Commit
•
45e3df8
0
Parent(s):
Duplicate from bigscience/mt0-xxl
Browse filesCo-authored-by: Thomas Wang <[email protected]>
- .gitattributes +33 -0
- README.md +960 -0
- config.json +32 -0
- model-00001-of-00006.safetensors +3 -0
- model-00002-of-00006.safetensors +3 -0
- model-00003-of-00006.safetensors +3 -0
- model-00004-of-00006.safetensors +3 -0
- model-00005-of-00006.safetensors +3 -0
- model-00006-of-00006.safetensors +3 -0
- model.safetensors.index.json +566 -0
- pytorch_model-00001-of-00006.bin +3 -0
- pytorch_model-00002-of-00006.bin +3 -0
- pytorch_model-00003-of-00006.bin +3 -0
- pytorch_model-00004-of-00006.bin +3 -0
- pytorch_model-00005-of-00006.bin +3 -0
- pytorch_model-00006-of-00006.bin +3 -0
- pytorch_model.bin.index.json +566 -0
- special_tokens_map.json +5 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +11 -0
.gitattributes
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,960 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- bigscience/xP3
|
| 4 |
+
- mc4
|
| 5 |
+
license: apache-2.0
|
| 6 |
+
language:
|
| 7 |
+
- af
|
| 8 |
+
- am
|
| 9 |
+
- ar
|
| 10 |
+
- az
|
| 11 |
+
- be
|
| 12 |
+
- bg
|
| 13 |
+
- bn
|
| 14 |
+
- ca
|
| 15 |
+
- ceb
|
| 16 |
+
- co
|
| 17 |
+
- cs
|
| 18 |
+
- cy
|
| 19 |
+
- da
|
| 20 |
+
- de
|
| 21 |
+
- el
|
| 22 |
+
- en
|
| 23 |
+
- eo
|
| 24 |
+
- es
|
| 25 |
+
- et
|
| 26 |
+
- eu
|
| 27 |
+
- fa
|
| 28 |
+
- fi
|
| 29 |
+
- fil
|
| 30 |
+
- fr
|
| 31 |
+
- fy
|
| 32 |
+
- ga
|
| 33 |
+
- gd
|
| 34 |
+
- gl
|
| 35 |
+
- gu
|
| 36 |
+
- ha
|
| 37 |
+
- haw
|
| 38 |
+
- hi
|
| 39 |
+
- hmn
|
| 40 |
+
- ht
|
| 41 |
+
- hu
|
| 42 |
+
- hy
|
| 43 |
+
- ig
|
| 44 |
+
- is
|
| 45 |
+
- it
|
| 46 |
+
- iw
|
| 47 |
+
- ja
|
| 48 |
+
- jv
|
| 49 |
+
- ka
|
| 50 |
+
- kk
|
| 51 |
+
- km
|
| 52 |
+
- kn
|
| 53 |
+
- ko
|
| 54 |
+
- ku
|
| 55 |
+
- ky
|
| 56 |
+
- la
|
| 57 |
+
- lb
|
| 58 |
+
- lo
|
| 59 |
+
- lt
|
| 60 |
+
- lv
|
| 61 |
+
- mg
|
| 62 |
+
- mi
|
| 63 |
+
- mk
|
| 64 |
+
- ml
|
| 65 |
+
- mn
|
| 66 |
+
- mr
|
| 67 |
+
- ms
|
| 68 |
+
- mt
|
| 69 |
+
- my
|
| 70 |
+
- ne
|
| 71 |
+
- nl
|
| 72 |
+
- 'no'
|
| 73 |
+
- ny
|
| 74 |
+
- pa
|
| 75 |
+
- pl
|
| 76 |
+
- ps
|
| 77 |
+
- pt
|
| 78 |
+
- ro
|
| 79 |
+
- ru
|
| 80 |
+
- sd
|
| 81 |
+
- si
|
| 82 |
+
- sk
|
| 83 |
+
- sl
|
| 84 |
+
- sm
|
| 85 |
+
- sn
|
| 86 |
+
- so
|
| 87 |
+
- sq
|
| 88 |
+
- sr
|
| 89 |
+
- st
|
| 90 |
+
- su
|
| 91 |
+
- sv
|
| 92 |
+
- sw
|
| 93 |
+
- ta
|
| 94 |
+
- te
|
| 95 |
+
- tg
|
| 96 |
+
- th
|
| 97 |
+
- tr
|
| 98 |
+
- uk
|
| 99 |
+
- und
|
| 100 |
+
- ur
|
| 101 |
+
- uz
|
| 102 |
+
- vi
|
| 103 |
+
- xh
|
| 104 |
+
- yi
|
| 105 |
+
- yo
|
| 106 |
+
- zh
|
| 107 |
+
- zu
|
| 108 |
+
tags:
|
| 109 |
+
- text2text-generation
|
| 110 |
+
widget:
|
| 111 |
+
- text: >-
|
| 112 |
+
<table> <tr> <th>Name</th> <th>Explanation</th> <th>Example models</th>
|
| 113 |
+
</tr> <tr> <td><a
|
| 114 |
+
href=https://huggingface.co/datasets/bigscience/xP3>xP3</a></t> <td>Mixture
|
| 115 |
+
of 13 training tasks in 46 languages with English prompts</td> <td><a
|
| 116 |
+
href=https://huggingface.co/bigscience/bloomz>bloomz</a> & <a
|
| 117 |
+
href=https://huggingface.co/bigscience/mt0-xxl>mt0-xxl</a></td> </tr> <tr>
|
| 118 |
+
<td><a href=https://huggingface.co/datasets/bigscience/xP3mt>xP3mt</a></t>
|
| 119 |
+
<td>Mixture of 13 training tasks in 46 languages with prompts in 20
|
| 120 |
+
languages (machine-translated from English)</td> <td><a
|
| 121 |
+
href=https://huggingface.co/bigscience/bloomz-mt>bloomz-mt</a> & <a
|
| 122 |
+
href=https://huggingface.co/bigscience/mt0-xxl-mt>mt0-xxl-mt</a></td> </tr>
|
| 123 |
+
<tr> <td><a
|
| 124 |
+
href=https://huggingface.co/datasets/bigscience/xP3all>xP3all</a></t>
|
| 125 |
+
<td>xP3 + our evaluation datasets adding an additional 3 tasks for a total
|
| 126 |
+
of 16 tasks in 46 languages with English prompts</td> <td></td> </tr> <tr>
|
| 127 |
+
<td><a
|
| 128 |
+
href=https://huggingface.co/datasets/bigscience/xP3megds>xP3megds</a></t>
|
| 129 |
+
<td><a
|
| 130 |
+
href=https://github.com/bigscience-workshop/Megatron-DeepSpeed>Megatron-DeepSpeed</a>
|
| 131 |
+
processed version of xP3</td> <td><a
|
| 132 |
+
href=https://huggingface.co/bigscience/bloomz>bloomz</a></td> </tr> <tr>
|
| 133 |
+
<td><a href=https://huggingface.co/datasets/Muennighoff/P3>P3</a></t>
|
| 134 |
+
<td>Repreprocessed version of the English-only <a
|
| 135 |
+
href=https://huggingface.co/datasets/bigscience/P3>P3</a> with 8 training
|
| 136 |
+
tasks</td> <td><a
|
| 137 |
+
href=https://huggingface.co/bigscience/bloomz-p3>bloomz-p3</a> & <a
|
| 138 |
+
href=https://huggingface.co/bigscience/mt0-xxl-p3>mt0-xxl-p3</a></td> </tr>
|
| 139 |
+
</table> Which dataset has the most tasks?
|
| 140 |
+
example_title: en-en struct-to-text
|
| 141 |
+
- text: Life is beautiful! Translate to Mongolian.
|
| 142 |
+
example_title: mn-en translation
|
| 143 |
+
- text: Le mot japonais «憂鬱» veut dire quoi en Odia?
|
| 144 |
+
example_title: jp-or-fr translation
|
| 145 |
+
- text: >-
|
| 146 |
+
Stell mir eine schwierige Quiz Frage bei der es um Astronomie geht. Bitte
|
| 147 |
+
stell die Frage auf Norwegisch.
|
| 148 |
+
example_title: de-nb quiz
|
| 149 |
+
- text: >-
|
| 150 |
+
We present BLOOMZ & mT0, a family of models capable of following human
|
| 151 |
+
instructions in dozens of languages zero-shot. We finetune BLOOM & mT5
|
| 152 |
+
pretrained multilingual language models on our crosslingual task mixture
|
| 153 |
+
(xP3) and find our resulting models capable of crosslingual generalization
|
| 154 |
+
to unseen tasks & languages. What are the keywords in Chinese?
|
| 155 |
+
example_title: zh-en keywords
|
| 156 |
+
- text: >-
|
| 157 |
+
一个传奇的开端，一个不灭的神话，这不仅仅是一部电影，而是作为一个走进新时代的标签，永远彪炳史册。Would you rate the previous
|
| 158 |
+
review as positive, neutral or negative?
|
| 159 |
+
example_title: zh-en sentiment
|
| 160 |
+
- text: 一个传奇的开端，一个不灭的神话，这不仅仅是一部电影，而是作为一个走进新时代的标签，永远彪炳史册。你认为这句话的立场是赞扬、中立还是批评？
|
| 161 |
+
example_title: zh-zh sentiment
|
| 162 |
+
- text: Suggest at least five related search terms to "Mạng neural nhân tạo".
|
| 163 |
+
example_title: vi-en query
|
| 164 |
+
- text: >-
|
| 165 |
+
Proposez au moins cinq mots clés concernant «Réseau de neurones
|
| 166 |
+
artificiels».
|
| 167 |
+
example_title: fr-fr query
|
| 168 |
+
- text: Explain in a sentence in Telugu what is backpropagation in neural networks.
|
| 169 |
+
example_title: te-en qa
|
| 170 |
+
- text: Why is the sky blue?
|
| 171 |
+
example_title: en-en qa
|
| 172 |
+
- text: >-
|
| 173 |
+
Write a fairy tale about a troll saving a princess from a dangerous dragon.
