
|
339 |
+
"layers.36.ffn_norm.weight": "consolidated-00007-of-00022.pth",
|
340 |
+
"layers.37.attention.wq.weight": "consolidated-00007-of-00022.pth",
|
341 |
+
"layers.37.attention.wk.weight": "consolidated-00007-of-00022.pth",
|
342 |
+
"layers.37.attention.wv.weight": "consolidated-00007-of-00022.pth",
|
343 |
+
"layers.37.attention.wo.weight": "consolidated-00007-of-00022.pth",
|
344 |
+
"layers.37.feed_forward.w1.weight": "consolidated-00007-of-00022.pth",
|
345 |
+
"layers.37.feed_forward.w3.weight": "consolidated-00007-of-00022.pth",
|
346 |
+
"layers.37.feed_forward.w2.weight": "consolidated-00007-of-00022.pth",
|
347 |
+
"layers.37.attention_norm.weight": "consolidated-00007-of-00022.pth",
|
348 |
+
"layers.37.ffn_norm.weight": "consolidated-00007-of-00022.pth",
|
349 |
+
"layers.38.attention.wq.weight": "consolidated-00007-of-00022.pth",
|
350 |
+
"layers.38.attention.wk.weight": "consolidated-00007-of-00022.pth",
|
351 |
+
"layers.38.attention.wv.weight": "consolidated-00007-of-00022.pth",
|
352 |
+
"layers.38.attention.wo.weight": "consolidated-00007-of-00022.pth",
|
353 |
+
"layers.38.feed_forward.w1.weight": "consolidated-00007-of-00022.pth",
|
354 |
+
"layers.38.feed_forward.w3.weight": "consolidated-00007-of-00022.pth",
|
355 |
+
"layers.38.feed_forward.w2.weight": "consolidated-00007-of-00022.pth",
|
356 |
+
"layers.38.attention_norm.weight": "consolidated-00007-of-00022.pth",
|
357 |
+
"layers.38.ffn_norm.weight": "consolidated-00007-of-00022.pth",
|
358 |
+
"layers.39.attention.wq.weight": "consolidated-00007-of-00022.pth",
|
359 |
+
"layers.39.attention.wk.weight": "consolidated-00007-of-00022.pth",
|
360 |
+
"layers.39.attention.wv.weight": "consolidated-00007-of-00022.pth",
|
361 |
+
"layers.39.attention.wo.weight": "consolidated-00007-of-00022.pth",
|
362 |
+
"layers.39.feed_forward.w1.weight": "consolidated-00007-of-00022.pth",
|
363 |
+
"layers.39.feed_forward.w3.weight": "consolidated-00007-of-00022.pth",
|
364 |
+
"layers.39.feed_forward.w2.weight": "consolidated-00007-of-00022.pth",
|
365 |
+
"layers.39.attention_norm.weight": "consolidated-00007-of-00022.pth",
|
366 |
+
"layers.39.ffn_norm.weight": "consolidated-00007-of-00022.pth",
|
367 |
+
"layers.40.attention.wq.weight": "consolidated-00007-of-00022.pth",
|
368 |
+
"layers.40.attention.wk.weight": "consolidated-00007-of-00022.pth",
|
369 |
+
"layers.40.attention.wv.weight": "consolidated-00007-of-00022.pth",
|
370 |
+
"layers.40.attention.wo.weight": "consolidated-00007-of-00022.pth",
|
371 |
+
"layers.40.feed_forward.w1.weight": "consolidated-00007-of-00022.pth",
|
372 |
+
"layers.40.feed_forward.w3.weight": "consolidated-00007-of-00022.pth",
|
373 |
+
"layers.40.feed_forward.w2.weight": "consolidated-00007-of-00022.pth",
|
374 |
+
"layers.40.attention_norm.weight": "consolidated-00007-of-00022.pth",
|
375 |
+
"layers.40.ffn_norm.weight": "consolidated-00007-of-00022.pth",
|
376 |
+
"layers.41.attention.wq.weight": "consolidated-00007-of-00022.pth",
|
377 |
+
"layers.41.attention.wk.weight": "consolidated-00007-of-00022.pth",
|
378 |
+
"layers.41.attention.wv.weight": "consolidated-00007-of-00022.pth",
|
379 |
+
"layers.41.attention.wo.weight": "consolidated-00007-of-00022.pth",
|
380 |
+
"layers.41.feed_forward.w1.weight": "consolidated-00007-of-00022.pth",
|
381 |
+
"layers.41.feed_forward.w3.weight": "consolidated-00008-of-00022.pth",
|
382 |
+
"layers.41.feed_forward.w2.weight": "consolidated-00008-of-00022.pth",
|
383 |
+
"layers.41.attention_norm.weight": "consolidated-00008-of-00022.pth",
|
384 |
+
"layers.41.ffn_norm.weight": "consolidated-00008-of-00022.pth",
|
385 |
+
"layers.42.attention.wq.weight": "consolidated-00008-of-00022.pth",
|
386 |
+
"layers.42.attention.wk.weight": "consolidated-00008-of-00022.pth",
|
387 |
+
"layers.42.attention.wv.weight": "consolidated-00008-of-00022.pth",
|
388 |
+
"layers.42.attention.wo.weight": "consolidated-00008-of-00022.pth",
|
389 |
+
"layers.42.feed_forward.w1.weight": "consolidated-00008-of-00022.pth",
|
390 |
+
"layers.42.feed_forward.w3.weight": "consolidated-00008-of-00022.pth",
|
391 |
+
"layers.42.feed_forward.w2.weight": "consolidated-00008-of-00022.pth",
|
392 |
+
"layers.42.attention_norm.weight": "consolidated-00008-of-00022.pth",
|
393 |
+
"layers.42.ffn_norm.weight": "consolidated-00008-of-00022.pth",
|
394 |
+
"layers.43.attention.wq.weight": "consolidated-00008-of-00022.pth",
|
395 |
+
"layers.43.attention.wk.weight": "consolidated-00008-of-00022.pth",
|
396 |
+
"layers.43.attention.wv.weight": "consolidated-00008-of-00022.pth",
|
397 |
+
"layers.43.attention.wo.weight": "consolidated-00008-of-00022.pth",
|
398 |
+
"layers.43.feed_forward.w1.weight": "consolidated-00008-of-00022.pth",
|
399 |
+
"layers.43.feed_forward.w3.weight": "consolidated-00008-of-00022.pth",
|
400 |
+
"layers.43.feed_forward.w2.weight": "consolidated-00008-of-00022.pth",
|
401 |
+
"layers.43.attention_norm.weight": "consolidated-00008-of-00022.pth",
|
402 |
+
"layers.43.ffn_norm.weight": "consolidated-00008-of-00022.pth",
|
403 |
+
"layers.44.attention.wq.weight": "consolidated-00008-of-00022.pth",
|
404 |
+
"layers.44.attention.wk.weight": "consolidated-00008-of-00022.pth",
|
405 |
+
"layers.44.attention.wv.weight": "consolidated-00008-of-00022.pth",
|
406 |
+
"layers.44.attention.wo.weight": "consolidated-00008-of-00022.pth",
|
407 |
+
"layers.44.feed_forward.w1.weight": "consolidated-00008-of-00022.pth",
|
408 |
+
"layers.44.feed_forward.w3.weight": "consolidated-00008-of-00022.pth",
|
409 |
+
"layers.44.feed_forward.w2.weight": "consolidated-00008-of-00022.pth",
|
410 |
+
"layers.44.attention_norm.weight": "consolidated-00008-of-00022.pth",
|
411 |
+
"layers.44.ffn_norm.weight": "consolidated-00008-of-00022.pth",
|
412 |
+
"layers.45.attention.wq.weight": "consolidated-00008-of-00022.pth",
|
413 |
+
"layers.45.attention.wk.weight": "consolidated-00008-of-00022.pth",
|
414 |
+
"layers.45.attention.wv.weight": "consolidated-00008-of-00022.pth",
|
415 |
+
"layers.45.attention.wo.weight": "consolidated-00008-of-00022.pth",
|
416 |
+
"layers.45.feed_forward.w1.weight": "consolidated-00008-of-00022.pth",
|
417 |
+
"layers.45.feed_forward.w3.weight": "consolidated-00008-of-00022.pth",
|
418 |
+
"layers.45.feed_forward.w2.weight": "consolidated-00008-of-00022.pth",
|
419 |
+
"layers.45.attention_norm.weight": "consolidated-00008-of-00022.pth",
|
420 |
+
"layers.45.ffn_norm.weight": "consolidated-00008-of-00022.pth",
|
421 |
+
"layers.46.attention.wq.weight": "consolidated-00008-of-00022.pth",
|
422 |
+
"layers.46.attention.wk.weight": "consolidated-00008-of-00022.pth",
|
423 |
+
"layers.46.attention.wv.weight": "consolidated-00008-of-00022.pth",
|
424 |
+
"layers.46.attention.wo.weight": "consolidated-00008-of-00022.pth",
|
425 |
+
"layers.46.feed_forward.w1.weight": "consolidated-00008-of-00022.pth",
|
426 |
+
"layers.46.feed_forward.w3.weight": "consolidated-00008-of-00022.pth",
|
427 |
+
"layers.46.feed_forward.w2.weight": "consolidated-00008-of-00022.pth",
|
428 |
+
"layers.46.attention_norm.weight": "consolidated-00008-of-00022.pth",
|
429 |
+
"layers.46.ffn_norm.weight": "consolidated-00008-of-00022.pth",
|
430 |
+
"layers.47.attention.wq.weight": "consolidated-00008-of-00022.pth",
|
431 |
+
"layers.47.attention.wk.weight": "consolidated-00008-of-00022.pth",
|
432 |
+
"layers.47.attention.wv.weight": "consolidated-00008-of-00022.pth",
|
433 |
+
"layers.47.attention.wo.weight": "consolidated-00008-of-00022.pth",
|
434 |
+
"layers.47.feed_forward.w1.weight": "consolidated-00008-of-00022.pth",
|
435 |
+
"layers.47.feed_forward.w3.weight": "consolidated-00009-of-00022.pth",
|
436 |
+
"layers.47.feed_forward.w2.weight": "consolidated-00009-of-00022.pth",
|
437 |
+
"layers.47.attention_norm.weight": "consolidated-00009-of-00022.pth",
|
438 |
+
"layers.47.ffn_norm.weight": "consolidated-00009-of-00022.pth",
|
439 |
+
"layers.48.attention.wq.weight": "consolidated-00009-of-00022.pth",
|
440 |
+
"layers.48.attention.wk.weight": "consolidated-00009-of-00022.pth",
|
441 |
+
"layers.48.attention.wv.weight": "consolidated-00009-of-00022.pth",
|
442 |
+
"layers.48.attention.wo.weight": "consolidated-00009-of-00022.pth",
|
443 |
+
"layers.48.feed_forward.w1.weight": "consolidated-00009-of-00022.pth",
|
444 |
+
"layers.48.feed_forward.w3.weight": "consolidated-00009-of-00022.pth",
|
445 |
+
"layers.48.feed_forward.w2.weight": "consolidated-00009-of-00022.pth",
|
446 |
+
"layers.48.attention_norm.weight": "consolidated-00009-of-00022.pth",
|
447 |
+
"layers.48.ffn_norm.weight": "consolidated-00009-of-00022.pth",
|
448 |
+
"layers.49.attention.wq.weight": "consolidated-00009-of-00022.pth",
|
449 |
+
"layers.49.attention.wk.weight": "consolidated-00009-of-00022.pth",
|
450 |
+
"layers.49.attention.wv.weight": "consolidated-00009-of-00022.pth",
|
451 |
+
"layers.49.attention.wo.weight": "consolidated-00009-of-00022.pth",
|
452 |
+
"layers.49.feed_forward.w1.weight": "consolidated-00009-of-00022.pth",
|
453 |
+
"layers.49.feed_forward.w3.weight": "consolidated-00009-of-00022.pth",
|
454 |
+
"layers.49.feed_forward.w2.weight": "consolidated-00009-of-00022.pth",
|
455 |
+
"layers.49.attention_norm.weight": "consolidated-00009-of-00022.pth",
|
456 |
+
"layers.49.ffn_norm.weight": "consolidated-00009-of-00022.pth",
|
457 |
+
"layers.50.attention.wq.weight": "consolidated-00009-of-00022.pth",
|
458 |
+
"layers.50.attention.wk.weight": "consolidated-00009-of-00022.pth",
|
459 |
+
"layers.50.attention.wv.weight": "consolidated-00009-of-00022.pth",
|
460 |
+
"layers.50.attention.wo.weight": "consolidated-00009-of-00022.pth",
|
461 |
+
"layers.50.feed_forward.w1.weight": "consolidated-00009-of-00022.pth",
|
462 |
+
"layers.50.feed_forward.w3.weight": "consolidated-00009-of-00022.pth",
|
463 |
+
"layers.50.feed_forward.w2.weight": "consolidated-00009-of-00022.pth",
|
464 |
+
"layers.50.attention_norm.weight": "consolidated-00009-of-00022.pth",
|
465 |
+
"layers.50.ffn_norm.weight": "consolidated-00009-of-00022.pth",
|
466 |
+
"layers.51.attention.wq.weight": "consolidated-00009-of-00022.pth",
|
467 |
+
"layers.51.attention.wk.weight": "consolidated-00009-of-00022.pth",
|
468 |
+
"layers.51.attention.wv.weight": "consolidated-00009-of-00022.pth",
|
469 |
+
"layers.51.attention.wo.weight": "consolidated-00009-of-00022.pth",
|
470 |
+
"layers.51.feed_forward.w1.weight": "consolidated-00009-of-00022.pth",
|
471 |
+
"layers.51.feed_forward.w3.weight": "consolidated-00009-of-00022.pth",
|
472 |
+
"layers.51.feed_forward.w2.weight": "consolidated-00009-of-00022.pth",
|
473 |
+
"layers.51.attention_norm.weight": "consolidated-00009-of-00022.pth",
|
474 |
+
"layers.51.ffn_norm.weight": "consolidated-00009-of-00022.pth",
|
475 |
+
"layers.52.attention.wq.weight": "consolidated-00009-of-00022.pth",
|
476 |
+
"layers.52.attention.wk.weight": "consolidated-00009-of-00022.pth",
|
477 |
+
"layers.52.attention.wv.weight": "consolidated-00009-of-00022.pth",
|
478 |
+
"layers.52.attention.wo.weight": "consolidated-00009-of-00022.pth",
|
479 |
+
"layers.52.feed_forward.w1.weight": "consolidated-00009-of-00022.pth",
|
480 |
+
"layers.52.feed_forward.w3.weight": "consolidated-00009-of-00022.pth",
|
481 |
+
"layers.52.feed_forward.w2.weight": "consolidated-00009-of-00022.pth",
|
482 |
+
"layers.52.attention_norm.weight": "consolidated-00009-of-00022.pth",
|
483 |
+
"layers.52.ffn_norm.weight": "consolidated-00009-of-00022.pth",
|
484 |
+
"layers.53.attention.wq.weight": "consolidated-00009-of-00022.pth",
|
485 |
+
"layers.53.attention.wk.weight": "consolidated-00009-of-00022.pth",
|
486 |
+
"layers.53.attention.wv.weight": "consolidated-00009-of-00022.pth",
|
487 |
+
"layers.53.attention.wo.weight": "consolidated-00009-of-00022.pth",
|
488 |
+
"layers.53.feed_forward.w1.weight": "consolidated-00009-of-00022.pth",
|
489 |
+
"layers.53.feed_forward.w3.weight": "consolidated-00010-of-00022.pth",
|
490 |
+
"layers.53.feed_forward.w2.weight": "consolidated-00010-of-00022.pth",
|
491 |
+
"layers.53.attention_norm.weight": "consolidated-00010-of-00022.pth",
|
492 |
+
"layers.53.ffn_norm.weight": "consolidated-00010-of-00022.pth",
|
493 |
+
"layers.54.attention.wq.weight": "consolidated-00010-of-00022.pth",
|
494 |
+
"layers.54.attention.wk.weight": "consolidated-00010-of-00022.pth",
|
495 |
+
"layers.54.attention.wv.weight": "consolidated-00010-of-00022.pth",
|
496 |
+
"layers.54.attention.wo.weight": "consolidated-00010-of-00022.pth",
|
497 |
+
"layers.54.feed_forward.w1.weight": "consolidated-00010-of-00022.pth",
|
498 |
+
"layers.54.feed_forward.w3.weight": "consolidated-00010-of-00022.pth",
|
499 |
+
"layers.54.feed_forward.w2.weight": "consolidated-00010-of-00022.pth",
|
500 |
+
"layers.54.attention_norm.weight": "consolidated-00010-of-00022.pth",
|
501 |
+
"layers.54.ffn_norm.weight": "consolidated-00010-of-00022.pth",
|
502 |
+
"layers.55.attention.wq.weight": "consolidated-00010-of-00022.pth",
|
503 |
+
"layers.55.attention.wk.weight": "consolidated-00010-of-00022.pth",
|
504 |
+
"layers.55.attention.wv.weight": "consolidated-00010-of-00022.pth",
|
505 |
+
"layers.55.attention.wo.weight": "consolidated-00010-of-00022.pth",
|
506 |
+
"layers.55.feed_forward.w1.weight": "consolidated-00010-of-00022.pth",
|
507 |
+
"layers.55.feed_forward.w3.weight": "consolidated-00010-of-00022.pth",
|
508 |
+
"layers.55.feed_forward.w2.weight": "consolidated-00010-of-00022.pth",
|
509 |
+
"layers.55.attention_norm.weight": "consolidated-00010-of-00022.pth",
|
510 |
+
"layers.55.ffn_norm.weight": "consolidated-00010-of-00022.pth",
|
511 |
+
"layers.56.attention.wq.weight": "consolidated-00010-of-00022.pth",
|
512 |
+
"layers.56.attention.wk.weight": "consolidated-00010-of-00022.pth",
|
513 |
+
"layers.56.attention.wv.weight": "consolidated-00010-of-00022.pth",
|
514 |
+
"layers.56.attention.wo.weight": "consolidated-00010-of-00022.pth",
|
515 |
+
"layers.56.feed_forward.w1.weight": "consolidated-00010-of-00022.pth",
|
516 |
+
"layers.56.feed_forward.w3.weight": "consolidated-00010-of-00022.pth",
|
517 |
+
"layers.56.feed_forward.w2.weight": "consolidated-00010-of-00022.pth",
|
518 |
+
"layers.56.attention_norm.weight": "consolidated-00010-of-00022.pth",
|
519 |
+
"layers.56.ffn_norm.weight": "consolidated-00010-of-00022.pth",
|
520 |
+
"layers.57.attention.wq.weight": "consolidated-00010-of-00022.pth",
|
521 |
+
"layers.57.attention.wk.weight": "consolidated-00010-of-00022.pth",
|
522 |
+
"layers.57.attention.wv.weight": "consolidated-00010-of-00022.pth",
|
523 |
+
"layers.57.attention.wo.weight": "consolidated-00010-of-00022.pth",
|
524 |
+
"layers.57.feed_forward.w1.weight": "consolidated-00010-of-00022.pth",
|
525 |
+
"layers.57.feed_forward.w3.weight": "consolidated-00010-of-00022.pth",
|
526 |
+
"layers.57.feed_forward.w2.weight": "consolidated-00010-of-00022.pth",
|
527 |
+
"layers.57.attention_norm.weight": "consolidated-00010-of-00022.pth",
|
528 |
+
"layers.57.ffn_norm.weight": "consolidated-00010-of-00022.pth",
|
529 |
+
"layers.58.attention.wq.weight": "consolidated-00010-of-00022.pth",
|
530 |
+
"layers.58.attention.wk.weight": "consolidated-00010-of-00022.pth",
|
531 |
+
"layers.58.attention.wv.weight": "consolidated-00010-of-00022.pth",
|
532 |
+
"layers.58.attention.wo.weight": "consolidated-00010-of-00022.pth",
|
533 |
+
"layers.58.feed_forward.w1.weight": "consolidated-00010-of-00022.pth",
|
534 |
+
"layers.58.feed_forward.w3.weight": "consolidated-00010-of-00022.pth",
|
535 |
+
"layers.58.feed_forward.w2.weight": "consolidated-00010-of-00022.pth",
|
536 |
+
"layers.58.attention_norm.weight": "consolidated-00010-of-00022.pth",
|
537 |
+
"layers.58.ffn_norm.weight": "consolidated-00010-of-00022.pth",
|
538 |
+
"layers.59.attention.wq.weight": "consolidated-00010-of-00022.pth",
|
539 |
+
"layers.59.attention.wk.weight": "consolidated-00010-of-00022.pth",
|
540 |
+
"layers.59.attention.wv.weight": "consolidated-00010-of-00022.pth",
|
541 |
+
"layers.59.attention.wo.weight": "consolidated-00010-of-00022.pth",
|
542 |
+
"layers.59.feed_forward.w1.weight": "consolidated-00010-of-00022.pth",