|
| 174 |
+
The fairy tale is a masterpiece that has achieved praise worldwide and its
|
| 175 |
+
moral is "Heroes Come in All Shapes and Sizes". Story (in Spanish):
|
| 176 |
+
example_title: es-en fable
|
| 177 |
+
- text: >-
|
| 178 |
+
Write a fable about wood elves living in a forest that is suddenly invaded
|
| 179 |
+
by ogres. The fable is a masterpiece that has achieved praise worldwide and
|
| 180 |
+
its moral is "Violence is the last refuge of the incompetent". Fable (in
|
| 181 |
+
Hindi):
|
| 182 |
+
example_title: hi-en fable
|
| 183 |
+
model-index:
|
| 184 |
+
- name: mt0-xxl
|
| 185 |
+
results:
|
| 186 |
+
- task:
|
| 187 |
+
type: Coreference resolution
|
| 188 |
+
dataset:
|
| 189 |
+
type: winogrande
|
| 190 |
+
name: Winogrande XL (xl)
|
| 191 |
+
config: xl
|
| 192 |
+
split: validation
|
| 193 |
+
revision: a80f460359d1e9a67c006011c94de42a8759430c
|
| 194 |
+
metrics:
|
| 195 |
+
- type: Accuracy
|
| 196 |
+
value: 63.38
|
| 197 |
+
- task:
|
| 198 |
+
type: Coreference resolution
|
| 199 |
+
dataset:
|
| 200 |
+
type: Muennighoff/xwinograd
|
| 201 |
+
name: XWinograd (en)
|
| 202 |
+
config: en
|
| 203 |
+
split: test
|
| 204 |
+
revision: 9dd5ea5505fad86b7bedad667955577815300cee
|
| 205 |
+
metrics:
|
| 206 |
+
- type: Accuracy
|
| 207 |
+
value: 81.29
|
| 208 |
+
- task:
|
| 209 |
+
type: Coreference resolution
|
| 210 |
+
dataset:
|
| 211 |
+
type: Muennighoff/xwinograd
|
| 212 |
+
name: XWinograd (fr)
|
| 213 |
+
config: fr
|
| 214 |
+
split: test
|
| 215 |
+
revision: 9dd5ea5505fad86b7bedad667955577815300cee
|
| 216 |
+
metrics:
|
| 217 |
+
- type: Accuracy
|
| 218 |
+
value: 78.31
|
| 219 |
+
- task:
|
| 220 |
+
type: Coreference resolution
|
| 221 |
+
dataset:
|
| 222 |
+
type: Muennighoff/xwinograd
|
| 223 |
+
name: XWinograd (jp)
|
| 224 |
+
config: jp
|
| 225 |
+
split: test
|
| 226 |
+
revision: 9dd5ea5505fad86b7bedad667955577815300cee
|
| 227 |
+
metrics:
|
| 228 |
+
- type: Accuracy
|
| 229 |
+
value: 78.62
|
| 230 |
+
- task:
|
| 231 |
+
type: Coreference resolution
|
| 232 |
+
dataset:
|
| 233 |
+
type: Muennighoff/xwinograd
|
| 234 |
+
name: XWinograd (pt)
|
| 235 |
+
config: pt
|
| 236 |
+
split: test
|
| 237 |
+
revision: 9dd5ea5505fad86b7bedad667955577815300cee
|
| 238 |
+
metrics:
|
| 239 |
+
- type: Accuracy
|
| 240 |
+
value: 77.95
|
| 241 |
+
- task:
|
| 242 |
+
type: Coreference resolution
|
| 243 |
+
dataset:
|
| 244 |
+
type: Muennighoff/xwinograd
|
| 245 |
+
name: XWinograd (ru)
|
| 246 |
+
config: ru
|
| 247 |
+
split: test
|
| 248 |
+
revision: 9dd5ea5505fad86b7bedad667955577815300cee
|
| 249 |
+
metrics:
|
| 250 |
+
- type: Accuracy
|
| 251 |
+
value: 76.51
|
| 252 |
+
- task:
|
| 253 |
+
type: Coreference resolution
|
| 254 |
+
dataset:
|
| 255 |
+
type: Muennighoff/xwinograd
|
| 256 |
+
name: XWinograd (zh)
|
| 257 |
+
config: zh
|
| 258 |
+
split: test
|
| 259 |
+
revision: 9dd5ea5505fad86b7bedad667955577815300cee
|
| 260 |
+
metrics:
|
| 261 |
+
- type: Accuracy
|
| 262 |
+
value: 77.38
|
| 263 |
+
- task:
|
| 264 |
+
type: Natural language inference
|
| 265 |
+
dataset:
|
| 266 |
+
type: anli
|
| 267 |
+
name: ANLI (r1)
|
| 268 |
+
config: r1
|
| 269 |
+
split: validation
|
| 270 |
+
revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094
|
| 271 |
+
metrics:
|
| 272 |
+
- type: Accuracy
|
| 273 |
+
value: 49.5
|
| 274 |
+
- task:
|
| 275 |
+
type: Natural language inference
|
| 276 |
+
dataset:
|
| 277 |
+
type: anli
|
| 278 |
+
name: ANLI (r2)
|
| 279 |
+
config: r2
|
| 280 |
+
split: validation
|
| 281 |
+
revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094
|
| 282 |
+
metrics:
|
| 283 |
+
- type: Accuracy
|
| 284 |
+
value: 43
|
| 285 |
+
- task:
|
| 286 |
+
type: Natural language inference
|
| 287 |
+
dataset:
|
| 288 |
+
type: anli
|
| 289 |
+
name: ANLI (r3)
|
| 290 |
+
config: r3
|
| 291 |
+
split: validation
|
| 292 |
+
revision: 9dbd830a06fea8b1c49d6e5ef2004a08d9f45094
|
| 293 |
+
metrics:
|
| 294 |
+
- type: Accuracy
|
| 295 |
+
value: 46.08
|
| 296 |
+
- task:
|
| 297 |
+
type: Natural language inference
|
| 298 |
+
dataset:
|
| 299 |
+
type: super_glue
|
| 300 |
+
name: SuperGLUE (cb)
|
| 301 |
+
config: cb
|
| 302 |
+
split: validation
|
| 303 |
+
revision: 9e12063561e7e6c79099feb6d5a493142584e9e2
|
| 304 |
+
metrics:
|
| 305 |
+
- type: Accuracy
|
| 306 |
+
value: 85.71
|
| 307 |
+
- task:
|
| 308 |
+
type: Natural language inference
|
| 309 |
+
dataset:
|
| 310 |
+
type: super_glue
|
| 311 |
+
name: SuperGLUE (rte)
|
| 312 |
+
config: rte
|
| 313 |
+
split: validation
|
| 314 |
+
revision: 9e12063561e7e6c79099feb6d5a493142584e9e2
|
| 315 |
+
metrics:
|
| 316 |
+
- type: Accuracy
|
| 317 |
+
value: 85.56
|
| 318 |
+
- task:
|
| 319 |
+
type: Natural language inference
|
| 320 |
+
dataset:
|
| 321 |
+
type: xnli
|
| 322 |
+
name: XNLI (ar)
|
| 323 |
+
config: ar
|
| 324 |
+
split: validation
|
| 325 |
+
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
|
| 326 |
+
metrics:
|
| 327 |
+
- type: Accuracy
|
| 328 |
+
value: 57.91
|
| 329 |
+
- task:
|
| 330 |
+
type: Natural language inference
|
| 331 |
+
dataset:
|
| 332 |
+
type: xnli
|
| 333 |
+
name: XNLI (bg)
|
| 334 |
+
config: bg
|
| 335 |
+
split: validation
|
| 336 |
+
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
|
| 337 |
+
metrics:
|
| 338 |
+
- type: Accuracy
|
| 339 |
+
value: 59.88
|
| 340 |
+
- task:
|
| 341 |
+
type: Natural language inference
|
| 342 |
+
dataset:
|
| 343 |
+
type: xnli
|
| 344 |
+
name: XNLI (de)
|
| 345 |
+
config: de
|
| 346 |
+
split: validation
|
| 347 |
+
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
|
| 348 |
+
metrics:
|
| 349 |
+
- type: Accuracy
|
| 350 |
+
value: 60.64
|
| 351 |
+
- task:
|
| 352 |
+
type: Natural language inference
|
| 353 |
+
dataset:
|
| 354 |
+
type: xnli
|
| 355 |
+
name: XNLI (el)
|
| 356 |
+
config: el
|
| 357 |
+
split: validation
|
| 358 |
+
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
|
| 359 |
+
metrics:
|
| 360 |
+
- type: Accuracy
|
| 361 |
+
value: 59
|
| 362 |
+
- task:
|
| 363 |
+
type: Natural language inference
|
| 364 |
+
dataset:
|
| 365 |
+
type: xnli
|
| 366 |
+
name: XNLI (en)
|
| 367 |
+
config: en
|
| 368 |
+
split: validation
|
| 369 |
+
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
|
| 370 |
+
metrics:
|
| 371 |
+
- type: Accuracy
|
| 372 |
+
value: 62.01
|
| 373 |
+
- task:
|
| 374 |
+
type: Natural language inference
|
| 375 |
+
dataset:
|
| 376 |
+
type: xnli
|
| 377 |
+
name: XNLI (es)
|
| 378 |
+
config: es
|
| 379 |
+
split: validation
|
| 380 |
+
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
|
| 381 |
+
metrics:
|
| 382 |
+
- type: Accuracy
|
| 383 |
+
value: 60.8
|
| 384 |
+
- task:
|
| 385 |
+
type: Natural language inference
|
| 386 |
+
dataset:
|
| 387 |
+
type: xnli
|
| 388 |
+
name: XNLI (fr)
|
| 389 |
+
config: fr
|
| 390 |
+
split: validation
|
| 391 |
+
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
|
| 392 |
+
metrics:
|
| 393 |
+
- type: Accuracy
|
| 394 |
+
value: 59.88
|
| 395 |
+
- task:
|
| 396 |
+
type: Natural language inference
|
| 397 |
+
dataset:
|
| 398 |
+
type: xnli
|
| 399 |
+
name: XNLI (hi)
|
| 400 |
+
config: hi
|
| 401 |
+
split: validation
|
| 402 |
+
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
|
| 403 |
+
metrics:
|
| 404 |
+
- type: Accuracy
|
| 405 |
+
value: 57.23
|
| 406 |
+
- task:
|
| 407 |
+
type: Natural language inference
|
| 408 |
+
dataset:
|
| 409 |
+
type: xnli
|
| 410 |
+
name: XNLI (ru)
|
| 411 |
+
config: ru
|
| 412 |
+
split: validation
|
| 413 |
+
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
|
| 414 |
+
metrics:
|
| 415 |
+
- type: Accuracy
|
| 416 |
+
value: 58.88
|
| 417 |
+
- task:
|
| 418 |
+
type: Natural language inference
|
| 419 |
+
dataset:
|
| 420 |
+
type: xnli
|
| 421 |
+
name: XNLI (sw)
|
| 422 |
+
config: sw
|
| 423 |
+
split: validation
|
| 424 |
+
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
|
| 425 |
+
metrics:
|
| 426 |
+
- type: Accuracy
|
| 427 |
+
value: 55.66
|
| 428 |
+
- task:
|
| 429 |
+
type: Natural language inference
|
| 430 |
+
dataset:
|
| 431 |
+
type: xnli
|
| 432 |
+
name: XNLI (th)
|
| 433 |
+
config: th
|
| 434 |
+
split: validation
|
| 435 |
+
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
|
| 436 |
+
metrics:
|
| 437 |
+
- type: Accuracy
|
| 438 |
+
value: 57.43
|
| 439 |
+
- task:
|
| 440 |
+
type: Natural language inference
|
| 441 |
+
dataset:
|
| 442 |
+
type: xnli
|
| 443 |
+
name: XNLI (tr)
|
| 444 |
+
config: tr
|
| 445 |
+
split: validation
|
| 446 |
+
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
|
| 447 |
+
metrics:
|
| 448 |
+
- type: Accuracy
|
| 449 |
+
value: 57.59
|
| 450 |
+
- task:
|
| 451 |
+
type: Natural language inference
|
| 452 |
+
dataset:
|
| 453 |
+
type: xnli
|
| 454 |
+
name: XNLI (ur)
|
| 455 |
+
config: ur
|
| 456 |
+
split: validation
|
| 457 |
+
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
|
| 458 |
+
metrics:
|
| 459 |
+
- type: Accuracy
|
| 460 |
+
value: 55.42
|
| 461 |
+
- task:
|
| 462 |
+
type: Natural language inference
|
| 463 |
+
dataset:
|
| 464 |
+
type: xnli
|
| 465 |
+
name: XNLI (vi)
|
| 466 |
+
config: vi
|
| 467 |
+
split: validation
|
| 468 |
+
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
|
| 469 |
+
metrics:
|
| 470 |
+
- type: Accuracy
|
| 471 |
+
value: 58.51
|
| 472 |
+
- task:
|
| 473 |
+
type: Natural language inference
|
| 474 |
+
dataset:
|
| 475 |
+
type: xnli
|
| 476 |
+
name: XNLI (zh)
|
| 477 |
+
config: zh
|
| 478 |
+