|
543 |
+
"layers.59.feed_forward.w3.weight": "consolidated-00011-of-00022.pth",
|
544 |
+
"layers.59.feed_forward.w2.weight": "consolidated-00011-of-00022.pth",
|
545 |
+
"layers.59.attention_norm.weight": "consolidated-00011-of-00022.pth",
|
546 |
+
"layers.59.ffn_norm.weight": "consolidated-00011-of-00022.pth",
|
547 |
+
"layers.60.attention.wq.weight": "consolidated-00011-of-00022.pth",
|
548 |
+
"layers.60.attention.wk.weight": "consolidated-00011-of-00022.pth",
|
549 |
+
"layers.60.attention.wv.weight": "consolidated-00011-of-00022.pth",
|
550 |
+
"layers.60.attention.wo.weight": "consolidated-00011-of-00022.pth",
|
551 |
+
"layers.60.feed_forward.w1.weight": "consolidated-00011-of-00022.pth",
|
552 |
+
"layers.60.feed_forward.w3.weight": "consolidated-00011-of-00022.pth",
|
553 |
+
"layers.60.feed_forward.w2.weight": "consolidated-00011-of-00022.pth",
|
554 |
+
"layers.60.attention_norm.weight": "consolidated-00011-of-00022.pth",
|
555 |
+
"layers.60.ffn_norm.weight": "consolidated-00011-of-00022.pth",
|
556 |
+
"layers.61.attention.wq.weight": "consolidated-00011-of-00022.pth",
|
557 |
+
"layers.61.attention.wk.weight": "consolidated-00011-of-00022.pth",
|
558 |
+
"layers.61.attention.wv.weight": "consolidated-00011-of-00022.pth",
|
559 |
+
"layers.61.attention.wo.weight": "consolidated-00011-of-00022.pth",
|
560 |
+
"layers.61.feed_forward.w1.weight": "consolidated-00011-of-00022.pth",
|
561 |
+
"layers.61.feed_forward.w3.weight": "consolidated-00011-of-00022.pth",
|
562 |
+
"layers.61.feed_forward.w2.weight": "consolidated-00011-of-00022.pth",
|
563 |
+
"layers.61.attention_norm.weight": "consolidated-00011-of-00022.pth",
|
564 |
+
"layers.61.ffn_norm.weight": "consolidated-00011-of-00022.pth",
|
565 |
+
"layers.62.attention.wq.weight": "consolidated-00011-of-00022.pth",
|
566 |
+
"layers.62.attention.wk.weight": "consolidated-00011-of-00022.pth",
|
567 |
+
"layers.62.attention.wv.weight": "consolidated-00011-of-00022.pth",
|
568 |
+
"layers.62.attention.wo.weight": "consolidated-00011-of-00022.pth",
|
569 |
+
"layers.62.feed_forward.w1.weight": "consolidated-00011-of-00022.pth",
|
570 |
+
"layers.62.feed_forward.w3.weight": "consolidated-00011-of-00022.pth",
|
571 |
+
"layers.62.feed_forward.w2.weight": "consolidated-00011-of-00022.pth",
|
572 |
+
"layers.62.attention_norm.weight": "consolidated-00011-of-00022.pth",
|
573 |
+
"layers.62.ffn_norm.weight": "consolidated-00011-of-00022.pth",
|
574 |
+
"layers.63.attention.wq.weight": "consolidated-00011-of-00022.pth",
|
575 |
+
"layers.63.attention.wk.weight": "consolidated-00011-of-00022.pth",
|
576 |
+
"layers.63.attention.wv.weight": "consolidated-00011-of-00022.pth",
|
577 |
+
"layers.63.attention.wo.weight": "consolidated-00011-of-00022.pth",
|
578 |
+
"layers.63.feed_forward.w1.weight": "consolidated-00011-of-00022.pth",
|
579 |
+
"layers.63.feed_forward.w3.weight": "consolidated-00011-of-00022.pth",
|
580 |
+
"layers.63.feed_forward.w2.weight": "consolidated-00011-of-00022.pth",
|
581 |
+
"layers.63.attention_norm.weight": "consolidated-00011-of-00022.pth",
|
582 |
+
"layers.63.ffn_norm.weight": "consolidated-00011-of-00022.pth",
|
583 |
+
"layers.64.attention.wq.weight": "consolidated-00011-of-00022.pth",
|
584 |
+
"layers.64.attention.wk.weight": "consolidated-00011-of-00022.pth",
|
585 |
+
"layers.64.attention.wv.weight": "consolidated-00011-of-00022.pth",
|
586 |
+
"layers.64.attention.wo.weight": "consolidated-00011-of-00022.pth",
|
587 |
+
"layers.64.feed_forward.w1.weight": "consolidated-00011-of-00022.pth",
|
588 |
+
"layers.64.feed_forward.w3.weight": "consolidated-00011-of-00022.pth",
|
589 |
+
"layers.64.feed_forward.w2.weight": "consolidated-00011-of-00022.pth",
|
590 |
+
"layers.64.attention_norm.weight": "consolidated-00011-of-00022.pth",
|
591 |
+
"layers.64.ffn_norm.weight": "consolidated-00011-of-00022.pth",
|
592 |
+
"layers.65.attention.wq.weight": "consolidated-00011-of-00022.pth",
|
593 |
+
"layers.65.attention.wk.weight": "consolidated-00011-of-00022.pth",
|
594 |
+
"layers.65.attention.wv.weight": "consolidated-00011-of-00022.pth",
|
595 |
+
"layers.65.attention.wo.weight": "consolidated-00011-of-00022.pth",
|
596 |
+
"layers.65.feed_forward.w1.weight": "consolidated-00011-of-00022.pth",
|
597 |
+
"layers.65.feed_forward.w3.weight": "consolidated-00012-of-00022.pth",
|
598 |
+
"layers.65.feed_forward.w2.weight": "consolidated-00012-of-00022.pth",
|
599 |
+
"layers.65.attention_norm.weight": "consolidated-00012-of-00022.pth",
|
600 |
+
"layers.65.ffn_norm.weight": "consolidated-00012-of-00022.pth",
|
601 |
+
"layers.66.attention.wq.weight": "consolidated-00012-of-00022.pth",
|
602 |
+
"layers.66.attention.wk.weight": "consolidated-00012-of-00022.pth",
|
603 |
+
"layers.66.attention.wv.weight": "consolidated-00012-of-00022.pth",
|
604 |
+
"layers.66.attention.wo.weight": "consolidated-00012-of-00022.pth",
|
605 |
+
"layers.66.feed_forward.w1.weight": "consolidated-00012-of-00022.pth",
|
606 |
+
"layers.66.feed_forward.w3.weight": "consolidated-00012-of-00022.pth",
|
607 |
+
"layers.66.feed_forward.w2.weight": "consolidated-00012-of-00022.pth",
|
608 |
+
"layers.66.attention_norm.weight": "consolidated-00012-of-00022.pth",
|
609 |
+
"layers.66.ffn_norm.weight": "consolidated-00012-of-00022.pth",
|
610 |
+
"layers.67.attention.wq.weight": "consolidated-00012-of-00022.pth",
|
611 |
+
"layers.67.attention.wk.weight": "consolidated-00012-of-00022.pth",
|
612 |
+
"layers.67.attention.wv.weight": "consolidated-00012-of-00022.pth",
|
613 |
+
"layers.67.attention.wo.weight": "consolidated-00012-of-00022.pth",
|
614 |
+
"layers.67.feed_forward.w1.weight": "consolidated-00012-of-00022.pth",
|
615 |
+
"layers.67.feed_forward.w3.weight": "consolidated-00012-of-00022.pth",
|
616 |
+
"layers.67.feed_forward.w2.weight": "consolidated-00012-of-00022.pth",
|
617 |
+
"layers.67.attention_norm.weight": "consolidated-00012-of-00022.pth",
|
618 |
+
"layers.67.ffn_norm.weight": "consolidated-00012-of-00022.pth",
|
619 |
+
"layers.68.attention.wq.weight": "consolidated-00012-of-00022.pth",
|
620 |
+
"layers.68.attention.wk.weight": "consolidated-00012-of-00022.pth",
|
621 |
+
"layers.68.attention.wv.weight": "consolidated-00012-of-00022.pth",
|
622 |
+
"layers.68.attention.wo.weight": "consolidated-00012-of-00022.pth",
|
623 |
+
"layers.68.feed_forward.w1.weight": "consolidated-00012-of-00022.pth",
|
624 |
+
"layers.68.feed_forward.w3.weight": "consolidated-00012-of-00022.pth",
|
625 |
+
"layers.68.feed_forward.w2.weight": "consolidated-00012-of-00022.pth",
|
626 |
+
"layers.68.attention_norm.weight": "consolidated-00012-of-00022.pth",
|
627 |
+
"layers.68.ffn_norm.weight": "consolidated-00012-of-00022.pth",
|
628 |
+
"layers.69.attention.wq.weight": "consolidated-00012-of-00022.pth",
|
629 |
+
"layers.69.attention.wk.weight": "consolidated-00012-of-00022.pth",
|
630 |
+
"layers.69.attention.wv.weight": "consolidated-00012-of-00022.pth",
|
631 |
+
"layers.69.attention.wo.weight": "consolidated-00012-of-00022.pth",
|
632 |
+
"layers.69.feed_forward.w1.weight": "consolidated-00012-of-00022.pth",
|
633 |
+
"layers.69.feed_forward.w3.weight": "consolidated-00012-of-00022.pth",
|
634 |
+
"layers.69.feed_forward.w2.weight": "consolidated-00012-of-00022.pth",
|
635 |
+
"layers.69.attention_norm.weight": "consolidated-00012-of-00022.pth",
|
636 |
+
"layers.69.ffn_norm.weight": "consolidated-00012-of-00022.pth",
|
637 |
+
"layers.70.attention.wq.weight": "consolidated-00012-of-00022.pth",
|
638 |
+
"layers.70.attention.wk.weight": "consolidated-00012-of-00022.pth",
|
639 |
+
"layers.70.attention.wv.weight": "consolidated-00012-of-00022.pth",
|
640 |
+
"layers.70.attention.wo.weight": "consolidated-00012-of-00022.pth",
|
641 |
+
"layers.70.feed_forward.w1.weight": "consolidated-00012-of-00022.pth",
|
642 |
+
"layers.70.feed_forward.w3.weight": "consolidated-00012-of-00022.pth",
|
643 |
+
"layers.70.feed_forward.w2.weight": "consolidated-00012-of-00022.pth",
|
644 |
+
"layers.70.attention_norm.weight": "consolidated-00012-of-00022.pth",
|
645 |
+
"layers.70.ffn_norm.weight": "consolidated-00012-of-00022.pth",
|
646 |
+
"layers.71.attention.wq.weight": "consolidated-00012-of-00022.pth",
|
647 |
+
"layers.71.attention.wk.weight": "consolidated-00012-of-00022.pth",
|
648 |
+
"layers.71.attention.wv.weight": "consolidated-00012-of-00022.pth",
|
649 |
+
"layers.71.attention.wo.weight": "consolidated-00012-of-00022.pth",
|
650 |
+
"layers.71.feed_forward.w1.weight": "consolidated-00012-of-00022.pth",
|
651 |
+
"layers.71.feed_forward.w3.weight": "consolidated-00013-of-00022.pth",
|
652 |
+
"layers.71.feed_forward.w2.weight": "consolidated-00013-of-00022.pth",
|
653 |
+
"layers.71.attention_norm.weight": "consolidated-00013-of-00022.pth",
|
654 |
+
"layers.71.ffn_norm.weight": "consolidated-00013-of-00022.pth",
|
655 |
+
"layers.72.attention.wq.weight": "consolidated-00013-of-00022.pth",
|
656 |
+
"layers.72.attention.wk.weight": "consolidated-00013-of-00022.pth",
|
657 |
+
"layers.72.attention.wv.weight": "consolidated-00013-of-00022.pth",
|
658 |
+
"layers.72.attention.wo.weight": "consolidated-00013-of-00022.pth",
|
659 |
+
"layers.72.feed_forward.w1.weight": "consolidated-00013-of-00022.pth",
|
660 |
+
"layers.72.feed_forward.w3.weight": "consolidated-00013-of-00022.pth",
|
661 |
+
"layers.72.feed_forward.w2.weight": "consolidated-00013-of-00022.pth",
|
662 |
+
"layers.72.attention_norm.weight": "consolidated-00013-of-00022.pth",
|
663 |
+
"layers.72.ffn_norm.weight": "consolidated-00013-of-00022.pth",
|
664 |
+
"layers.73.attention.wq.weight": "consolidated-00013-of-00022.pth",
|
665 |
+
"layers.73.attention.wk.weight": "consolidated-00013-of-00022.pth",
|
666 |
+
"layers.73.attention.wv.weight": "consolidated-00013-of-00022.pth",
|
667 |
+
"layers.73.attention.wo.weight": "consolidated-00013-of-00022.pth",
|
668 |
+
"layers.73.feed_forward.w1.weight": "consolidated-00013-of-00022.pth",
|
669 |
+
"layers.73.feed_forward.w3.weight": "consolidated-00013-of-00022.pth",
|
670 |
+
"layers.73.feed_forward.w2.weight": "consolidated-00013-of-00022.pth",
|
671 |
+
"layers.73.attention_norm.weight": "consolidated-00013-of-00022.pth",
|
672 |
+
"layers.73.ffn_norm.weight": "consolidated-00013-of-00022.pth",
|
673 |
+
"layers.74.attention.wq.weight": "consolidated-00013-of-00022.pth",
|
674 |
+
"layers.74.attention.wk.weight": "consolidated-00013-of-00022.pth",
|
675 |
+
"layers.74.attention.wv.weight": "consolidated-00013-of-00022.pth",
|
676 |
+
"layers.74.attention.wo.weight": "consolidated-00013-of-00022.pth",
|
677 |
+
"layers.74.feed_forward.w1.weight": "consolidated-00013-of-00022.pth",
|
678 |
+
"layers.74.feed_forward.w3.weight": "consolidated-00013-of-00022.pth",
|
679 |
+
"layers.74.feed_forward.w2.weight": "consolidated-00013-of-00022.pth",
|
680 |
+
"layers.74.attention_norm.weight": "consolidated-00013-of-00022.pth",
|
681 |
+
"layers.74.ffn_norm.weight": "consolidated-00013-of-00022.pth",
|
682 |
+
"layers.75.attention.wq.weight": "consolidated-00013-of-00022.pth",
|
683 |
+
"layers.75.attention.wk.weight": "consolidated-00013-of-00022.pth",
|
684 |
+
"layers.75.attention.wv.weight": "consolidated-00013-of-00022.pth",
|
685 |
+
"layers.75.attention.wo.weight": "consolidated-00013-of-00022.pth",
|
686 |
+
"layers.75.feed_forward.w1.weight": "consolidated-00013-of-00022.pth",
|
687 |
+
"layers.75.feed_forward.w3.weight": "consolidated-00013-of-00022.pth",
|
688 |
+
"layers.75.feed_forward.w2.weight": "consolidated-00013-of-00022.pth",
|
689 |
+
"layers.75.attention_norm.weight": "consolidated-00013-of-00022.pth",
|
690 |
+
"layers.75.ffn_norm.weight": "consolidated-00013-of-00022.pth",
|
691 |
+
"layers.76.attention.wq.weight": "consolidated-00013-of-00022.pth",
|
692 |
+
"layers.76.attention.wk.weight": "consolidated-00013-of-00022.pth",
|
693 |
+
"layers.76.attention.wv.weight": "consolidated-00013-of-00022.pth",
|
694 |
+
"layers.76.attention.wo.weight": "consolidated-00013-of-00022.pth",
|
695 |
+
"layers.76.feed_forward.w1.weight": "consolidated-00013-of-00022.pth",
|
696 |
+
"layers.76.feed_forward.w3.weight": "consolidated-00013-of-00022.pth",
|
697 |
+
"layers.76.feed_forward.w2.weight": "consolidated-00013-of-00022.pth",
|
698 |
+
"layers.76.attention_norm.weight": "consolidated-00013-of-00022.pth",
|
699 |
+
"layers.76.ffn_norm.weight": "consolidated-00013-of-00022.pth",
|
700 |
+
"layers.77.attention.wq.weight": "consolidated-00013-of-00022.pth",
|
701 |
+
"layers.77.attention.wk.weight": "consolidated-00013-of-00022.pth",
|
702 |
+
"layers.77.attention.wv.weight": "consolidated-00013-of-00022.pth",
|
703 |
+
"layers.77.attention.wo.weight": "consolidated-00013-of-00022.pth",
|
704 |
+
"layers.77.feed_forward.w1.weight": "consolidated-00013-of-00022.pth",
|
705 |
+
"layers.77.feed_forward.w3.weight": "consolidated-00014-of-00022.pth",
|
706 |
+
"layers.77.feed_forward.w2.weight": "consolidated-00014-of-00022.pth",
|
707 |
+
"layers.77.attention_norm.weight": "consolidated-00014-of-00022.pth",
|
708 |
+
"layers.77.ffn_norm.weight": "consolidated-00014-of-00022.pth",
|
709 |
+
"layers.78.attention.wq.weight": "consolidated-00014-of-00022.pth",
|
710 |
+
"layers.78.attention.wk.weight": "consolidated-00014-of-00022.pth",
|
711 |
+
"layers.78.attention.wv.weight": "consolidated-00014-of-00022.pth",
|
712 |
+
"layers.78.attention.wo.weight": "consolidated-00014-of-00022.pth",
|
713 |
+
"layers.78.feed_forward.w1.weight": "consolidated-00014-of-00022.pth",
|
714 |
+
"layers.78.feed_forward.w3.weight": "consolidated-00014-of-00022.pth",
|
715 |
+
"layers.78.feed_forward.w2.weight": "consolidated-00014-of-00022.pth",
|
716 |
+
"layers.78.attention_norm.weight": "consolidated-00014-of-00022.pth",
|
717 |
+
"layers.78.ffn_norm.weight": "consolidated-00014-of-00022.pth",
|
718 |
+
"layers.79.attention.wq.weight": "consolidated-00014-of-00022.pth",
|
719 |
+
"layers.79.attention.wk.weight": "consolidated-00014-of-00022.pth",
|
720 |
+
"layers.79.attention.wv.weight": "consolidated-00014-of-00022.pth",
|
721 |
+
"layers.79.attention.wo.weight": "consolidated-00014-of-00022.pth",
|
722 |
+
"layers.79.feed_forward.w1.weight": "consolidated-00014-of-00022.pth",
|
723 |
+
"layers.79.feed_forward.w3.weight": "consolidated-00014-of-00022.pth",
|
724 |
+
"layers.79.feed_forward.w2.weight": "consolidated-00014-of-00022.pth",
|
725 |
+
"layers.79.attention_norm.weight": "consolidated-00014-of-00022.pth",
|
726 |
+
"layers.79.ffn_norm.weight": "consolidated-00014-of-00022.pth",
|
727 |
+
"layers.80.attention.wq.weight": "consolidated-00014-of-00022.pth",
|
728 |
+
"layers.80.attention.wk.weight": "consolidated-00014-of-00022.pth",
|
729 |
+
"layers.80.attention.wv.weight": "consolidated-00014-of-00022.pth",
|
730 |
+
"layers.80.attention.wo.weight": "consolidated-00014-of-00022.pth",
|
731 |
+
"layers.80.feed_forward.w1.weight": "consolidated-00014-of-00022.pth",
|
732 |
+
"layers.80.feed_forward.w3.weight": "consolidated-00014-of-00022.pth",
|
733 |
+
"layers.80.feed_forward.w2.weight": "consolidated-00014-of-00022.pth",
|
734 |
+
"layers.80.attention_norm.weight": "consolidated-00014-of-00022.pth",
|
735 |
+
"layers.80.ffn_norm.weight": "consolidated-00014-of-00022.pth",
|
736 |
+
"layers.81.attention.wq.weight": "consolidated-00014-of-00022.pth",
|
737 |
+
"layers.81.attention.wk.weight": "consolidated-00014-of-00022.pth",
|
738 |
+
"layers.81.attention.wv.weight": "consolidated-00014-of-00022.pth",
|
739 |
+
"layers.81.attention.wo.weight": "consolidated-00014-of-00022.pth",
|
740 |
+
"layers.81.feed_forward.w1.weight": "consolidated-00014-of-00022.pth",
|
741 |
+
"layers.81.feed_forward.w3.weight": "consolidated-00014-of-00022.pth",
|
742 |
+
"layers.81.feed_forward.w2.weight": "consolidated-00014-of-00022.pth",
|
743 |
+
"layers.81.attention_norm.weight": "consolidated-00014-of-00022.pth",
|
744 |
+
"layers.81.ffn_norm.weight": "consolidated-00014-of-00022.pth",
|
745 |
+
"layers.82.attention.wq.weight": "consolidated-00014-of-00022.pth",
|
746 |
+
"layers.82.attention.wk.weight": "consolidated-00014-of-00022.pth",