split: validation
|
| 479 |
+
revision: a5a45e4ff92d5d3f34de70aaf4b72c3bdf9f7f16
|
| 480 |
+
metrics:
|
| 481 |
+
- type: Accuracy
|
| 482 |
+
value: 59.12
|
| 483 |
+
- task:
|
| 484 |
+
type: Sentence completion
|
| 485 |
+
dataset:
|
| 486 |
+
type: story_cloze
|
| 487 |
+
name: StoryCloze (2016)
|
| 488 |
+
config: '2016'
|
| 489 |
+
split: validation
|
| 490 |
+
revision: e724c6f8cdf7c7a2fb229d862226e15b023ee4db
|
| 491 |
+
metrics:
|
| 492 |
+
- type: Accuracy
|
| 493 |
+
value: 96.04
|
| 494 |
+
- task:
|
| 495 |
+
type: Sentence completion
|
| 496 |
+
dataset:
|
| 497 |
+
type: super_glue
|
| 498 |
+
name: SuperGLUE (copa)
|
| 499 |
+
config: copa
|
| 500 |
+
split: validation
|
| 501 |
+
revision: 9e12063561e7e6c79099feb6d5a493142584e9e2
|
| 502 |
+
metrics:
|
| 503 |
+
- type: Accuracy
|
| 504 |
+
value: 93
|
| 505 |
+
- task:
|
| 506 |
+
type: Sentence completion
|
| 507 |
+
dataset:
|
| 508 |
+
type: xcopa
|
| 509 |
+
name: XCOPA (et)
|
| 510 |
+
config: et
|
| 511 |
+
split: validation
|
| 512 |
+
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
|
| 513 |
+
metrics:
|
| 514 |
+
- type: Accuracy
|
| 515 |
+
value: 79
|
| 516 |
+
- task:
|
| 517 |
+
type: Sentence completion
|
| 518 |
+
dataset:
|
| 519 |
+
type: xcopa
|
| 520 |
+
name: XCOPA (ht)
|
| 521 |
+
config: ht
|
| 522 |
+
split: validation
|
| 523 |
+
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
|
| 524 |
+
metrics:
|
| 525 |
+
- type: Accuracy
|
| 526 |
+
value: 81
|
| 527 |
+
- task:
|
| 528 |
+
type: Sentence completion
|
| 529 |
+
dataset:
|
| 530 |
+
type: xcopa
|
| 531 |
+
name: XCOPA (id)
|
| 532 |
+
config: id
|
| 533 |
+
split: validation
|
| 534 |
+
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
|
| 535 |
+
metrics:
|
| 536 |
+
- type: Accuracy
|
| 537 |
+
value: 92
|
| 538 |
+
- task:
|
| 539 |
+
type: Sentence completion
|
| 540 |
+
dataset:
|
| 541 |
+
type: xcopa
|
| 542 |
+
name: XCOPA (it)
|
| 543 |
+
config: it
|
| 544 |
+
split: validation
|
| 545 |
+
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
|
| 546 |
+
metrics:
|
| 547 |
+
- type: Accuracy
|
| 548 |
+
value: 90
|
| 549 |
+
- task:
|
| 550 |
+
type: Sentence completion
|
| 551 |
+
dataset:
|
| 552 |
+
type: xcopa
|
| 553 |
+
name: XCOPA (qu)
|
| 554 |
+
config: qu
|
| 555 |
+
split: validation
|
| 556 |
+
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
|
| 557 |
+
metrics:
|
| 558 |
+
- type: Accuracy
|
| 559 |
+
value: 59
|
| 560 |
+
- task:
|
| 561 |
+
type: Sentence completion
|
| 562 |
+
dataset:
|
| 563 |
+
type: xcopa
|
| 564 |
+
name: XCOPA (sw)
|
| 565 |
+
config: sw
|
| 566 |
+
split: validation
|
| 567 |
+
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
|
| 568 |
+
metrics:
|
| 569 |
+
- type: Accuracy
|
| 570 |
+
value: 79
|
| 571 |
+
- task:
|
| 572 |
+
type: Sentence completion
|
| 573 |
+
dataset:
|
| 574 |
+
type: xcopa
|
| 575 |
+
name: XCOPA (ta)
|
| 576 |
+
config: ta
|
| 577 |
+
split: validation
|
| 578 |
+
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
|
| 579 |
+
metrics:
|
| 580 |
+
- type: Accuracy
|
| 581 |
+
value: 84
|
| 582 |
+
- task:
|
| 583 |
+
type: Sentence completion
|
| 584 |
+
dataset:
|
| 585 |
+
type: xcopa
|
| 586 |
+
name: XCOPA (th)
|
| 587 |
+
config: th
|
| 588 |
+
split: validation
|
| 589 |
+
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
|
| 590 |
+
metrics:
|
| 591 |
+
- type: Accuracy
|
| 592 |
+
value: 77
|
| 593 |
+
- task:
|
| 594 |
+
type: Sentence completion
|
| 595 |
+
dataset:
|
| 596 |
+
type: xcopa
|
| 597 |
+
name: XCOPA (tr)
|
| 598 |
+
config: tr
|
| 599 |
+
split: validation
|
| 600 |
+
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
|
| 601 |
+
metrics:
|
| 602 |
+
- type: Accuracy
|
| 603 |
+
value: 79
|
| 604 |
+
- task:
|
| 605 |
+
type: Sentence completion
|
| 606 |
+
dataset:
|
| 607 |
+
type: xcopa
|
| 608 |
+
name: XCOPA (vi)
|
| 609 |
+
config: vi
|
| 610 |
+
split: validation
|
| 611 |
+
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
|
| 612 |
+
metrics:
|
| 613 |
+
- type: Accuracy
|
| 614 |
+
value: 88
|
| 615 |
+
- task:
|
| 616 |
+
type: Sentence completion
|
| 617 |
+
dataset:
|
| 618 |
+
type: xcopa
|
| 619 |
+
name: XCOPA (zh)
|
| 620 |
+
config: zh
|
| 621 |
+
split: validation
|
| 622 |
+
revision: 37f73c60fb123111fa5af5f9b705d0b3747fd187
|
| 623 |
+
metrics:
|
| 624 |
+
- type: Accuracy
|
| 625 |
+
value: 89
|
| 626 |
+
- task:
|
| 627 |
+
type: Sentence completion
|
| 628 |
+
dataset:
|
| 629 |
+
type: Muennighoff/xstory_cloze
|
| 630 |
+
name: XStoryCloze (ar)
|
| 631 |
+
config: ar
|
| 632 |
+
split: validation
|
| 633 |
+
revision: 8bb76e594b68147f1a430e86829d07189622b90d
|
| 634 |
+
metrics:
|
| 635 |
+
- type: Accuracy
|
| 636 |
+
value: 91.07
|
| 637 |
+
- task:
|
| 638 |
+
type: Sentence completion
|
| 639 |
+
dataset:
|
| 640 |
+
type: Muennighoff/xstory_cloze
|
| 641 |
+
name: XStoryCloze (es)
|
| 642 |
+
config: es
|
| 643 |
+
split: validation
|
| 644 |
+
revision: 8bb76e594b68147f1a430e86829d07189622b90d
|
| 645 |
+
metrics:
|
| 646 |
+
- type: Accuracy
|
| 647 |
+
value: 92.52
|
| 648 |
+
- task:
|
| 649 |
+
type: Sentence completion
|
| 650 |
+
dataset:
|
| 651 |
+
type: Muennighoff/xstory_cloze
|
| 652 |
+
name: XStoryCloze (eu)
|
| 653 |
+
config: eu
|
| 654 |
+
split: validation
|
| 655 |
+
revision: 8bb76e594b68147f1a430e86829d07189622b90d
|
| 656 |
+
metrics:
|
| 657 |
+
- type: Accuracy
|
| 658 |
+
value: 90.6
|
| 659 |
+
- task:
|
| 660 |
+
type: Sentence completion
|
| 661 |
+
dataset:
|
| 662 |
+
type: Muennighoff/xstory_cloze
|
| 663 |
+
name: XStoryCloze (hi)
|
| 664 |
+
config: hi
|
| 665 |
+
split: validation
|
| 666 |
+
revision: 8bb76e594b68147f1a430e86829d07189622b90d
|
| 667 |
+
metrics:
|
| 668 |
+
- type: Accuracy
|
| 669 |
+
value: 92.32
|
| 670 |
+
- task:
|
| 671 |
+
type: Sentence completion
|
| 672 |
+
dataset:
|
| 673 |
+
type: Muennighoff/xstory_cloze
|
| 674 |
+
name: XStoryCloze (id)
|
| 675 |
+
config: id
|
| 676 |
+
split: validation
|
| 677 |
+
revision: 8bb76e594b68147f1a430e86829d07189622b90d
|
| 678 |
+
metrics:
|
| 679 |
+
- type: Accuracy
|
| 680 |
+
value: 93.51
|
| 681 |
+
- task:
|
| 682 |
+
type: Sentence completion
|
| 683 |
+
dataset:
|
| 684 |
+
type: Muennighoff/xstory_cloze
|
| 685 |
+
name: XStoryCloze (my)
|
| 686 |
+
config: my
|
| 687 |
+
split: validation
|
| 688 |
+
revision: 8bb76e594b68147f1a430e86829d07189622b90d
|
| 689 |
+
metrics:
|
| 690 |
+
- type: Accuracy
|
| 691 |
+
value: 87.49
|
| 692 |
+
- task:
|
| 693 |
+
type: Sentence completion
|
| 694 |
+
dataset:
|
| 695 |
+
type: Muennighoff/xstory_cloze
|
| 696 |
+
name: XStoryCloze (ru)
|
| 697 |
+
config: ru
|
| 698 |
+
split: validation
|
| 699 |
+
revision: 8bb76e594b68147f1a430e86829d07189622b90d
|
| 700 |
+
metrics:
|
| 701 |
+
- type: Accuracy
|
| 702 |
+
value: 91.4
|
| 703 |
+
- task:
|
| 704 |
+
type: Sentence completion
|
| 705 |
+
dataset:
|
| 706 |
+
type: Muennighoff/xstory_cloze
|
| 707 |
+
name: XStoryCloze (sw)
|
| 708 |
+
config: sw
|
| 709 |
+
split: validation
|
| 710 |
+
revision: 8bb76e594b68147f1a430e86829d07189622b90d
|
| 711 |
+
metrics:
|
| 712 |
+
- type: Accuracy
|
| 713 |
+
value: 89.41
|
| 714 |
+
- task:
|
| 715 |
+
type: Sentence completion
|
| 716 |
+
dataset:
|
| 717 |
+
type: Muennighoff/xstory_cloze
|
| 718 |
+
name: XStoryCloze (te)
|
| 719 |
+
config: te
|
| 720 |
+
split: validation
|
| 721 |
+
revision: 8bb76e594b68147f1a430e86829d07189622b90d
|
| 722 |
+
metrics:
|
| 723 |
+
- type: Accuracy
|
| 724 |
+
value: 90.54
|
| 725 |
+
- task:
|
| 726 |
+
type: Sentence completion
|
| 727 |
+
dataset:
|
| 728 |
+
type: Muennighoff/xstory_cloze
|
| 729 |
+
name: XStoryCloze (zh)
|
| 730 |
+
config: zh
|
| 731 |
+
split: validation
|
| 732 |
+
revision: 8bb76e594b68147f1a430e86829d07189622b90d
|
| 733 |
+
metrics:
|
| 734 |
+
- type: Accuracy
|
| 735 |
+
value: 93.85
|
| 736 |
+
pipeline_tag: text2text-generation
|
| 737 |
+
---
|
| 738 |
+
|
| 739 |
+
|
| 740 |
+
|
| 741 |
+
# Table of Contents
|
| 742 |
+
|
| 743 |
+
1. [Model Summary](#model-summary)
|
| 744 |
+
2. [Use](#use)
|
| 745 |
+
3. [Limitations](#limitations)
|
| 746 |
+
4. [Training](#training)
|
| 747 |
+
5. [Evaluation](#evaluation)
|
| 748 |
+
7. [Citation](#citation)
|
| 749 |
+
|
| 750 |
+
# Model Summary
|
| 751 |
+
|
| 752 |
+
> We present BLOOMZ & mT0, a family of models capable of following human instructions in dozens of languages zero-shot. We finetune BLOOM & mT5 pretrained multilingual language models on our crosslingual task mixture (xP3) and find our resulting models capable of crosslingual generalization to unseen tasks & languages.
|
| 753 |
+
|
| 754 |
+
- **Repository:** [bigscience-workshop/xmtf](https://github.com/bigscience-workshop/xmtf)
|
| 755 |
+
- **Paper:** [Crosslingual Generalization through Multitask Finetuning](https://arxiv.org/abs/2211.01786)
|
| 756 |
+
- **Point of Contact:** [Niklas Muennighoff](mailto:[email protected])
|
| 757 |
+
- **Languages:** Refer to [mc4](https://huggingface.co/datasets/mc4) for pretraining & [xP3](https://huggingface.co/bigscience/xP3) for finetuning language proportions. It understands both pretraining & finetuning languages.
|
| 758 |
+
- **BLOOMZ & mT0 Model Family:**
|
| 759 |
+
|
| 760 |
+
<div class="max-w-full overflow-auto">
|
| 761 |
+
<table>
|
| 762 |
+
<tr>
|
| 763 |
+
<th colspan="12">Multitask finetuned on <a style="font-weight:bold" href=https://huggingface.co/datasets/bigscience/xP3>xP3</a>. Recommended for prompting in English.