|
747 |
+
"layers.82.attention.wv.weight": "consolidated-00014-of-00022.pth",
|
748 |
+
"layers.82.attention.wo.weight": "consolidated-00014-of-00022.pth",
|
749 |
+
"layers.82.feed_forward.w1.weight": "consolidated-00014-of-00022.pth",
|
750 |
+
"layers.82.feed_forward.w3.weight": "consolidated-00014-of-00022.pth",
|
751 |
+
"layers.82.feed_forward.w2.weight": "consolidated-00014-of-00022.pth",
|
752 |
+
"layers.82.attention_norm.weight": "consolidated-00014-of-00022.pth",
|
753 |
+
"layers.82.ffn_norm.weight": "consolidated-00014-of-00022.pth",
|
754 |
+
"layers.83.attention.wq.weight": "consolidated-00014-of-00022.pth",
|
755 |
+
"layers.83.attention.wk.weight": "consolidated-00014-of-00022.pth",
|
756 |
+
"layers.83.attention.wv.weight": "consolidated-00014-of-00022.pth",
|
757 |
+
"layers.83.attention.wo.weight": "consolidated-00014-of-00022.pth",
|
758 |
+
"layers.83.feed_forward.w1.weight": "consolidated-00014-of-00022.pth",
|
759 |
+
"layers.83.feed_forward.w3.weight": "consolidated-00015-of-00022.pth",
|
760 |
+
"layers.83.feed_forward.w2.weight": "consolidated-00015-of-00022.pth",
|
761 |
+
"layers.83.attention_norm.weight": "consolidated-00015-of-00022.pth",
|
762 |
+
"layers.83.ffn_norm.weight": "consolidated-00015-of-00022.pth",
|
763 |
+
"layers.84.attention.wq.weight": "consolidated-00015-of-00022.pth",
|
764 |
+
"layers.84.attention.wk.weight": "consolidated-00015-of-00022.pth",
|
765 |
+
"layers.84.attention.wv.weight": "consolidated-00015-of-00022.pth",
|
766 |
+
"layers.84.attention.wo.weight": "consolidated-00015-of-00022.pth",
|
767 |
+
"layers.84.feed_forward.w1.weight": "consolidated-00015-of-00022.pth",
|
768 |
+
"layers.84.feed_forward.w3.weight": "consolidated-00015-of-00022.pth",
|
769 |
+
"layers.84.feed_forward.w2.weight": "consolidated-00015-of-00022.pth",
|
770 |
+
"layers.84.attention_norm.weight": "consolidated-00015-of-00022.pth",
|
771 |
+
"layers.84.ffn_norm.weight": "consolidated-00015-of-00022.pth",
|
772 |
+
"layers.85.attention.wq.weight": "consolidated-00015-of-00022.pth",
|
773 |
+
"layers.85.attention.wk.weight": "consolidated-00015-of-00022.pth",
|
774 |
+
"layers.85.attention.wv.weight": "consolidated-00015-of-00022.pth",
|
775 |
+
"layers.85.attention.wo.weight": "consolidated-00015-of-00022.pth",
|
776 |
+
"layers.85.feed_forward.w1.weight": "consolidated-00015-of-00022.pth",
|
777 |
+
"layers.85.feed_forward.w3.weight": "consolidated-00015-of-00022.pth",
|
778 |
+
"layers.85.feed_forward.w2.weight": "consolidated-00015-of-00022.pth",
|
779 |
+
"layers.85.attention_norm.weight": "consolidated-00015-of-00022.pth",
|
780 |
+
"layers.85.ffn_norm.weight": "consolidated-00015-of-00022.pth",
|
781 |
+
"layers.86.attention.wq.weight": "consolidated-00015-of-00022.pth",
|
782 |
+
"layers.86.attention.wk.weight": "consolidated-00015-of-00022.pth",
|
783 |
+
"layers.86.attention.wv.weight": "consolidated-00015-of-00022.pth",
|
784 |
+
"layers.86.attention.wo.weight": "consolidated-00015-of-00022.pth",
|
785 |
+
"layers.86.feed_forward.w1.weight": "consolidated-00015-of-00022.pth",
|
786 |
+
"layers.86.feed_forward.w3.weight": "consolidated-00015-of-00022.pth",
|
787 |
+
"layers.86.feed_forward.w2.weight": "consolidated-00015-of-00022.pth",
|
788 |
+
"layers.86.attention_norm.weight": "consolidated-00015-of-00022.pth",
|
789 |
+
"layers.86.ffn_norm.weight": "consolidated-00015-of-00022.pth",
|
790 |
+
"layers.87.attention.wq.weight": "consolidated-00015-of-00022.pth",
|
791 |
+
"layers.87.attention.wk.weight": "consolidated-00015-of-00022.pth",
|
792 |
+
"layers.87.attention.wv.weight": "consolidated-00015-of-00022.pth",
|
793 |
+
"layers.87.attention.wo.weight": "consolidated-00015-of-00022.pth",
|
794 |
+
"layers.87.feed_forward.w1.weight": "consolidated-00015-of-00022.pth",
|
795 |
+
"layers.87.feed_forward.w3.weight": "consolidated-00015-of-00022.pth",
|
796 |
+
"layers.87.feed_forward.w2.weight": "consolidated-00015-of-00022.pth",
|
797 |
+
"layers.87.attention_norm.weight": "consolidated-00015-of-00022.pth",
|
798 |
+
"layers.87.ffn_norm.weight": "consolidated-00015-of-00022.pth",
|
799 |
+
"layers.88.attention.wq.weight": "consolidated-00015-of-00022.pth",
|
800 |
+
"layers.88.attention.wk.weight": "consolidated-00015-of-00022.pth",
|
801 |
+
"layers.88.attention.wv.weight": "consolidated-00015-of-00022.pth",
|
802 |
+
"layers.88.attention.wo.weight": "consolidated-00015-of-00022.pth",
|
803 |
+
"layers.88.feed_forward.w1.weight": "consolidated-00015-of-00022.pth",
|
804 |
+
"layers.88.feed_forward.w3.weight": "consolidated-00015-of-00022.pth",
|
805 |
+
"layers.88.feed_forward.w2.weight": "consolidated-00015-of-00022.pth",
|
806 |
+
"layers.88.attention_norm.weight": "consolidated-00015-of-00022.pth",
|
807 |
+
"layers.88.ffn_norm.weight": "consolidated-00015-of-00022.pth",
|
808 |
+
"layers.89.attention.wq.weight": "consolidated-00015-of-00022.pth",
|
809 |
+
"layers.89.attention.wk.weight": "consolidated-00015-of-00022.pth",
|
810 |
+
"layers.89.attention.wv.weight": "consolidated-00015-of-00022.pth",
|
811 |
+
"layers.89.attention.wo.weight": "consolidated-00015-of-00022.pth",
|
812 |
+
"layers.89.feed_forward.w1.weight": "consolidated-00015-of-00022.pth",
|
813 |
+
"layers.89.feed_forward.w3.weight": "consolidated-00016-of-00022.pth",
|
814 |
+
"layers.89.feed_forward.w2.weight": "consolidated-00016-of-00022.pth",
|
815 |
+
"layers.89.attention_norm.weight": "consolidated-00016-of-00022.pth",
|
816 |
+
"layers.89.ffn_norm.weight": "consolidated-00016-of-00022.pth",
|
817 |
+
"layers.90.attention.wq.weight": "consolidated-00016-of-00022.pth",
|
818 |
+
"layers.90.attention.wk.weight": "consolidated-00016-of-00022.pth",
|
819 |
+
"layers.90.attention.wv.weight": "consolidated-00016-of-00022.pth",
|
820 |
+
"layers.90.attention.wo.weight": "consolidated-00016-of-00022.pth",
|
821 |
+
"layers.90.feed_forward.w1.weight": "consolidated-00016-of-00022.pth",
|
822 |
+
"layers.90.feed_forward.w3.weight": "consolidated-00016-of-00022.pth",
|
823 |
+
"layers.90.feed_forward.w2.weight": "consolidated-00016-of-00022.pth",
|
824 |
+
"layers.90.attention_norm.weight": "consolidated-00016-of-00022.pth",
|
825 |
+
"layers.90.ffn_norm.weight": "consolidated-00016-of-00022.pth",
|
826 |
+
"layers.91.attention.wq.weight": "consolidated-00016-of-00022.pth",
|
827 |
+
"layers.91.attention.wk.weight": "consolidated-00016-of-00022.pth",
|
828 |
+
"layers.91.attention.wv.weight": "consolidated-00016-of-00022.pth",
|
829 |
+
"layers.91.attention.wo.weight": "consolidated-00016-of-00022.pth",
|
830 |
+
"layers.91.feed_forward.w1.weight": "consolidated-00016-of-00022.pth",
|
831 |
+
"layers.91.feed_forward.w3.weight": "consolidated-00016-of-00022.pth",
|
832 |
+
"layers.91.feed_forward.w2.weight": "consolidated-00016-of-00022.pth",
|
833 |
+
"layers.91.attention_norm.weight": "consolidated-00016-of-00022.pth",
|
834 |
+
"layers.91.ffn_norm.weight": "consolidated-00016-of-00022.pth",
|
835 |
+
"layers.92.attention.wq.weight": "consolidated-00016-of-00022.pth",
|
836 |
+
"layers.92.attention.wk.weight": "consolidated-00016-of-00022.pth",
|
837 |
+
"layers.92.attention.wv.weight": "consolidated-00016-of-00022.pth",
|
838 |
+
"layers.92.attention.wo.weight": "consolidated-00016-of-00022.pth",
|
839 |
+
"layers.92.feed_forward.w1.weight": "consolidated-00016-of-00022.pth",
|
840 |
+
"layers.92.feed_forward.w3.weight": "consolidated-00016-of-00022.pth",
|
841 |
+
"layers.92.feed_forward.w2.weight": "consolidated-00016-of-00022.pth",
|
842 |
+
"layers.92.attention_norm.weight": "consolidated-00016-of-00022.pth",
|
843 |
+
"layers.92.ffn_norm.weight": "consolidated-00016-of-00022.pth",
|
844 |
+
"layers.93.attention.wq.weight": "consolidated-00016-of-00022.pth",
|
845 |
+
"layers.93.attention.wk.weight": "consolidated-00016-of-00022.pth",
|
846 |
+
"layers.93.attention.wv.weight": "consolidated-00016-of-00022.pth",
|
847 |
+
"layers.93.attention.wo.weight": "consolidated-00016-of-00022.pth",
|
848 |
+
"layers.93.feed_forward.w1.weight": "consolidated-00016-of-00022.pth",
|
849 |
+
"layers.93.feed_forward.w3.weight": "consolidated-00016-of-00022.pth",
|
850 |
+
"layers.93.feed_forward.w2.weight": "consolidated-00016-of-00022.pth",
|
851 |
+
"layers.93.attention_norm.weight": "consolidated-00016-of-00022.pth",
|
852 |
+
"layers.93.ffn_norm.weight": "consolidated-00016-of-00022.pth",
|
853 |
+
"layers.94.attention.wq.weight": "consolidated-00016-of-00022.pth",
|
854 |
+
"layers.94.attention.wk.weight": "consolidated-00016-of-00022.pth",
|
855 |
+
"layers.94.attention.wv.weight": "consolidated-00016-of-00022.pth",
|
856 |
+
"layers.94.attention.wo.weight": "consolidated-00016-of-00022.pth",
|
857 |
+
"layers.94.feed_forward.w1.weight": "consolidated-00016-of-00022.pth",
|
858 |
+
"layers.94.feed_forward.w3.weight": "consolidated-00016-of-00022.pth",
|
859 |
+
"layers.94.feed_forward.w2.weight": "consolidated-00016-of-00022.pth",
|
860 |
+
"layers.94.attention_norm.weight": "consolidated-00016-of-00022.pth",
|
861 |
+
"layers.94.ffn_norm.weight": "consolidated-00016-of-00022.pth",
|
862 |
+
"layers.95.attention.wq.weight": "consolidated-00016-of-00022.pth",
|
863 |
+
"layers.95.attention.wk.weight": "consolidated-00016-of-00022.pth",
|
864 |
+
"layers.95.attention.wv.weight": "consolidated-00016-of-00022.pth",
|
865 |
+
"layers.95.attention.wo.weight": "consolidated-00016-of-00022.pth",
|
866 |
+
"layers.95.feed_forward.w1.weight": "consolidated-00016-of-00022.pth",
|
867 |
+
"layers.95.feed_forward.w3.weight": "consolidated-00017-of-00022.pth",
|
868 |
+
"layers.95.feed_forward.w2.weight": "consolidated-00017-of-00022.pth",
|
869 |
+
"layers.95.attention_norm.weight": "consolidated-00017-of-00022.pth",
|
870 |
+
"layers.95.ffn_norm.weight": "consolidated-00017-of-00022.pth",
|
871 |
+
"layers.96.attention.wq.weight": "consolidated-00017-of-00022.pth",
|
872 |
+
"layers.96.attention.wk.weight": "consolidated-00017-of-00022.pth",
|
873 |
+
"layers.96.attention.wv.weight": "consolidated-00017-of-00022.pth",
|
874 |
+
"layers.96.attention.wo.weight": "consolidated-00017-of-00022.pth",
|
875 |
+
"layers.96.feed_forward.w1.weight": "consolidated-00017-of-00022.pth",
|
876 |
+
"layers.96.feed_forward.w3.weight": "consolidated-00017-of-00022.pth",
|
877 |
+
"layers.96.feed_forward.w2.weight": "consolidated-00017-of-00022.pth",
|
878 |
+
"layers.96.attention_norm.weight": "consolidated-00017-of-00022.pth",
|
879 |
+
"layers.96.ffn_norm.weight": "consolidated-00017-of-00022.pth",
|
880 |
+
"layers.97.attention.wq.weight": "consolidated-00017-of-00022.pth",
|
881 |
+
"layers.97.attention.wk.weight": "consolidated-00017-of-00022.pth",
|
882 |
+
"layers.97.attention.wv.weight": "consolidated-00017-of-00022.pth",
|
883 |
+
"layers.97.attention.wo.weight": "consolidated-00017-of-00022.pth",
|
884 |
+
"layers.97.feed_forward.w1.weight": "consolidated-00017-of-00022.pth",
|
885 |
+
"layers.97.feed_forward.w3.weight": "consolidated-00017-of-00022.pth",
|
886 |
+
"layers.97.feed_forward.w2.weight": "consolidated-00017-of-00022.pth",
|
887 |
+
"layers.97.attention_norm.weight": "consolidated-00017-of-00022.pth",
|
888 |
+
"layers.97.ffn_norm.weight": "consolidated-00017-of-00022.pth",
|
889 |
+
"layers.98.attention.wq.weight": "consolidated-00017-of-00022.pth",
|
890 |
+
"layers.98.attention.wk.weight": "consolidated-00017-of-00022.pth",
|
891 |
+
"layers.98.attention.wv.weight": "consolidated-00017-of-00022.pth",
|
892 |
+
"layers.98.attention.wo.weight": "consolidated-00017-of-00022.pth",
|
893 |
+
"layers.98.feed_forward.w1.weight": "consolidated-00017-of-00022.pth",
|
894 |
+
"layers.98.feed_forward.w3.weight": "consolidated-00017-of-00022.pth",
|
895 |
+
"layers.98.feed_forward.w2.weight": "consolidated-00017-of-00022.pth",
|
896 |
+
"layers.98.attention_norm.weight": "consolidated-00017-of-00022.pth",
|
897 |
+
"layers.98.ffn_norm.weight": "consolidated-00017-of-00022.pth",
|
898 |
+
"layers.99.attention.wq.weight": "consolidated-00017-of-00022.pth",
|
899 |
+
"layers.99.attention.wk.weight": "consolidated-00017-of-00022.pth",
|
900 |
+
"layers.99.attention.wv.weight": "consolidated-00017-of-00022.pth",
|
901 |
+
"layers.99.attention.wo.weight": "consolidated-00017-of-00022.pth",
|
902 |
+
"layers.99.feed_forward.w1.weight": "consolidated-00017-of-00022.pth",
|
903 |
+
"layers.99.feed_forward.w3.weight": "consolidated-00017-of-00022.pth",
|
904 |
+
"layers.99.feed_forward.w2.weight": "consolidated-00017-of-00022.pth",
|
905 |
+
"layers.99.attention_norm.weight": "consolidated-00017-of-00022.pth",
|
906 |
+
"layers.99.ffn_norm.weight": "consolidated-00017-of-00022.pth",
|
907 |
+
"layers.100.attention.wq.weight": "consolidated-00017-of-00022.pth",
|
908 |
+
"layers.100.attention.wk.weight": "consolidated-00017-of-00022.pth",
|
909 |
+
"layers.100.attention.wv.weight": "consolidated-00017-of-00022.pth",
|
910 |
+
"layers.100.attention.wo.weight": "consolidated-00017-of-00022.pth",
|
911 |
+
"layers.100.feed_forward.w1.weight": "consolidated-00017-of-00022.pth",
|
912 |
+
"layers.100.feed_forward.w3.weight": "consolidated-00017-of-00022.pth",
|
913 |
+
"layers.100.feed_forward.w2.weight": "consolidated-00017-of-00022.pth",
|
914 |
+
"layers.100.attention_norm.weight": "consolidated-00017-of-00022.pth",
|
915 |
+
"layers.100.ffn_norm.weight": "consolidated-00017-of-00022.pth",
|
916 |
+
"layers.101.attention.wq.weight": "consolidated-00017-of-00022.pth",
|
917 |
+
"layers.101.attention.wk.weight": "consolidated-00017-of-00022.pth",
|
918 |
+
"layers.101.attention.wv.weight": "consolidated-00017-of-00022.pth",
|
919 |
+
"layers.101.attention.wo.weight": "consolidated-00017-of-00022.pth",
|
920 |
+
"layers.101.feed_forward.w1.weight": "consolidated-00017-of-00022.pth",
|
921 |
+
"layers.101.feed_forward.w3.weight": "consolidated-00018-of-00022.pth",
|
922 |
+
"layers.101.feed_forward.w2.weight": "consolidated-00018-of-00022.pth",
|
923 |
+
"layers.101.attention_norm.weight": "consolidated-00018-of-00022.pth",
|
924 |
+
"layers.101.ffn_norm.weight": "consolidated-00018-of-00022.pth",
|
925 |
+
"layers.102.attention.wq.weight": "consolidated-00018-of-00022.pth",
|
926 |
+
"layers.102.attention.wk.weight": "consolidated-00018-of-00022.pth",
|
927 |
+
"layers.102.attention.wv.weight": "consolidated-00018-of-00022.pth",
|
928 |
+
"layers.102.attention.wo.weight": "consolidated-00018-of-00022.pth",
|
929 |
+
"layers.102.feed_forward.w1.weight": "consolidated-00018-of-00022.pth",
|
930 |
+
"layers.102.feed_forward.w3.weight": "consolidated-00018-of-00022.pth",
|
931 |
+
"layers.102.feed_forward.w2.weight": "consolidated-00018-of-00022.pth",
|
932 |
+
"layers.102.attention_norm.weight": "consolidated-00018-of-00022.pth",
|
933 |
+
"layers.102.ffn_norm.weight": "consolidated-00018-of-00022.pth",
|
934 |
+
"layers.103.attention.wq.weight": "consolidated-00018-of-00022.pth",
|
935 |
+
"layers.103.attention.wk.weight": "consolidated-00018-of-00022.pth",
|
936 |
+
"layers.103.attention.wv.weight": "consolidated-00018-of-00022.pth",
|
937 |
+
"layers.103.attention.wo.weight": "consolidated-00018-of-00022.pth",
|
938 |
+
"layers.103.feed_forward.w1.weight": "consolidated-00018-of-00022.pth",
|
939 |
+
"layers.103.feed_forward.w3.weight": "consolidated-00018-of-00022.pth",
|
940 |
+
"layers.103.feed_forward.w2.weight": "consolidated-00018-of-00022.pth",
|
941 |
+
"layers.103.attention_norm.weight": "consolidated-00018-of-00022.pth",
|
942 |
+
"layers.103.ffn_norm.weight": "consolidated-00018-of-00022.pth",
|
943 |
+
"layers.104.attention.wq.weight": "consolidated-00018-of-00022.pth",
|
944 |
+
"layers.104.attention.wk.weight": "consolidated-00018-of-00022.pth",
|
945 |
+
"layers.104.attention.wv.weight": "consolidated-00018-of-00022.pth",
|
946 |
+
"layers.104.attention.wo.weight": "consolidated-00018-of-00022.pth",
|
947 |
+
"layers.104.feed_forward.w1.weight": "consolidated-00018-of-00022.pth",
|
948 |
+
"layers.104.feed_forward.w3.weight": "consolidated-00018-of-00022.pth",
|
949 |
+
"layers.104.feed_forward.w2.weight": "consolidated-00018-of-00022.pth",
|
950 |
+