|
| 764 |
+
</tr>
|
| 765 |
+
<tr>
|
| 766 |
+
<td>Parameters</td>
|
| 767 |
+
<td>300M</td>
|
| 768 |
+
<td>580M</td>
|
| 769 |
+
<td>1.2B</td>
|
| 770 |
+
<td>3.7B</td>
|
| 771 |
+
<td>13B</td>
|
| 772 |
+
<td>560M</td>
|
| 773 |
+
<td>1.1B</td>
|
| 774 |
+
<td>1.7B</td>
|
| 775 |
+
<td>3B</td>
|
| 776 |
+
<td>7.1B</td>
|
| 777 |
+
<td>176B</td>
|
| 778 |
+
</tr>
|
| 779 |
+
<tr>
|
| 780 |
+
<td>Finetuned Model</td>
|
| 781 |
+
<td><a href=https://huggingface.co/bigscience/mt0-small>mt0-small</a></td>
|
| 782 |
+
<td><a href=https://huggingface.co/bigscience/mt0-base>mt0-base</a></td>
|
| 783 |
+
<td><a href=https://huggingface.co/bigscience/mt0-large>mt0-large</a></td>
|
| 784 |
+
<td><a href=https://huggingface.co/bigscience/mt0-xl>mt0-xl</a></td>
|
| 785 |
+
<td><a href=https://huggingface.co/bigscience/mt0-xxl>mt0-xxl</a></td>
|
| 786 |
+
<td><a href=https://huggingface.co/bigscience/bloomz-560m>bloomz-560m</a></td>
|
| 787 |
+
<td><a href=https://huggingface.co/bigscience/bloomz-1b1>bloomz-1b1</a></td>
|
| 788 |
+
<td><a href=https://huggingface.co/bigscience/bloomz-1b7>bloomz-1b7</a></td>
|
| 789 |
+
<td><a href=https://huggingface.co/bigscience/bloomz-3b>bloomz-3b</a></td>
|
| 790 |
+
<td><a href=https://huggingface.co/bigscience/bloomz-7b1>bloomz-7b1</a></td>
|
| 791 |
+
<td><a href=https://huggingface.co/bigscience/bloomz>bloomz</a></td>
|
| 792 |
+
</tr>
|
| 793 |
+
</tr>
|
| 794 |
+
<tr>
|
| 795 |
+
<th colspan="12">Multitask finetuned on <a style="font-weight:bold" href=https://huggingface.co/datasets/bigscience/xP3mt>xP3mt</a>. Recommended for prompting in non-English.</th>
|
| 796 |
+
</tr>
|
| 797 |
+
<tr>
|
| 798 |
+
<td>Finetuned Model</td>
|
| 799 |
+
<td></td>
|
| 800 |
+
<td></td>
|
| 801 |
+
<td></td>
|
| 802 |
+
<td></td>
|
| 803 |
+
<td><a href=https://huggingface.co/bigscience/mt0-xxl-mt>mt0-xxl-mt</a></td>
|
| 804 |
+
<td></td>
|
| 805 |
+
<td></td>
|
| 806 |
+
<td></td>
|
| 807 |
+
<td></td>
|
| 808 |
+
<td><a href=https://huggingface.co/bigscience/bloomz-7b1-mt>bloomz-7b1-mt</a></td>
|
| 809 |
+
<td><a href=https://huggingface.co/bigscience/bloomz-mt>bloomz-mt</a></td>
|
| 810 |
+
</tr>
|
| 811 |
+
<th colspan="12">Multitask finetuned on <a style="font-weight:bold" href=https://huggingface.co/datasets/Muennighoff/P3>P3</a>. Released for research purposes only. Strictly inferior to above models!</th>
|
| 812 |
+
</tr>
|
| 813 |
+
<tr>
|
| 814 |
+
<td>Finetuned Model</td>
|
| 815 |
+
<td></td>
|
| 816 |
+
<td></td>
|
| 817 |
+
<td></td>
|
| 818 |
+
<td></td>
|
| 819 |
+
<td><a href=https://huggingface.co/bigscience/mt0-xxl-p3>mt0-xxl-p3</a></td>
|
| 820 |
+
<td></td>
|
| 821 |
+
<td></td>
|
| 822 |
+
<td></td>
|
| 823 |
+
<td></td>
|
| 824 |
+
<td><a href=https://huggingface.co/bigscience/bloomz-7b1-p3>bloomz-7b1-p3</a></td>
|
| 825 |
+
<td><a href=https://huggingface.co/bigscience/bloomz-p3>bloomz-p3</a></td>
|
| 826 |
+
</tr>
|
| 827 |
+
<th colspan="12">Original pretrained checkpoints. Not recommended.</th>
|
| 828 |
+
<tr>
|
| 829 |
+
<td>Pretrained Model</td>
|
| 830 |
+
<td><a href=https://huggingface.co/google/mt5-small>mt5-small</a></td>
|
| 831 |
+
<td><a href=https://huggingface.co/google/mt5-base>mt5-base</a></td>
|
| 832 |
+
<td><a href=https://huggingface.co/google/mt5-large>mt5-large</a></td>
|
| 833 |
+
<td><a href=https://huggingface.co/google/mt5-xl>mt5-xl</a></td>
|
| 834 |
+
<td><a href=https://huggingface.co/google/mt5-xxl>mt5-xxl</a></td>
|
| 835 |
+
<td><a href=https://huggingface.co/bigscience/bloom-560m>bloom-560m</a></td>
|
| 836 |
+
<td><a href=https://huggingface.co/bigscience/bloom-1b1>bloom-1b1</a></td>
|
| 837 |
+
<td><a href=https://huggingface.co/bigscience/bloom-1b7>bloom-1b7</a></td>
|
| 838 |
+
<td><a href=https://huggingface.co/bigscience/bloom-3b>bloom-3b</a></td>
|
| 839 |
+
<td><a href=https://huggingface.co/bigscience/bloom-7b1>bloom-7b1</a></td>
|
| 840 |
+
<td><a href=https://huggingface.co/bigscience/bloom>bloom</a></td>
|
| 841 |
+
</tr>
|
| 842 |
+
</table>
|
| 843 |
+
</div>
|
| 844 |
+
|
| 845 |
+
|
| 846 |
+
# Use
|
| 847 |
+
|
| 848 |
+
## Intended use
|
| 849 |
+
|
| 850 |
+
We recommend using the model to perform tasks expressed in natural language. For example, given the prompt "*Translate to English: Je t’aime.*", the model will most likely answer "*I love you.*". Some prompt ideas from our paper:
|
| 851 |
+
- 一个传奇的开端，一个不灭的神话，这不仅仅是一部电影，而是作为一个走进新时代的标签，永远彪炳史册。你认为这句话的立场是赞扬、中立还是批评?
|
| 852 |
+
- Suggest at least five related search terms to "Mạng neural nhân tạo".
|
| 853 |
+
- Write a fairy tale about a troll saving a princess from a dangerous dragon. The fairy tale is a masterpiece that has achieved praise worldwide and its moral is "Heroes Come in All Shapes and Sizes". Story (in Spanish):
|
| 854 |
+
- Explain in a sentence in Telugu what is backpropagation in neural networks.
|
| 855 |
+
|
| 856 |
+
**Feel free to share your generations in the Community tab!**
|
| 857 |
+
|
| 858 |
+
## How to use
|
| 859 |
+
|
| 860 |
+
### CPU
|
| 861 |
+
|
| 862 |
+
<details>
|
| 863 |
+
<summary> Click to expand </summary>
|
| 864 |
+
|
| 865 |
+
```python
|
| 866 |
+
# pip install -q transformers
|
| 867 |
+
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
|
| 868 |
+
|
| 869 |
+
checkpoint = "bigscience/mt0-xxl"
|
| 870 |
+
|
| 871 |
+
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
|
| 872 |
+
model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)
|
| 873 |
+
|
| 874 |
+
inputs = tokenizer.encode("Translate to English: Je t’aime.", return_tensors="pt")
|
| 875 |
+
outputs = model.generate(inputs)
|
| 876 |
+
print(tokenizer.decode(outputs[0]))
|
| 877 |
+
```
|
| 878 |
+
|
| 879 |
+
</details>
|
| 880 |
+
|
| 881 |
+
### GPU
|
| 882 |
+
|
| 883 |
+
<details>
|
| 884 |
+
<summary> Click to expand </summary>
|
| 885 |
+
|
| 886 |
+
```python
|
| 887 |
+
# pip install -q transformers accelerate
|
| 888 |
+
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
|
| 889 |
+
|
| 890 |
+
checkpoint = "bigscience/mt0-xxl"
|
| 891 |
+
|
| 892 |
+
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
|
| 893 |
+
model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint, torch_dtype="auto", device_map="auto")
|
| 894 |
+
|
| 895 |
+
inputs = tokenizer.encode("Translate to English: Je t’aime.", return_tensors="pt").to("cuda")
|
| 896 |
+
outputs = model.generate(inputs)
|
| 897 |
+
print(tokenizer.decode(outputs[0]))
|
| 898 |
+
```
|
| 899 |
+
|
| 900 |
+
</details>
|
| 901 |
+
|
| 902 |
+
### GPU in 8bit
|
| 903 |
+
|
| 904 |
+
<details>
|
| 905 |
+
<summary> Click to expand </summary>
|
| 906 |
+
|
| 907 |
+
```python
|
| 908 |
+
# pip install -q transformers accelerate bitsandbytes
|
| 909 |
+
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
|
| 910 |
+
|
| 911 |
+
checkpoint = "bigscience/mt0-xxl"
|
| 912 |
+
|
| 913 |
+
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
|
| 914 |
+
model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint, device_map="auto", load_in_8bit=True)
|
| 915 |
+
|
| 916 |
+
inputs = tokenizer.encode("Translate to English: Je t’aime.", return_tensors="pt").to("cuda")
|
| 917 |
+
outputs = model.generate(inputs)
|
| 918 |
+
print(tokenizer.decode(outputs[0]))
|
| 919 |
+
```
|
| 920 |
+
|
| 921 |
+
</details>
|
| 922 |
+
|
| 923 |
+
<!-- Necessary for whitespace -->
|
| 924 |
+
###
|
| 925 |
+
|
| 926 |
+
# Limitations
|
| 927 |
+
|
| 928 |
+
**Prompt Engineering:** The performance may vary depending on the prompt. For BLOOMZ models, we recommend making it very clear when the input stops to avoid the model trying to continue it. For example, the prompt "*Translate to English: Je t'aime*" without the full stop (.) at the end, may result in the model trying to continue the French sentence. Better prompts are e.g. "*Translate to English: Je t'aime.*", "*Translate to English: Je t'aime. Translation:*" "*What is "Je t'aime." in English?*", where it is clear for the model when it should answer. Further, we recommend providing the model as much context as possible. For example, if you want it to answer in Telugu, then tell the model, e.g. "*Explain in a sentence in Telugu what is backpropagation in neural networks.*".
|
| 929 |
+
|
| 930 |
+
# Training
|
| 931 |
+
|
| 932 |
+
## Model
|
| 933 |
+
|
| 934 |
+
- **Architecture:** Same as [mt5-xxl](https://huggingface.co/google/mt5-xxl), also refer to the `config.json` file
|
| 935 |
+
- **Finetuning steps:** 7000
|
| 936 |
+
- **Finetuning tokens:** 1.29 billion
|
| 937 |
+
- **Precision:** bfloat16
|
| 938 |
+
|
| 939 |
+
## Hardware
|
| 940 |
+
|
| 941 |
+
- **TPUs:** TPUv4-256
|
| 942 |
+
|
| 943 |
+
## Software
|
| 944 |
+
|
| 945 |
+
- **Orchestration:** [T5X](https://github.com/google-research/t5x)
|
| 946 |
+
- **Neural networks:** [Jax](https://github.com/google/jax)
|
| 947 |
+
|
| 948 |
+
# Evaluation
|
| 949 |
+
|
| 950 |
+
We refer to Table 7 from our [paper](https://arxiv.org/abs/2211.01786) & [bigscience/evaluation-results](https://huggingface.co/datasets/bigscience/evaluation-results) for zero-shot results on unseen tasks. The sidebar reports zero-shot performance of the best prompt per dataset config.
|
| 951 |
+
|
| 952 |
+
# Citation
|
| 953 |
+
```bibtex
|
| 954 |
+
@article{muennighoff2022crosslingual,
|
| 955 |
+
title={Crosslingual generalization through multitask finetuning},
|
| 956 |
+
author={Muennighoff, Niklas and Wang, Thomas and Sutawika, Lintang and Roberts, Adam and Biderman, Stella and Scao, Teven Le and Bari, M Saiful and Shen, Sheng and Yong, Zheng-Xin and Schoelkopf, Hailey and others},
|
| 957 |
+
journal={arXiv preprint arXiv:2211.01786},
|
| 958 |
+
year={2022}
|
| 959 |
+
}
|
| 960 |
+
```
|
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/mt5-xxl",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 10240,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 4096,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": true,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "mt5",
|
| 19 |
+
"num_decoder_layers": 24,
|
| 20 |
+
"num_heads": 64,
|
| 21 |
+
"num_layers": 24,
|
| 22 |
+
"output_past": true,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"relative_attention_max_distance": 128,
|
| 25 |
+
"relative_attention_num_buckets": 32,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"tokenizer_class": "T5Tokenizer",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.23.1",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 250112
|
| 32 |
+
}
|
model-00001-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d248e71582e351642d5e44e381e9be233ee2b04eb5833a7603d69ed51ac39585
|
| 3 |
+
size 9936568872
|
model-00002-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eda538fe84abd7cab450a68c69a76588dc7a6c34ddc2418b6ab0e514bcdc0952
|
| 3 |
+
size 9865443384
|
model-00003-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:881ec52a2544492e0a96949cef398ba8c9b2aa37a33618a0c37f418fa259a94e
|
| 3 |
+
size 9869476808
|
model-00004-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fee75c951a13df924f0d496087fb477c4c72ac1c6a26f4b860ceaa825014cb87
|
| 3 |
+
size 9999712688
|
model-00005-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:644f87dc1851d7c073cb46747fb0fb72738174e93ed0e07fd7c8e6aeca002f3d
|
| 3 |
+
size 9999712416
|
model-00006-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:287e19e2e0b91211df7cf90d8760e60572ca04b1ada82110e582a4581baa9255
|
| 3 |
+
size 6111219176
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,566 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 55782064128
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"decoder.block.0.layer.0.SelfAttention.k.weight": "model-00003-of-00006.safetensors",
|
| 7 |
+
"decoder.block.0.layer.0.SelfAttention.o.weight": "model-00003-of-00006.safetensors",
|
| 8 |
+
"decoder.block.0.layer.0.SelfAttention.q.weight": "model-00003-of-00006.safetensors",
|
| 9 |
+
"decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00006.safetensors",
|
| 10 |
+
"decoder.block.0.layer.0.SelfAttention.v.weight": "model-00003-of-00006.safetensors",
|
| 11 |
+
"decoder.block.0.layer.0.layer_norm.weight": "model-00003-of-00006.safetensors",
|
| 12 |
+
"decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00003-of-00006.safetensors",
|
| 13 |
+
"decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00003-of-00006.safetensors",
|
| 14 |
+
"decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00003-of-00006.safetensors",
|
| 15 |
+
"decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00003-of-00006.safetensors",
|
| 16 |
+
"decoder.block.0.layer.1.layer_norm.weight": "model-00003-of-00006.safetensors",
|
| 17 |
+
"decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00006.safetensors",
|
| 18 |
+
"decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00006.safetensors",
|
| 19 |
+
"decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00003-of-00006.safetensors",
|
| 20 |
+
"decoder.block.0.layer.2.layer_norm.weight": "model-00003-of-00006.safetensors",
|
| 21 |
+
"decoder.block.1.layer.0.SelfAttention.k.weight": "model-00003-of-00006.safetensors",
|
| 22 |
+
"decoder.block.1.layer.0.SelfAttention.o.weight": "model-00003-of-00006.safetensors",
|
| 23 |
+
"decoder.block.1.layer.0.SelfAttention.q.weight": "model-00003-of-00006.safetensors",
|
| 24 |
+
"decoder.block.1.layer.0.SelfAttention.v.weight": "model-00003-of-00006.safetensors",
|
| 25 |
+
"decoder.block.1.layer.0.layer_norm.weight": "model-00003-of-00006.safetensors",
|
| 26 |
+
"decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00003-of-00006.safetensors",
|
| 27 |
+
"decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00003-of-00006.safetensors",
|
| 28 |
+
"decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00003-of-00006.safetensors",
|
| 29 |
+
"decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00003-of-00006.safetensors",
|
| 30 |
+
"decoder.block.1.layer.1.layer_norm.weight": "model-00003-of-00006.safetensors",
|
| 31 |
+
"decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00006.safetensors",
|
| 32 |
+
"decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00006.safetensors",
|
| 33 |
+
"decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00003-of-00006.safetensors",
|
| 34 |
+
"decoder.block.1.layer.2.layer_norm.weight": "model-00003-of-00006.safetensors",
|
| 35 |
+
"decoder.block.10.layer.0.SelfAttention.k.weight": "model-00004-of-00006.safetensors",
|
| 36 |
+
"decoder.block.10.layer.0.SelfAttention.o.weight": "model-00004-of-00006.safetensors",
|
| 37 |
+
"decoder.block.10.layer.0.SelfAttention.q.weight": "model-00004-of-00006.safetensors",
|
| 38 |
+
"decoder.block.10.layer.0.SelfAttention.v.weight": "model-00004-of-00006.safetensors",
|
| 39 |
+
"decoder.block.10.layer.0.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 40 |
+
"decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00004-of-00006.safetensors",
|
| 41 |
+
"decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00004-of-00006.safetensors",
|
| 42 |
+
"decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00004-of-00006.safetensors",
|
| 43 |
+
"decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00004-of-00006.safetensors",
|
| 44 |
+
"decoder.block.10.layer.1.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 45 |
+
"decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00006.safetensors",
|
| 46 |
+
"decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00006.safetensors",
|
| 47 |
+
"decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00004-of-00006.safetensors",
|
| 48 |
+
"decoder.block.10.layer.2.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 49 |
+
"decoder.block.11.layer.0.SelfAttention.k.weight": "model-00004-of-00006.safetensors",
|
| 50 |
+
"decoder.block.11.layer.0.SelfAttention.o.weight": "model-00004-of-00006.safetensors",
|
| 51 |
+
"decoder.block.11.layer.0.SelfAttention.q.weight": "model-00004-of-00006.safetensors",
|
| 52 |
+
"decoder.block.11.layer.0.SelfAttention.v.weight": "model-00004-of-00006.safetensors",
|
| 53 |
+
"decoder.block.11.layer.0.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 54 |
+
"decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00004-of-00006.safetensors",
|
| 55 |
+
"decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00004-of-00006.safetensors",
|
| 56 |
+
"decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00004-of-00006.safetensors",
|
| 57 |
+
"decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00004-of-00006.safetensors",
|
| 58 |
+
"decoder.block.11.layer.1.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 59 |
+
"decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00006.safetensors",
|
| 60 |
+
"decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00006.safetensors",
|
| 61 |
+
"decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00004-of-00006.safetensors",
|
| 62 |
+
"decoder.block.11.layer.2.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 63 |
+
"decoder.block.12.layer.0.SelfAttention.k.weight": "model-00004-of-00006.safetensors",
|
| 64 |
+
"decoder.block.12.layer.0.SelfAttention.o.weight": "model-00004-of-00006.safetensors",
|
| 65 |
+
"decoder.block.12.layer.0.SelfAttention.q.weight": "model-00004-of-00006.safetensors",
|
| 66 |
+
"decoder.block.12.layer.0.SelfAttention.v.weight": "model-00004-of-00006.safetensors",
|
| 67 |
+
"decoder.block.12.layer.0.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 68 |
+
"decoder.block.12.layer.1.EncDecAttention.k.weight": "model-00004-of-00006.safetensors",
|
| 69 |
+
"decoder.block.12.layer.1.EncDecAttention.o.weight": "model-00005-of-00006.safetensors",
|
| 70 |
+
"decoder.block.12.layer.1.EncDecAttention.q.weight": "model-00004-of-00006.safetensors",
|
| 71 |
+
"decoder.block.12.layer.1.EncDecAttention.v.weight": "model-00004-of-00006.safetensors",
|
| 72 |
+
"decoder.block.12.layer.1.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 73 |
+
"decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00006.safetensors",
|
| 74 |
+
"decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00006.safetensors",
|
| 75 |
+
"decoder.block.12.layer.2.DenseReluDense.wo.weight": "model-00005-of-00006.safetensors",
|
| 76 |
+
"decoder.block.12.layer.2.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 77 |
+
"decoder.block.13.layer.0.SelfAttention.k.weight": "model-00005-of-00006.safetensors",
|
| 78 |
+
"decoder.block.13.layer.0.SelfAttention.o.weight": "model-00005-of-00006.safetensors",
|
| 79 |
+
"decoder.block.13.layer.0.SelfAttention.q.weight": "model-00005-of-00006.safetensors",
|
| 80 |
+
"decoder.block.13.layer.0.SelfAttention.v.weight": "model-00005-of-00006.safetensors",
|
| 81 |
+
"decoder.block.13.layer.0.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 82 |
+
"decoder.block.13.layer.1.EncDecAttention.k.weight": "model-00005-of-00006.safetensors",
|
| 83 |
+
"decoder.block.13.layer.1.EncDecAttention.o.weight": "model-00005-of-00006.safetensors",
|
| 84 |
+
"decoder.block.13.layer.1.EncDecAttention.q.weight": "model-00005-of-00006.safetensors",
|
| 85 |
+
"decoder.block.13.layer.1.EncDecAttention.v.weight": "model-00005-of-00006.safetensors",
|
| 86 |
+
"decoder.block.13.layer.1.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 87 |
+
"decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00006.safetensors",
|
| 88 |
+
"decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00006.safetensors",
|
| 89 |
+
"decoder.block.13.layer.2.DenseReluDense.wo.weight": "model-00005-of-00006.safetensors",
|
| 90 |
+
"decoder.block.13.layer.2.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 91 |
+
"decoder.block.14.layer.0.SelfAttention.k.weight": "model-00005-of-00006.safetensors",
|
| 92 |
+
"decoder.block.14.layer.0.SelfAttention.o.weight": "model-00005-of-00006.safetensors",
|
| 93 |
+
"decoder.block.14.layer.0.SelfAttention.q.weight": "model-00005-of-00006.safetensors",
|
| 94 |
+
"decoder.block.14.layer.0.SelfAttention.v.weight": "model-00005-of-00006.safetensors",
|
| 95 |
+
"decoder.block.14.layer.0.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 96 |
+
"decoder.block.14.layer.1.EncDecAttention.k.weight": "model-00005-of-00006.safetensors",
|
| 97 |
+
"decoder.block.14.layer.1.EncDecAttention.o.weight": "model-00005-of-00006.safetensors",
|
| 98 |
+
"decoder.block.14.layer.1.EncDecAttention.q.weight": "model-00005-of-00006.safetensors",
|
| 99 |
+
"decoder.block.14.layer.1.EncDecAttention.v.weight": "model-00005-of-00006.safetensors",
|
| 100 |
+
"decoder.block.14.layer.1.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 101 |
+
"decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00006.safetensors",
|
| 102 |
+
"decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00006.safetensors",
|
| 103 |
+
"decoder.block.14.layer.2.DenseReluDense.wo.weight": "model-00005-of-00006.safetensors",
|
| 104 |
+
"decoder.block.14.layer.2.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 105 |
+
"decoder.block.15.layer.0.SelfAttention.k.weight": "model-00005-of-00006.safetensors",
|
| 106 |
+
"decoder.block.15.layer.0.SelfAttention.o.weight": "model-00005-of-00006.safetensors",
|
| 107 |
+
"decoder.block.15.layer.0.SelfAttention.q.weight": "model-00005-of-00006.safetensors",
|
| 108 |
+
"decoder.block.15.layer.0.SelfAttention.v.weight": "model-00005-of-00006.safetensors",
|
| 109 |
+
"decoder.block.15.layer.0.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 110 |
+
"decoder.block.15.layer.1.EncDecAttention.k.weight": "model-00005-of-00006.safetensors",
|
| 111 |
+
"decoder.block.15.layer.1.EncDecAttention.o.weight": "model-00005-of-00006.safetensors",
|
| 112 |
+
"decoder.block.15.layer.1.EncDecAttention.q.weight": "model-00005-of-00006.safetensors",
|
| 113 |
+
"decoder.block.15.layer.1.EncDecAttention.v.weight": "model-00005-of-00006.safetensors",
|
| 114 |
+
"decoder.block.15.layer.1.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 115 |
+
"decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00006.safetensors",
|
| 116 |
+
"decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00006.safetensors",
|
| 117 |
+
"decoder.block.15.layer.2.DenseReluDense.wo.weight": "model-00005-of-00006.safetensors",
|
| 118 |
+
"decoder.block.15.layer.2.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 119 |
+
"decoder.block.16.layer.0.SelfAttention.k.weight": "model-00005-of-00006.safetensors",
|
| 120 |
+
"decoder.block.16.layer.0.SelfAttention.o.weight": "model-00005-of-00006.safetensors",
|
| 121 |
+
"decoder.block.16.layer.0.SelfAttention.q.weight": "model-00005-of-00006.safetensors",
|
| 122 |
+
"decoder.block.16.layer.0.SelfAttention.v.weight": "model-00005-of-00006.safetensors",
|
| 123 |
+
"decoder.block.16.layer.0.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 124 |
+
"decoder.block.16.layer.1.EncDecAttention.k.weight": "model-00005-of-00006.safetensors",
|
| 125 |
+
"decoder.block.16.layer.1.EncDecAttention.o.weight": "model-00005-of-00006.safetensors",
|
| 126 |
+
"decoder.block.16.layer.1.EncDecAttention.q.weight": "model-00005-of-00006.safetensors",
|
| 127 |
+
"decoder.block.16.layer.1.EncDecAttention.v.weight": "model-00005-of-00006.safetensors",
|
| 128 |
+
"decoder.block.16.layer.1.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 129 |
+
"decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00006.safetensors",
|
| 130 |
+
"decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00006.safetensors",
|
| 131 |
+
"decoder.block.16.layer.2.DenseReluDense.wo.weight": "model-00005-of-00006.safetensors",
|
| 132 |
+
"decoder.block.16.layer.2.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 133 |
+
"decoder.block.17.layer.0.SelfAttention.k.weight": "model-00005-of-00006.safetensors",
|
| 134 |
+
"decoder.block.17.layer.0.SelfAttention.o.weight": "model-00005-of-00006.safetensors",
|
| 135 |
+
"decoder.block.17.layer.0.SelfAttention.q.weight": "model-00005-of-00006.safetensors",
|
| 136 |
+
"decoder.block.17.layer.0.SelfAttention.v.weight": "model-00005-of-00006.safetensors",
|
| 137 |
+
"decoder.block.17.layer.0.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 138 |
+
"decoder.block.17.layer.1.EncDecAttention.k.weight": "model-00005-of-00006.safetensors",
|
| 139 |
+
"decoder.block.17.layer.1.EncDecAttention.o.weight": "model-00005-of-00006.safetensors",
|
| 140 |
+
"decoder.block.17.layer.1.EncDecAttention.q.weight": "model-00005-of-00006.safetensors",
|
| 141 |
+
"decoder.block.17.layer.1.EncDecAttention.v.weight": "model-00005-of-00006.safetensors",
|
| 142 |
+
"decoder.block.17.layer.1.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 143 |
+
"decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00006.safetensors",
|
| 144 |
+
"decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00006.safetensors",
|
| 145 |
+
"decoder.block.17.layer.2.DenseReluDense.wo.weight": "model-00005-of-00006.safetensors",
|
| 146 |
+
"decoder.block.17.layer.2.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 147 |
+
"decoder.block.18.layer.0.SelfAttention.k.weight": "model-00005-of-00006.safetensors",
|
| 148 |
+
"decoder.block.18.layer.0.SelfAttention.o.weight": "model-00005-of-00006.safetensors",
|
| 149 |
+
"decoder.block.18.layer.0.SelfAttention.q.weight": "model-00005-of-00006.safetensors",
|
| 150 |
+
"decoder.block.18.layer.0.SelfAttention.v.weight": "model-00005-of-00006.safetensors",
|
| 151 |
+
"decoder.block.18.layer.0.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 152 |
+
"decoder.block.18.layer.1.EncDecAttention.k.weight": "model-00005-of-00006.safetensors",
|
| 153 |
+
"decoder.block.18.layer.1.EncDecAttention.o.weight": "model-00005-of-00006.safetensors",
|
| 154 |
+
"decoder.block.18.layer.1.EncDecAttention.q.weight": "model-00005-of-00006.safetensors",
|
| 155 |
+
"decoder.block.18.layer.1.EncDecAttention.v.weight": "model-00005-of-00006.safetensors",
|
| 156 |
+
"decoder.block.18.layer.1.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 157 |
+
"decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00006.safetensors",
|
| 158 |
+
"decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00006.safetensors",
|
| 159 |
+
"decoder.block.18.layer.2.DenseReluDense.wo.weight": "model-00005-of-00006.safetensors",
|
| 160 |
+
"decoder.block.18.layer.2.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 161 |
+
"decoder.block.19.layer.0.SelfAttention.k.weight": "model-00005-of-00006.safetensors",
|
| 162 |
+
"decoder.block.19.layer.0.SelfAttention.o.weight": "model-00005-of-00006.safetensors",
|
| 163 |
+
"decoder.block.19.layer.0.SelfAttention.q.weight": "model-00005-of-00006.safetensors",
|
| 164 |
+
"decoder.block.19.layer.0.SelfAttention.v.weight": "model-00005-of-00006.safetensors",
|
| 165 |
+
"decoder.block.19.layer.0.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 166 |
+
"decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00005-of-00006.safetensors",
|
| 167 |
+
"decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00005-of-00006.safetensors",
|
| 168 |
+
"decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00005-of-00006.safetensors",
|
| 169 |
+
"decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00005-of-00006.safetensors",
|
| 170 |
+
"decoder.block.19.layer.1.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 171 |
+
"decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00006.safetensors",
|
| 172 |
+
"decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00006.safetensors",
|
| 173 |
+
"decoder.block.19.layer.2.DenseReluDense.wo.weight": "model-00005-of-00006.safetensors",
|
| 174 |
+
"decoder.block.19.layer.2.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 175 |
+
"decoder.block.2.layer.0.SelfAttention.k.weight": "model-00003-of-00006.safetensors",
|
| 176 |
+
"decoder.block.2.layer.0.SelfAttention.o.weight": "model-00003-of-00006.safetensors",
|
| 177 |
+
"decoder.block.2.layer.0.SelfAttention.q.weight": "model-00003-of-00006.safetensors",
|
| 178 |
+
"decoder.block.2.layer.0.SelfAttention.v.weight": "model-00003-of-00006.safetensors",
|
| 179 |
+
"decoder.block.2.layer.0.layer_norm.weight": "model-00003-of-00006.safetensors",
|
| 180 |
+
"decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00003-of-00006.safetensors",
|
| 181 |
+
"decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00003-of-00006.safetensors",
|
| 182 |
+
"decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00003-of-00006.safetensors",
|
| 183 |
+
"decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00003-of-00006.safetensors",
|
| 184 |
+
"decoder.block.2.layer.1.layer_norm.weight": "model-00003-of-00006.safetensors",
|
| 185 |
+
"decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00006.safetensors",
|
| 186 |
+
"decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00006.safetensors",
|
| 187 |
+
"decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00004-of-00006.safetensors",
|
| 188 |
+
"decoder.block.2.layer.2.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 189 |
+
"decoder.block.20.layer.0.SelfAttention.k.weight": "model-00005-of-00006.safetensors",
|
| 190 |
+
"decoder.block.20.layer.0.SelfAttention.o.weight": "model-00005-of-00006.safetensors",
|
| 191 |
+
"decoder.block.20.layer.0.SelfAttention.q.weight": "model-00005-of-00006.safetensors",
|
| 192 |
+
"decoder.block.20.layer.0.SelfAttention.v.weight": "model-00005-of-00006.safetensors",
|
| 193 |
+
"decoder.block.20.layer.0.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 194 |
+
"decoder.block.20.layer.1.EncDecAttention.k.weight": "model-00005-of-00006.safetensors",
|
| 195 |
+
"decoder.block.20.layer.1.EncDecAttention.o.weight": "model-00005-of-00006.safetensors",
|
| 196 |
+
"decoder.block.20.layer.1.EncDecAttention.q.weight": "model-00005-of-00006.safetensors",
|
| 197 |
+
"decoder.block.20.layer.1.EncDecAttention.v.weight": "model-00005-of-00006.safetensors",
|
| 198 |
+
"decoder.block.20.layer.1.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 199 |
+
"decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00006.safetensors",
|
| 200 |
+
"decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00006.safetensors",
|
| 201 |
+
"decoder.block.20.layer.2.DenseReluDense.wo.weight": "model-00005-of-00006.safetensors",
|
| 202 |
+
"decoder.block.20.layer.2.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 203 |
+
"decoder.block.21.layer.0.SelfAttention.k.weight": "model-00005-of-00006.safetensors",
|
| 204 |
+
"decoder.block.21.layer.0.SelfAttention.o.weight": "model-00005-of-00006.safetensors",
|
| 205 |
+
"decoder.block.21.layer.0.SelfAttention.q.weight": "model-00005-of-00006.safetensors",
|
| 206 |
+
"decoder.block.21.layer.0.SelfAttention.v.weight": "model-00005-of-00006.safetensors",
|
| 207 |
+
"decoder.block.21.layer.0.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 208 |
+
"decoder.block.21.layer.1.EncDecAttention.k.weight": "model-00005-of-00006.safetensors",
|
| 209 |
+
"decoder.block.21.layer.1.EncDecAttention.o.weight": "model-00005-of-00006.safetensors",
|
| 210 |
+
"decoder.block.21.layer.1.EncDecAttention.q.weight": "model-00005-of-00006.safetensors",
|
| 211 |
+
"decoder.block.21.layer.1.EncDecAttention.v.weight": "model-00005-of-00006.safetensors",
|
| 212 |
+
"decoder.block.21.layer.1.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 213 |
+
"decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00006.safetensors",
|
| 214 |
+
"decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00006.safetensors",
|
| 215 |
+
"decoder.block.21.layer.2.DenseReluDense.wo.weight": "model-00005-of-00006.safetensors",
|
| 216 |
+
"decoder.block.21.layer.2.layer_norm.weight": "model-00005-of-00006.safetensors",
|
| 217 |
+
"decoder.block.22.layer.0.SelfAttention.k.weight": "model-00006-of-00006.safetensors",
|
| 218 |
+
"decoder.block.22.layer.0.SelfAttention.o.weight": "model-00006-of-00006.safetensors",
|
| 219 |
+
"decoder.block.22.layer.0.SelfAttention.q.weight": "model-00005-of-00006.safetensors",
|
| 220 |
+
"decoder.block.22.layer.0.SelfAttention.v.weight": "model-00006-of-00006.safetensors",
|
| 221 |
+
"decoder.block.22.layer.0.layer_norm.weight": "model-00006-of-00006.safetensors",
|
| 222 |
+
"decoder.block.22.layer.1.EncDecAttention.k.weight": "model-00006-of-00006.safetensors",
|
| 223 |
+
"decoder.block.22.layer.1.EncDecAttention.o.weight": "model-00006-of-00006.safetensors",
|
| 224 |
+
"decoder.block.22.layer.1.EncDecAttention.q.weight": "model-00006-of-00006.safetensors",
|
| 225 |
+
"decoder.block.22.layer.1.EncDecAttention.v.weight": "model-00006-of-00006.safetensors",
|
| 226 |
+
"decoder.block.22.layer.1.layer_norm.weight": "model-00006-of-00006.safetensors",
|
| 227 |
+
"decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00006.safetensors",
|
| 228 |
+
"decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00006.safetensors",
|
| 229 |
+
"decoder.block.22.layer.2.DenseReluDense.wo.weight": "model-00006-of-00006.safetensors",
|
| 230 |
+
"decoder.block.22.layer.2.layer_norm.weight": "model-00006-of-00006.safetensors",
|
| 231 |
+
"decoder.block.23.layer.0.SelfAttention.k.weight": "model-00006-of-00006.safetensors",
|
| 232 |
+
"decoder.block.23.layer.0.SelfAttention.o.weight": "model-00006-of-00006.safetensors",
|
| 233 |
+
"decoder.block.23.layer.0.SelfAttention.q.weight": "model-00006-of-00006.safetensors",
|
| 234 |
+
"decoder.block.23.layer.0.SelfAttention.v.weight": "model-00006-of-00006.safetensors",
|
| 235 |
+
"decoder.block.23.layer.0.layer_norm.weight": "model-00006-of-00006.safetensors",
|
| 236 |
+
"decoder.block.23.layer.1.EncDecAttention.k.weight": "model-00006-of-00006.safetensors",
|
| 237 |
+
"decoder.block.23.layer.1.EncDecAttention.o.weight": "model-00006-of-00006.safetensors",
|
| 238 |
+
"decoder.block.23.layer.1.EncDecAttention.q.weight": "model-00006-of-00006.safetensors",
|
| 239 |
+
"decoder.block.23.layer.1.EncDecAttention.v.weight": "model-00006-of-00006.safetensors",
|
| 240 |
+
"decoder.block.23.layer.1.layer_norm.weight": "model-00006-of-00006.safetensors",
|
| 241 |
+
"decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00006.safetensors",
|
| 242 |
+
"decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00006.safetensors",
|
| 243 |
+
"decoder.block.23.layer.2.DenseReluDense.wo.weight": "model-00006-of-00006.safetensors",
|
| 244 |
+
"decoder.block.23.layer.2.layer_norm.weight": "model-00006-of-00006.safetensors",
|
| 245 |
+
"decoder.block.3.layer.0.SelfAttention.k.weight": "model-00004-of-00006.safetensors",
|
| 246 |
+
"decoder.block.3.layer.0.SelfAttention.o.weight": "model-00004-of-00006.safetensors",
|
| 247 |
+
"decoder.block.3.layer.0.SelfAttention.q.weight": "model-00004-of-00006.safetensors",
|
| 248 |
+
"decoder.block.3.layer.0.SelfAttention.v.weight": "model-00004-of-00006.safetensors",
|
| 249 |
+
"decoder.block.3.layer.0.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 250 |
+
"decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00004-of-00006.safetensors",
|
| 251 |
+
"decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00004-of-00006.safetensors",
|
| 252 |
+
"decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00004-of-00006.safetensors",
|
| 253 |
+
"decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00004-of-00006.safetensors",
|
| 254 |
+
"decoder.block.3.layer.1.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 255 |
+
"decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00006.safetensors",
|
| 256 |
+
"decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00006.safetensors",
|
| 257 |
+
"decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00004-of-00006.safetensors",
|
| 258 |
+
"decoder.block.3.layer.2.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 259 |
+
"decoder.block.4.layer.0.SelfAttention.k.weight": "model-00004-of-00006.safetensors",
|
| 260 |
+
"decoder.block.4.layer.0.SelfAttention.o.weight": "model-00004-of-00006.safetensors",
|
| 261 |
+
"decoder.block.4.layer.0.SelfAttention.q.weight": "model-00004-of-00006.safetensors",
|
| 262 |
+
"decoder.block.4.layer.0.SelfAttention.v.weight": "model-00004-of-00006.safetensors",
|
| 263 |
+
"decoder.block.4.layer.0.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 264 |
+
"decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00004-of-00006.safetensors",
|
| 265 |
+
"decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00004-of-00006.safetensors",
|
| 266 |
+
"decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00004-of-00006.safetensors",
|
| 267 |
+
"decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00004-of-00006.safetensors",
|
| 268 |
+
"decoder.block.4.layer.1.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 269 |
+
"decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00006.safetensors",
|
| 270 |
+
"decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00006.safetensors",
|
| 271 |
+
"decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00004-of-00006.safetensors",
|
| 272 |
+
"decoder.block.4.layer.2.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 273 |
+
"decoder.block.5.layer.0.SelfAttention.k.weight": "model-00004-of-00006.safetensors",
|
| 274 |
+
"decoder.block.5.layer.0.SelfAttention.o.weight": "model-00004-of-00006.safetensors",
|
| 275 |
+
"decoder.block.5.layer.0.SelfAttention.q.weight": "model-00004-of-00006.safetensors",
|
| 276 |
+
"decoder.block.5.layer.0.SelfAttention.v.weight": "model-00004-of-00006.safetensors",
|
| 277 |
+
"decoder.block.5.layer.0.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 278 |
+
"decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00004-of-00006.safetensors",
|
| 279 |
+
"decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00004-of-00006.safetensors",
|
| 280 |
+
"decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00004-of-00006.safetensors",
|
| 281 |
+
"decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00004-of-00006.safetensors",
|
| 282 |
+
"decoder.block.5.layer.1.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 283 |
+
"decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00006.safetensors",
|
| 284 |
+
"decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00006.safetensors",
|
| 285 |
+
"decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00004-of-00006.safetensors",
|
| 286 |
+
"decoder.block.5.layer.2.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 287 |
+
"decoder.block.6.layer.0.SelfAttention.k.weight": "model-00004-of-00006.safetensors",
|
| 288 |
+
"decoder.block.6.layer.0.SelfAttention.o.weight": "model-00004-of-00006.safetensors",
|
| 289 |
+
"decoder.block.6.layer.0.SelfAttention.q.weight": "model-00004-of-00006.safetensors",
|
| 290 |
+
"decoder.block.6.layer.0.SelfAttention.v.weight": "model-00004-of-00006.safetensors",
|
| 291 |
+
"decoder.block.6.layer.0.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 292 |
+
"decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00004-of-00006.safetensors",
|
| 293 |
+
"decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00004-of-00006.safetensors",
|
| 294 |
+
"decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00004-of-00006.safetensors",
|
| 295 |
+
"decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00004-of-00006.safetensors",
|
| 296 |
+
"decoder.block.6.layer.1.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 297 |
+
"decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00006.safetensors",
|
| 298 |
+
"decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00006.safetensors",
|
| 299 |
+
"decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00004-of-00006.safetensors",
|
| 300 |
+
"decoder.block.6.layer.2.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 301 |
+
"decoder.block.7.layer.0.SelfAttention.k.weight": "model-00004-of-00006.safetensors",
|
| 302 |
+
"decoder.block.7.layer.0.SelfAttention.o.weight": "model-00004-of-00006.safetensors",
|
| 303 |
+
"decoder.block.7.layer.0.SelfAttention.q.weight": "model-00004-of-00006.safetensors",
|
| 304 |
+
"decoder.block.7.layer.0.SelfAttention.v.weight": "model-00004-of-00006.safetensors",
|
| 305 |
+
"decoder.block.7.layer.0.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 306 |
+
"decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00004-of-00006.safetensors",
|
| 307 |
+
"decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00004-of-00006.safetensors",
|
| 308 |
+
"decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00004-of-00006.safetensors",
|
| 309 |
+
"decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00004-of-00006.safetensors",
|
| 310 |
+
"decoder.block.7.layer.1.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 311 |
+
"decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00006.safetensors",
|
| 312 |
+
"decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00006.safetensors",
|
| 313 |
+
"decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00004-of-00006.safetensors",
|
| 314 |
+
"decoder.block.7.layer.2.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 315 |
+
"decoder.block.8.layer.0.SelfAttention.k.weight": "model-00004-of-00006.safetensors",
|
| 316 |
+
"decoder.block.8.layer.0.SelfAttention.o.weight": "model-00004-of-00006.safetensors",
|
| 317 |
+
"decoder.block.8.layer.0.SelfAttention.q.weight": "model-00004-of-00006.safetensors",
|
| 318 |
+
"decoder.block.8.layer.0.SelfAttention.v.weight": "model-00004-of-00006.safetensors",
|
| 319 |
+
"decoder.block.8.layer.0.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 320 |
+
"decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00004-of-00006.safetensors",
|
| 321 |
+
"decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00004-of-00006.safetensors",
|
| 322 |
+
"decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00004-of-00006.safetensors",
|
| 323 |
+
"decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00004-of-00006.safetensors",
|
| 324 |
+
"decoder.block.8.layer.1.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 325 |
+
"decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00006.safetensors",
|
| 326 |
+
"decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00006.safetensors",
|
| 327 |
+
"decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00004-of-00006.safetensors",
|
| 328 |
+
"decoder.block.8.layer.2.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 329 |
+
"decoder.block.9.layer.0.SelfAttention.k.weight": "model-00004-of-00006.safetensors",
|
| 330 |
+
"decoder.block.9.layer.0.SelfAttention.o.weight": "model-00004-of-00006.safetensors",
|
| 331 |
+
"decoder.block.9.layer.0.SelfAttention.q.weight": "model-00004-of-00006.safetensors",
|
| 332 |
+
"decoder.block.9.layer.0.SelfAttention.v.weight": "model-00004-of-00006.safetensors",
|
| 333 |
+
"decoder.block.9.layer.0.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 334 |
+
"decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00004-of-00006.safetensors",
|
| 335 |
+
"decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00004-of-00006.safetensors",
|
| 336 |
+
"decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00004-of-00006.safetensors",
|
| 337 |
+
"decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00004-of-00006.safetensors",
|
| 338 |
+
"decoder.block.9.layer.1.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 339 |
+
"decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00006.safetensors",
|
| 340 |
+
"decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00006.safetensors",
|
| 341 |
+
"decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00004-of-00006.safetensors",
|
| 342 |
+
"decoder.block.9.layer.2.layer_norm.weight": "model-00004-of-00006.safetensors",
|
| 343 |
+
"decoder.embed_tokens.weight": "model-00003-of-00006.safetensors",
|
| 344 |
+
"decoder.final_layer_norm.weight": "model-00006-of-00006.safetensors",
|
| 345 |
+
"encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00006.safetensors",
|
| 346 |
+
"encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00006.safetensors",
|
| 347 |
+
"encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00006.safetensors",
|
| 348 |
+
"encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00006.safetensors",
|
| 349 |
+
"encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00006.safetensors",
|
| 350 |
+
"encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00006.safetensors",
|
| 351 |
+
"encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00006.safetensors",
|
| 352 |
+
"encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00006.safetensors",
|
| 353 |
+
"encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00006.safetensors",
|
| 354 |
+
"encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00006.safetensors",
|
| 355 |
+
"encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00006.safetensors",
|
| 356 |
+
"encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00006.safetensors",
|
| 357 |
+
"encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00006.safetensors",
|
| 358 |
+
"encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00006.safetensors",
|
| 359 |
+
"encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00006.safetensors",
|
| 360 |
+
"encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00006.safetensors",
|
| 361 |
+
"encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00006.safetensors",
|
| 362 |
+
"encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00006.safetensors",
|
| 363 |
+
"encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00006.safetensors",
|
| 364 |
+
"encoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors",
|
| 365 |
+
"encoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors",
|
| 366 |
+
"encoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors",
|
| 367 |
+
"encoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors",
|
| 368 |
+
"encoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 369 |
+
"encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00006.safetensors",
|
| 370 |
+
"encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00006.safetensors",
|
| 371 |
+
"encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00002-of-00006.safetensors",
|
| 372 |
+
"encoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 373 |
+
"encoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors",
|
| 374 |
+
"encoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors",
|
| 375 |
+
"encoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors",
|
| 376 |
+
"encoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors",
|
| 377 |
+
"encoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 378 |
+
"encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00006.safetensors",
|
| 379 |
+
"encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00006.safetensors",
|
| 380 |
+
"encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00002-of-00006.safetensors",
|
| 381 |
+
"encoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 382 |
+
"encoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors",
|
| 383 |
+
"encoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors",
|
| 384 |
+
"encoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors",
|
| 385 |
+
"encoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors",
|
| 386 |
+
"encoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 387 |
+
"encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00006.safetensors",
|
| 388 |
+
"encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00006.safetensors",
|
| 389 |
+
"encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00002-of-00006.safetensors",
|
| 390 |
+
"encoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 391 |
+
"encoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors",
|
| 392 |
+
"encoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors",
|
| 393 |
+
"encoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors",
|
| 394 |
+
"encoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors",
|
| 395 |
+
"encoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 396 |
+
"encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00006.safetensors",
|
| 397 |
+
"encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00006.safetensors",
|
| 398 |
+
"encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00002-of-00006.safetensors",
|
| 399 |
+
"encoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 400 |
+
"encoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors",
|
| 401 |
+
"encoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors",
|
| 402 |
+
"encoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors",
|
| 403 |
+
"encoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors",
|
| 404 |
+
"encoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 405 |
+
"encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00006.safetensors",
|
| 406 |
+
"encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00006.safetensors",
|
| 407 |
+
"encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00002-of-00006.safetensors",
|
| 408 |
+
"encoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 409 |
+
"encoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors",
|
| 410 |
+
"encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors",
|
| 411 |
+
"encoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors",
|
| 412 |
+
"encoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors",
|
| 413 |
+
"encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 414 |
+
"encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00006.safetensors",
|
| 415 |
+
"encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00006.safetensors",
|
| 416 |
+
"encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00006.safetensors",
|
| 417 |
+
"encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 418 |
+
"encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors",
|
| 419 |
+
"encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors",
|
| 420 |
+
"encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors",
|
| 421 |
+
"encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors",
|
| 422 |
+
"encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 423 |
+
"encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00006.safetensors",
|
| 424 |
+
"encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00006.safetensors",
|
| 425 |
+
"encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00006.safetensors",
|
| 426 |
+
"encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 427 |
+
"encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors",
|
| 428 |
+
"encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors",
|
| 429 |
+
"encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors",
|
| 430 |
+
"encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors",
|
| 431 |
+
"encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 432 |
+
"encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00006.safetensors",
|
| 433 |
+
"encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00006.safetensors",
|
| 434 |
+
"encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00006.safetensors",
|
| 435 |
+
"encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 436 |
+
"encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors",
|
| 437 |
+
"encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors",
|
| 438 |
+
"encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors",
|
| 439 |
+
"encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors",
|
| 440 |
+
"encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 441 |
+
"encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00006.safetensors",
|
| 442 |
+
"encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00006.safetensors",
|
| 443 |
+
"encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00006.safetensors",
|
| 444 |
+
"encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 445 |
+
"encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors",
|
| 446 |
+
"encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors",
|
| 447 |
+
"encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors",
|
| 448 |
+
"encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors",
|
| 449 |
+
"encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 450 |
+
"encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00006.safetensors",
|
| 451 |
+
"encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00006.safetensors",
|
| 452 |
+
"encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00006.safetensors",
|
| 453 |
+
"encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 454 |
+
"encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00006.safetensors",
|
| 455 |
+
"encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00006.safetensors",
|
| 456 |
+
"encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00006.safetensors",
|
| 457 |
+
"encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00006.safetensors",
|
| 458 |
+
"encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00006.safetensors",
|
| 459 |
+
"encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00006.safetensors",
|
| 460 |
+
"encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00006.safetensors",
|
| 461 |
+
"encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00006.safetensors",
|
| 462 |
+
"encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00006.safetensors",
|
| 463 |
+
"encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors",
|
| 464 |
+
"encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors",
|
| 465 |
+
"encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors",
|
| 466 |
+
"encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors",
|
| 467 |
+
"encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 468 |
+
"encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00006.safetensors",
|
| 469 |
+
"encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00006.safetensors",
|
| 470 |
+
"encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00003-of-00006.safetensors",
|
| 471 |
+
"encoder.block.20.layer.1.layer_norm.weight": "model-00003-of-00006.safetensors",
|
| 472 |
+
"encoder.block.21.layer.0.SelfAttention.k.weight": "model-00003-of-00006.safetensors",
|
| 473 |
+
"encoder.block.21.layer.0.SelfAttention.o.weight": "model-00003-of-00006.safetensors",
|
| 474 |
+
"encoder.block.21.layer.0.SelfAttention.q.weight": "model-00003-of-00006.safetensors",
|
| 475 |
+
"encoder.block.21.layer.0.SelfAttention.v.weight": "model-00003-of-00006.safetensors",
|
| 476 |
+
"encoder.block.21.layer.0.layer_norm.weight": "model-00003-of-00006.safetensors",
|
| 477 |
+
"encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00006.safetensors",
|
| 478 |
+
"encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00006.safetensors",
|
| 479 |
+
"encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00003-of-00006.safetensors",
|
| 480 |
+
"encoder.block.21.layer.1.layer_norm.weight": "model-00003-of-00006.safetensors",
|
| 481 |
+
"encoder.block.22.layer.0.SelfAttention.k.weight": "model-00003-of-00006.safetensors",
|
| 482 |
+
"encoder.block.22.layer.0.SelfAttention.o.weight": "model-00003-of-00006.safetensors",
|
| 483 |
+
"encoder.block.22.layer.0.SelfAttention.q.weight": "model-00003-of-00006.safetensors",
|
| 484 |
+
"encoder.block.22.layer.0.SelfAttention.v.weight": "model-00003-of-00006.safetensors",
|
| 485 |
+
"encoder.block.22.layer.0.layer_norm.weight": "model-00003-of-00006.safetensors",
|
| 486 |
+
"encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00006.safetensors",
|
| 487 |
+
"encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00006.safetensors",
|
| 488 |
+
"encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00003-of-00006.safetensors",
|
| 489 |
+
"encoder.block.22.layer.1.layer_norm.weight": "model-00003-of-00006.safetensors",
|
| 490 |
+
"encoder.block.23.layer.0.SelfAttention.k.weight": "model-00003-of-00006.safetensors",
|
| 491 |
+
"encoder.block.23.layer.0.SelfAttention.o.weight": "model-00003-of-00006.safetensors",
|
| 492 |
+
"encoder.block.23.layer.0.SelfAttention.q.weight": "model-00003-of-00006.safetensors",
|
| 493 |
+
"encoder.block.23.layer.0.SelfAttention.v.weight": "model-00003-of-00006.safetensors",
|
| 494 |
+
"encoder.block.23.layer.0.layer_norm.weight": "model-00003-of-00006.safetensors",
|
| 495 |
+
"encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00006.safetensors",
|
| 496 |
+
"encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00006.safetensors",
|
| 497 |
+
"encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00003-of-00006.safetensors",
|
| 498 |
+
"encoder.block.23.layer.1.layer_norm.weight": "model-00003-of-00006.safetensors",
|
| 499 |
+
"encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00006.safetensors",
|
| 500 |
+
"encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00006.safetensors",
|
| 501 |
+
"encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00006.safetensors",
|
| 502 |
+
"encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00006.safetensors",
|
| 503 |
+
"encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00006.safetensors",
|
| 504 |
+
"encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00006.safetensors",
|
| 505 |
+
"encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00006.safetensors",
|
| 506 |
+
"encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00006.safetensors",
|
| 507 |
+
"encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00006.safetensors",
|
| 508 |
+
"encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00006.safetensors",
|
| 509 |
+
"encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00006.safetensors",
|
| 510 |
+
"encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00006.safetensors",
|
| 511 |
+
"encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00006.safetensors",
|
| 512 |
+
"encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00006.safetensors",
|
| 513 |
+
"encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00006.safetensors",
|
| 514 |
+
"encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00006.safetensors",
|
| 515 |
+
"encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00006.safetensors",
|
| 516 |
+
"encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00006.safetensors",
|
| 517 |
+
"encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00006.safetensors",
|
| 518 |
+
"encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00006.safetensors",
|
| 519 |
+
"encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00006.safetensors",
|
| 520 |
+
"encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00006.safetensors",
|
| 521 |
+
"encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00006.safetensors",
|
| 522 |
+
"encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00006.safetensors",
|
| 523 |
+
"encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00006.safetensors",
|
| 524 |
+
"encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00006.safetensors",
|
| 525 |
+
"encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00006.safetensors",
|
| 526 |
+
"encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00006.safetensors",
|
| 527 |
+
"encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00006.safetensors",
|
| 528 |
+
"encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00006.safetensors",
|
| 529 |
+
"encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00006.safetensors",
|
| 530 |
+
"encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00006.safetensors",
|
| 531 |
+
"encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00006.safetensors",
|
| 532 |
+
"encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00006.safetensors",
|
| 533 |
+
"encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00006.safetensors",
|
| 534 |
+
"encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00006.safetensors",
|
| 535 |
+
"encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00006.safetensors",
|
| 536 |
+
"encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00006.safetensors",
|
| 537 |
+
"encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00006.safetensors",
|
| 538 |
+
"encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00006.safetensors",
|
| 539 |
+
"encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00006.safetensors",
|
| 540 |
+
"encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00006.safetensors",
|
| 541 |
+
"encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00006.safetensors",
|
| 542 |
+
"encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00002-of-00006.safetensors",
|
| 543 |
+
"encoder.block.7.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 544 |
+
"encoder.block.8.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors",
|
| 545 |
+
"encoder.block.8.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors",
|
| 546 |
+
"encoder.block.8.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors",
|
| 547 |
+
"encoder.block.8.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors",
|
| 548 |
+
"encoder.block.8.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 549 |
+
"encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00006.safetensors",
|
| 550 |
+
"encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00006.safetensors",
|
| 551 |
+
"encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00002-of-00006.safetensors",
|
| 552 |
+
"encoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 553 |
+
"encoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00006.safetensors",
|
| 554 |
+
"encoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00006.safetensors",
|
| 555 |
+
"encoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00006.safetensors",
|
| 556 |
+
"encoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00006.safetensors",
|
| 557 |
+
"encoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 558 |
+
"encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00006.safetensors",
|
| 559 |
+
"encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00006.safetensors",
|
| 560 |
+
"encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00002-of-00006.safetensors",
|
| 561 |
+
"encoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00006.safetensors",
|
| 562 |
+
"encoder.final_layer_norm.weight": "model-00003-of-00006.safetensors",
|
| 563 |
+
"lm_head.weight": "model-00006-of-00006.safetensors",
|
| 564 |
+
"shared.weight": "model-00001-of-00006.safetensors"
|
| 565 |
+
}
|
| 566 |
+
}
|
pytorch_model-00001-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:295a276775d79359cfd243bd93c9e2c408a8e33718e5bee1d05625f026af6175
|
| 3 |
+
size 9936583612
|
pytorch_model-00002-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c21533a6182886bec48cd0190952b3c5e71224873234135c2754f7c81d02ac82
|
| 3 |
+
size 9865466989
|
pytorch_model-00003-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62cc874eb7f5cfa6fcbde4a19bab7de1f7bf8b47f0f01c45713927115c85a153
|
| 3 |
+
size 9869491791
|
pytorch_model-00004-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36b2a5945f7c037b99eaf5ed891fc158b23a791b92042861a5298b0c8ec224be
|
| 3 |
+
size 9999740653
|
pytorch_model-00005-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f769732a1c4ba3a9cbd9ea1c2701ade3cdf2a35f73e75ac77d0c26788a5d88f
|
| 3 |
+
size 9999739675
|
pytorch_model-00006-of-00006.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92679f99746d0e1082d7407091cb7f2a588d49b9bf13724f706e8912f86c5786
|
| 3 |
+
size 6111224758
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,566 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 55782064128
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00006.bin",
|
| 7 |
+
"decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00006.bin",
|
| 8 |
+
"decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00006.bin",
|
| 9 |
+
"decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00003-of-00006.bin",
|
| 10 |
+
"decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00006.bin",
|
| 11 |
+
"decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 12 |
+
"decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00006.bin",
|
| 13 |
+
"decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00006.bin",
|
| 14 |
+
"decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00006.bin",
|
| 15 |
+
"decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00006.bin",
|
| 16 |
+
"decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 17 |
+
"decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00006.bin",
|
| 18 |
+
"decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00006.bin",
|
| 19 |
+
"decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00006.bin",
|
| 20 |
+
"decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 21 |
+
"decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00006.bin",
|
| 22 |
+
"decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00006.bin",
|
| 23 |
+
"decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00006.bin",
|
| 24 |
+
"decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00006.bin",
|
| 25 |
+
"decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 26 |
+
"decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00006.bin",
|
| 27 |
+
"decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00006.bin",
|
| 28 |
+
"decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00006.bin",