"layers.104.attention_norm.weight": "consolidated-00018-of-00022.pth",
|
951 |
+
"layers.104.ffn_norm.weight": "consolidated-00018-of-00022.pth",
|
952 |
+
"layers.105.attention.wq.weight": "consolidated-00018-of-00022.pth",
|
953 |
+
"layers.105.attention.wk.weight": "consolidated-00018-of-00022.pth",
|
954 |
+
"layers.105.attention.wv.weight": "consolidated-00018-of-00022.pth",
|
955 |
+
"layers.105.attention.wo.weight": "consolidated-00018-of-00022.pth",
|
956 |
+
"layers.105.feed_forward.w1.weight": "consolidated-00018-of-00022.pth",
|
957 |
+
"layers.105.feed_forward.w3.weight": "consolidated-00018-of-00022.pth",
|
958 |
+
"layers.105.feed_forward.w2.weight": "consolidated-00018-of-00022.pth",
|
959 |
+
"layers.105.attention_norm.weight": "consolidated-00018-of-00022.pth",
|
960 |
+
"layers.105.ffn_norm.weight": "consolidated-00018-of-00022.pth",
|
961 |
+
"layers.106.attention.wq.weight": "consolidated-00018-of-00022.pth",
|
962 |
+
"layers.106.attention.wk.weight": "consolidated-00018-of-00022.pth",
|
963 |
+
"layers.106.attention.wv.weight": "consolidated-00018-of-00022.pth",
|
964 |
+
"layers.106.attention.wo.weight": "consolidated-00018-of-00022.pth",
|
965 |
+
"layers.106.feed_forward.w1.weight": "consolidated-00018-of-00022.pth",
|
966 |
+
"layers.106.feed_forward.w3.weight": "consolidated-00018-of-00022.pth",
|
967 |
+
"layers.106.feed_forward.w2.weight": "consolidated-00018-of-00022.pth",
|
968 |
+
"layers.106.attention_norm.weight": "consolidated-00018-of-00022.pth",
|
969 |
+
"layers.106.ffn_norm.weight": "consolidated-00018-of-00022.pth",
|
970 |
+
"layers.107.attention.wq.weight": "consolidated-00018-of-00022.pth",
|
971 |
+
"layers.107.attention.wk.weight": "consolidated-00018-of-00022.pth",
|
972 |
+
"layers.107.attention.wv.weight": "consolidated-00018-of-00022.pth",
|
973 |
+
"layers.107.attention.wo.weight": "consolidated-00018-of-00022.pth",
|
974 |
+
"layers.107.feed_forward.w1.weight": "consolidated-00018-of-00022.pth",
|
975 |
+
"layers.107.feed_forward.w3.weight": "consolidated-00019-of-00022.pth",
|
976 |
+
"layers.107.feed_forward.w2.weight": "consolidated-00019-of-00022.pth",
|
977 |
+
"layers.107.attention_norm.weight": "consolidated-00019-of-00022.pth",
|
978 |
+
"layers.107.ffn_norm.weight": "consolidated-00019-of-00022.pth",
|
979 |
+
"layers.108.attention.wq.weight": "consolidated-00019-of-00022.pth",
|
980 |
+
"layers.108.attention.wk.weight": "consolidated-00019-of-00022.pth",
|
981 |
+
"layers.108.attention.wv.weight": "consolidated-00019-of-00022.pth",
|
982 |
+
"layers.108.attention.wo.weight": "consolidated-00019-of-00022.pth",
|
983 |
+
"layers.108.feed_forward.w1.weight": "consolidated-00019-of-00022.pth",
|
984 |
+
"layers.108.feed_forward.w3.weight": "consolidated-00019-of-00022.pth",
|
985 |
+
"layers.108.feed_forward.w2.weight": "consolidated-00019-of-00022.pth",
|
986 |
+
"layers.108.attention_norm.weight": "consolidated-00019-of-00022.pth",
|
987 |
+
"layers.108.ffn_norm.weight": "consolidated-00019-of-00022.pth",
|
988 |
+
"layers.109.attention.wq.weight": "consolidated-00019-of-00022.pth",
|
989 |
+
"layers.109.attention.wk.weight": "consolidated-00019-of-00022.pth",
|
990 |
+
"layers.109.attention.wv.weight": "consolidated-00019-of-00022.pth",
|
991 |
+
"layers.109.attention.wo.weight": "consolidated-00019-of-00022.pth",
|
992 |
+
"layers.109.feed_forward.w1.weight": "consolidated-00019-of-00022.pth",
|
993 |
+
"layers.109.feed_forward.w3.weight": "consolidated-00019-of-00022.pth",
|
994 |
+
"layers.109.feed_forward.w2.weight": "consolidated-00019-of-00022.pth",
|
995 |
+
"layers.109.attention_norm.weight": "consolidated-00019-of-00022.pth",
|
996 |
+
"layers.109.ffn_norm.weight": "consolidated-00019-of-00022.pth",
|
997 |
+
"layers.110.attention.wq.weight": "consolidated-00019-of-00022.pth",
|
998 |
+
"layers.110.attention.wk.weight": "consolidated-00019-of-00022.pth",
|
999 |
+
"layers.110.attention.wv.weight": "consolidated-00019-of-00022.pth",
|
1000 |
+
"layers.110.attention.wo.weight": "consolidated-00019-of-00022.pth",
|
1001 |
+
"layers.110.feed_forward.w1.weight": "consolidated-00019-of-00022.pth",
|
1002 |
+
"layers.110.feed_forward.w3.weight": "consolidated-00019-of-00022.pth",
|
1003 |
+
"layers.110.feed_forward.w2.weight": "consolidated-00019-of-00022.pth",
|
1004 |
+
"layers.110.attention_norm.weight": "consolidated-00019-of-00022.pth",
|
1005 |
+
"layers.110.ffn_norm.weight": "consolidated-00019-of-00022.pth",
|
1006 |
+
"layers.111.attention.wq.weight": "consolidated-00019-of-00022.pth",
|
1007 |
+
"layers.111.attention.wk.weight": "consolidated-00019-of-00022.pth",
|
1008 |
+
"layers.111.attention.wv.weight": "consolidated-00019-of-00022.pth",
|
1009 |
+
"layers.111.attention.wo.weight": "consolidated-00019-of-00022.pth",
|
1010 |
+
"layers.111.feed_forward.w1.weight": "consolidated-00019-of-00022.pth",
|
1011 |
+
"layers.111.feed_forward.w3.weight": "consolidated-00019-of-00022.pth",
|
1012 |
+
"layers.111.feed_forward.w2.weight": "consolidated-00019-of-00022.pth",
|
1013 |
+
"layers.111.attention_norm.weight": "consolidated-00019-of-00022.pth",
|
1014 |
+
"layers.111.ffn_norm.weight": "consolidated-00019-of-00022.pth",
|
1015 |
+
"layers.112.attention.wq.weight": "consolidated-00019-of-00022.pth",
|
1016 |
+
"layers.112.attention.wk.weight": "consolidated-00019-of-00022.pth",
|
1017 |
+
"layers.112.attention.wv.weight": "consolidated-00019-of-00022.pth",
|
1018 |
+
"layers.112.attention.wo.weight": "consolidated-00019-of-00022.pth",
|
1019 |
+
"layers.112.feed_forward.w1.weight": "consolidated-00019-of-00022.pth",
|
1020 |
+
"layers.112.feed_forward.w3.weight": "consolidated-00019-of-00022.pth",
|
1021 |
+
"layers.112.feed_forward.w2.weight": "consolidated-00019-of-00022.pth",
|
1022 |
+
"layers.112.attention_norm.weight": "consolidated-00019-of-00022.pth",
|
1023 |
+
"layers.112.ffn_norm.weight": "consolidated-00019-of-00022.pth",
|
1024 |
+
"layers.113.attention.wq.weight": "consolidated-00019-of-00022.pth",
|
1025 |
+
"layers.113.attention.wk.weight": "consolidated-00019-of-00022.pth",
|
1026 |
+
"layers.113.attention.wv.weight": "consolidated-00019-of-00022.pth",
|
1027 |
+
"layers.113.attention.wo.weight": "consolidated-00019-of-00022.pth",
|
1028 |
+
"layers.113.feed_forward.w1.weight": "consolidated-00019-of-00022.pth",
|
1029 |
+
"layers.113.feed_forward.w3.weight": "consolidated-00020-of-00022.pth",
|
1030 |
+
"layers.113.feed_forward.w2.weight": "consolidated-00020-of-00022.pth",
|
1031 |
+
"layers.113.attention_norm.weight": "consolidated-00020-of-00022.pth",
|
1032 |
+
"layers.113.ffn_norm.weight": "consolidated-00020-of-00022.pth",
|
1033 |
+
"layers.114.attention.wq.weight": "consolidated-00020-of-00022.pth",
|
1034 |
+
"layers.114.attention.wk.weight": "consolidated-00020-of-00022.pth",
|
1035 |
+
"layers.114.attention.wv.weight": "consolidated-00020-of-00022.pth",
|
1036 |
+
"layers.114.attention.wo.weight": "consolidated-00020-of-00022.pth",
|
1037 |
+
"layers.114.feed_forward.w1.weight": "consolidated-00020-of-00022.pth",
|
1038 |
+
"layers.114.feed_forward.w3.weight": "consolidated-00020-of-00022.pth",
|
1039 |
+
"layers.114.feed_forward.w2.weight": "consolidated-00020-of-00022.pth",
|
1040 |
+
"layers.114.attention_norm.weight": "consolidated-00020-of-00022.pth",
|
1041 |
+
"layers.114.ffn_norm.weight": "consolidated-00020-of-00022.pth",
|
1042 |
+
"layers.115.attention.wq.weight": "consolidated-00020-of-00022.pth",
|
1043 |
+
"layers.115.attention.wk.weight": "consolidated-00020-of-00022.pth",
|
1044 |
+
"layers.115.attention.wv.weight": "consolidated-00020-of-00022.pth",
|
1045 |
+
"layers.115.attention.wo.weight": "consolidated-00020-of-00022.pth",
|
1046 |
+
"layers.115.feed_forward.w1.weight": "consolidated-00020-of-00022.pth",
|
1047 |
+
"layers.115.feed_forward.w3.weight": "consolidated-00020-of-00022.pth",
|
1048 |
+
"layers.115.feed_forward.w2.weight": "consolidated-00020-of-00022.pth",
|
1049 |
+
"layers.115.attention_norm.weight": "consolidated-00020-of-00022.pth",
|
1050 |
+
"layers.115.ffn_norm.weight": "consolidated-00020-of-00022.pth",
|
1051 |
+
"layers.116.attention.wq.weight": "consolidated-00020-of-00022.pth",
|
1052 |
+
"layers.116.attention.wk.weight": "consolidated-00020-of-00022.pth",
|
1053 |
+
"layers.116.attention.wv.weight": "consolidated-00020-of-00022.pth",
|
1054 |
+
"layers.116.attention.wo.weight": "consolidated-00020-of-00022.pth",
|
1055 |
+
"layers.116.feed_forward.w1.weight": "consolidated-00020-of-00022.pth",
|
1056 |
+
"layers.116.feed_forward.w3.weight": "consolidated-00020-of-00022.pth",
|
1057 |
+
"layers.116.feed_forward.w2.weight": "consolidated-00020-of-00022.pth",
|
1058 |
+
"layers.116.attention_norm.weight": "consolidated-00020-of-00022.pth",
|
1059 |
+
"layers.116.ffn_norm.weight": "consolidated-00020-of-00022.pth",
|
1060 |
+
"layers.117.attention.wq.weight": "consolidated-00020-of-00022.pth",
|
1061 |
+
"layers.117.attention.wk.weight": "consolidated-00020-of-00022.pth",
|
1062 |
+
"layers.117.attention.wv.weight": "consolidated-00020-of-00022.pth",
|
1063 |
+
"layers.117.attention.wo.weight": "consolidated-00020-of-00022.pth",
|
1064 |
+
"layers.117.feed_forward.w1.weight": "consolidated-00020-of-00022.pth",
|
1065 |
+
"layers.117.feed_forward.w3.weight": "consolidated-00020-of-00022.pth",
|
1066 |
+
"layers.117.feed_forward.w2.weight": "consolidated-00020-of-00022.pth",
|
1067 |
+
"layers.117.attention_norm.weight": "consolidated-00020-of-00022.pth",
|
1068 |
+
"layers.117.ffn_norm.weight": "consolidated-00020-of-00022.pth",
|
1069 |
+
"layers.118.attention.wq.weight": "consolidated-00020-of-00022.pth",
|
1070 |
+
"layers.118.attention.wk.weight": "consolidated-00020-of-00022.pth",
|
1071 |
+
"layers.118.attention.wv.weight": "consolidated-00020-of-00022.pth",
|
1072 |
+
"layers.118.attention.wo.weight": "consolidated-00020-of-00022.pth",
|
1073 |
+
"layers.118.feed_forward.w1.weight": "consolidated-00020-of-00022.pth",
|
1074 |
+
"layers.118.feed_forward.w3.weight": "consolidated-00020-of-00022.pth",
|
1075 |
+
"layers.118.feed_forward.w2.weight": "consolidated-00020-of-00022.pth",
|
1076 |
+
"layers.118.attention_norm.weight": "consolidated-00020-of-00022.pth",
|
1077 |
+
"layers.118.ffn_norm.weight": "consolidated-00020-of-00022.pth",
|
1078 |
+
"layers.119.attention.wq.weight": "consolidated-00020-of-00022.pth",
|
1079 |
+
"layers.119.attention.wk.weight": "consolidated-00020-of-00022.pth",
|
1080 |
+
"layers.119.attention.wv.weight": "consolidated-00020-of-00022.pth",
|
1081 |
+
"layers.119.attention.wo.weight": "consolidated-00020-of-00022.pth",
|
1082 |
+
"layers.119.feed_forward.w1.weight": "consolidated-00020-of-00022.pth",
|
1083 |
+
"layers.119.feed_forward.w3.weight": "consolidated-00021-of-00022.pth",
|
1084 |
+
"layers.119.feed_forward.w2.weight": "consolidated-00021-of-00022.pth",
|
1085 |
+
"layers.119.attention_norm.weight": "consolidated-00021-of-00022.pth",
|
1086 |
+
"layers.119.ffn_norm.weight": "consolidated-00021-of-00022.pth",
|
1087 |
+
"layers.120.attention.wq.weight": "consolidated-00021-of-00022.pth",
|
1088 |
+
"layers.120.attention.wk.weight": "consolidated-00021-of-00022.pth",
|
1089 |
+
"layers.120.attention.wv.weight": "consolidated-00021-of-00022.pth",
|
1090 |
+
"layers.120.attention.wo.weight": "consolidated-00021-of-00022.pth",
|
1091 |
+
"layers.120.feed_forward.w1.weight": "consolidated-00021-of-00022.pth",
|
1092 |
+
"layers.120.feed_forward.w3.weight": "consolidated-00021-of-00022.pth",
|
1093 |
+
"layers.120.feed_forward.w2.weight": "consolidated-00021-of-00022.pth",
|
1094 |
+
"layers.120.attention_norm.weight": "consolidated-00021-of-00022.pth",
|
1095 |
+
"layers.120.ffn_norm.weight": "consolidated-00021-of-00022.pth",
|
1096 |
+
"layers.121.attention.wq.weight": "consolidated-00021-of-00022.pth",
|
1097 |
+
"layers.121.attention.wk.weight": "consolidated-00021-of-00022.pth",
|
1098 |
+
"layers.121.attention.wv.weight": "consolidated-00021-of-00022.pth",
|
1099 |
+
"layers.121.attention.wo.weight": "consolidated-00021-of-00022.pth",
|
1100 |
+
"layers.121.feed_forward.w1.weight": "consolidated-00021-of-00022.pth",
|
1101 |
+
"layers.121.feed_forward.w3.weight": "consolidated-00021-of-00022.pth",
|
1102 |
+
"layers.121.feed_forward.w2.weight": "consolidated-00021-of-00022.pth",
|
1103 |
+
"layers.121.attention_norm.weight": "consolidated-00021-of-00022.pth",
|
1104 |
+
"layers.121.ffn_norm.weight": "consolidated-00021-of-00022.pth",
|
1105 |
+
"layers.122.attention.wq.weight": "consolidated-00021-of-00022.pth",
|
1106 |
+
"layers.122.attention.wk.weight": "consolidated-00021-of-00022.pth",
|
1107 |
+
"layers.122.attention.wv.weight": "consolidated-00021-of-00022.pth",
|
1108 |
+
"layers.122.attention.wo.weight": "consolidated-00021-of-00022.pth",
|
1109 |
+
"layers.122.feed_forward.w1.weight": "consolidated-00021-of-00022.pth",
|
1110 |
+
"layers.122.feed_forward.w3.weight": "consolidated-00021-of-00022.pth",
|
1111 |
+
"layers.122.feed_forward.w2.weight": "consolidated-00021-of-00022.pth",
|
1112 |
+
"layers.122.attention_norm.weight": "consolidated-00021-of-00022.pth",
|
1113 |
+
"layers.122.ffn_norm.weight": "consolidated-00021-of-00022.pth",
|
1114 |
+
"layers.123.attention.wq.weight": "consolidated-00021-of-00022.pth",
|
1115 |
+
"layers.123.attention.wk.weight": "consolidated-00021-of-00022.pth",
|
1116 |
+
"layers.123.attention.wv.weight": "consolidated-00021-of-00022.pth",
|
1117 |
+
"layers.123.attention.wo.weight": "consolidated-00021-of-00022.pth",
|
1118 |
+
"layers.123.feed_forward.w1.weight": "consolidated-00021-of-00022.pth",
|
1119 |
+
"layers.123.feed_forward.w3.weight": "consolidated-00021-of-00022.pth",
|
1120 |
+
"layers.123.feed_forward.w2.weight": "consolidated-00021-of-00022.pth",
|
1121 |
+
"layers.123.attention_norm.weight": "consolidated-00021-of-00022.pth",
|
1122 |
+
"layers.123.ffn_norm.weight": "consolidated-00021-of-00022.pth",
|
1123 |
+
"layers.124.attention.wq.weight": "consolidated-00021-of-00022.pth",
|
1124 |
+
"layers.124.attention.wk.weight": "consolidated-00021-of-00022.pth",
|
1125 |
+
"layers.124.attention.wv.weight": "consolidated-00021-of-00022.pth",
|
1126 |
+
"layers.124.attention.wo.weight": "consolidated-00021-of-00022.pth",
|
1127 |
+
"layers.124.feed_forward.w1.weight": "consolidated-00021-of-00022.pth",
|
1128 |
+
"layers.124.feed_forward.w3.weight": "consolidated-00021-of-00022.pth",
|
1129 |
+
"layers.124.feed_forward.w2.weight": "consolidated-00021-of-00022.pth",
|
1130 |
+
"layers.124.attention_norm.weight": "consolidated-00021-of-00022.pth",
|
1131 |
+
"layers.124.ffn_norm.weight": "consolidated-00021-of-00022.pth",
|
1132 |
+
"layers.125.attention.wq.weight": "consolidated-00021-of-00022.pth",
|
1133 |
+
"layers.125.attention.wk.weight": "consolidated-00021-of-00022.pth",
|
1134 |
+
"layers.125.attention.wv.weight": "consolidated-00021-of-00022.pth",
|
1135 |
+
"layers.125.attention.wo.weight": "consolidated-00021-of-00022.pth",
|
1136 |
+
"layers.125.feed_forward.w1.weight": "consolidated-00021-of-00022.pth",
|
1137 |
+
"layers.125.feed_forward.w3.weight": "consolidated-00022-of-00022.pth",
|
1138 |
+
"layers.125.feed_forward.w2.weight": "consolidated-00022-of-00022.pth",
|
1139 |
+
"layers.125.attention_norm.weight": "consolidated-00022-of-00022.pth",
|
1140 |
+
"layers.125.ffn_norm.weight": "consolidated-00022-of-00022.pth",
|
1141 |
+
"norm.weight": "consolidated-00022-of-00022.pth",
|
1142 |
+
"output.weight": "consolidated-00022-of-00022.pth"
|
1143 |
+
}
|
1144 |
+
}
|
mp8/consolidated.02/consolidated-00001-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a74d2dd5b327ef9e529eb5010a5490270849c4b0eb1a8e6b9b2ff64519f40af
|
3 |
+
size 4870980313
|
mp8/consolidated.02/consolidated-00002-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e0210b8d092c04f3215430912ee65d75a1d62150893b1f254b614edc6e6ee55
|
3 |
+
size 4781917812
|
mp8/consolidated.02/consolidated-00003-of-00022.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb410b976be6349162eeb5ab74c03836d39d05c0b781cc73ff829fb7e099066f
|
3 |
+
size 4781917876
|