|
| 29 |
+
"decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00006.bin",
|
| 30 |
+
"decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 31 |
+
"decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00006.bin",
|
| 32 |
+
"decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00006.bin",
|
| 33 |
+
"decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00006.bin",
|
| 34 |
+
"decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 35 |
+
"decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 36 |
+
"decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 37 |
+
"decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 38 |
+
"decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 39 |
+
"decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 40 |
+
"decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 41 |
+
"decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 42 |
+
"decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 43 |
+
"decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 44 |
+
"decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 45 |
+
"decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00006.bin",
|
| 46 |
+
"decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00006.bin",
|
| 47 |
+
"decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
|
| 48 |
+
"decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 49 |
+
"decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 50 |
+
"decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 51 |
+
"decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 52 |
+
"decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 53 |
+
"decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 54 |
+
"decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 55 |
+
"decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 56 |
+
"decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 57 |
+
"decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 58 |
+
"decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 59 |
+
"decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00006.bin",
|
| 60 |
+
"decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00006.bin",
|
| 61 |
+
"decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
|
| 62 |
+
"decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 63 |
+
"decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 64 |
+
"decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 65 |
+
"decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 66 |
+
"decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 67 |
+
"decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 68 |
+
"decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 69 |
+
"decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 70 |
+
"decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 71 |
+
"decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 72 |
+
"decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 73 |
+
"decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00006.bin",
|
| 74 |
+
"decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00006.bin",
|
| 75 |
+
"decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
|
| 76 |
+
"decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 77 |
+
"decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 78 |
+
"decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 79 |
+
"decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 80 |
+
"decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 81 |
+
"decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 82 |
+
"decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 83 |
+
"decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 84 |
+
"decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 85 |
+
"decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 86 |
+
"decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 87 |
+
"decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00006.bin",
|
| 88 |
+
"decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00006.bin",
|
| 89 |
+
"decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
|
| 90 |
+
"decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 91 |
+
"decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 92 |
+
"decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 93 |
+
"decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 94 |
+
"decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 95 |
+
"decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 96 |
+
"decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 97 |
+
"decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 98 |
+
"decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 99 |
+
"decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 100 |
+
"decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 101 |
+
"decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00006.bin",
|
| 102 |
+
"decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00006.bin",
|
| 103 |
+
"decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
|
| 104 |
+
"decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 105 |
+
"decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 106 |
+
"decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 107 |
+
"decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 108 |
+
"decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 109 |
+
"decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 110 |
+
"decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 111 |
+
"decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 112 |
+
"decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 113 |
+
"decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 114 |
+
"decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 115 |
+
"decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00006.bin",
|
| 116 |
+
"decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00006.bin",
|
| 117 |
+
"decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
|
| 118 |
+
"decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 119 |
+
"decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 120 |
+
"decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 121 |
+
"decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 122 |
+
"decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 123 |
+
"decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 124 |
+
"decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 125 |
+
"decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 126 |
+
"decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 127 |
+
"decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 128 |
+
"decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 129 |
+
"decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00006.bin",
|
| 130 |
+
"decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00006.bin",
|
| 131 |
+
"decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
|
| 132 |
+
"decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 133 |
+
"decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 134 |
+
"decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 135 |
+
"decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 136 |
+
"decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 137 |
+
"decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 138 |
+
"decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 139 |
+
"decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 140 |
+
"decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 141 |
+
"decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 142 |
+
"decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 143 |
+
"decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00006.bin",
|
| 144 |
+
"decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00006.bin",
|
| 145 |
+
"decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
|
| 146 |
+
"decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 147 |
+
"decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 148 |
+
"decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 149 |
+
"decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 150 |
+
"decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 151 |
+
"decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 152 |
+
"decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 153 |
+
"decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 154 |
+
"decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 155 |
+
"decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 156 |
+
"decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 157 |
+
"decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00006.bin",
|
| 158 |
+
"decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00006.bin",
|
| 159 |
+
"decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
|
| 160 |
+
"decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 161 |
+
"decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 162 |
+
"decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 163 |
+
"decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 164 |
+
"decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 165 |
+
"decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 166 |
+
"decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 167 |
+
"decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 168 |
+
"decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 169 |
+
"decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 170 |
+
"decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 171 |
+
"decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00006.bin",
|
| 172 |
+
"decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00006.bin",
|
| 173 |
+
"decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
|
| 174 |
+
"decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 175 |
+
"decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00006.bin",
|
| 176 |
+
"decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00006.bin",
|
| 177 |
+
"decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00006.bin",
|
| 178 |
+
"decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00006.bin",
|
| 179 |
+
"decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 180 |
+
"decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00006.bin",
|
| 181 |
+
"decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00006.bin",
|
| 182 |
+
"decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00006.bin",
|
| 183 |
+
"decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00006.bin",
|
| 184 |
+
"decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 185 |
+
"decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00006.bin",
|
| 186 |
+
"decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00006.bin",
|
| 187 |
+
"decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
|
| 188 |
+
"decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 189 |
+
"decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 190 |
+
"decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 191 |
+
"decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 192 |
+
"decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 193 |
+
"decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 194 |
+
"decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 195 |
+
"decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 196 |
+
"decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 197 |
+
"decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 198 |
+
"decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 199 |
+
"decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00006.bin",
|
| 200 |
+
"decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00006.bin",
|
| 201 |
+
"decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
|
| 202 |
+
"decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 203 |
+
"decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 204 |
+
"decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 205 |
+
"decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 206 |
+
"decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 207 |
+
"decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 208 |
+
"decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
|
| 209 |
+
"decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
|
| 210 |
+
"decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 211 |
+
"decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
|
| 212 |
+
"decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 213 |
+
"decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00006.bin",
|
| 214 |
+
"decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00006.bin",
|
| 215 |
+
"decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
|
| 216 |
+
"decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
|
| 217 |
+
"decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00006.bin",
|
| 218 |
+
"decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00006.bin",
|
| 219 |
+
"decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
|
| 220 |
+
"decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00006.bin",
|
| 221 |
+
"decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00006-of-00006.bin",
|
| 222 |
+
"decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00006.bin",
|
| 223 |
+
"decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00006.bin",
|
| 224 |
+
"decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00006.bin",
|
| 225 |
+
"decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00006.bin",
|
| 226 |
+
"decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00006-of-00006.bin",
|
| 227 |
+
"decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00006.bin",
|
| 228 |
+
"decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00006.bin",
|
| 229 |
+
"decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00006.bin",
|
| 230 |
+
"decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00006-of-00006.bin",
|
| 231 |
+
"decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00006.bin",
|
| 232 |
+
"decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00006.bin",
|
| 233 |
+
"decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00006.bin",
|
| 234 |
+
"decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00006.bin",
|
| 235 |
+
"decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00006-of-00006.bin",
|
| 236 |
+
"decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00006.bin",
|
| 237 |
+
"decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00006.bin",
|
| 238 |
+
"decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00006.bin",
|
| 239 |
+
"decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00006.bin",
|
| 240 |
+
"decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00006-of-00006.bin",
|
| 241 |
+
"decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00006.bin",
|
| 242 |
+
"decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00006.bin",
|
| 243 |
+
"decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00006.bin",
|
| 244 |
+
"decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00006-of-00006.bin",
|
| 245 |
+
"decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 246 |
+
"decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 247 |
+
"decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 248 |
+
"decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 249 |
+
"decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 250 |
+
"decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 251 |
+
"decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 252 |
+
"decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 253 |
+
"decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 254 |
+
"decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 255 |
+
"decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00006.bin",
|
| 256 |
+
"decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00006.bin",
|
| 257 |
+
"decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
|
| 258 |
+
"decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 259 |
+
"decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 260 |
+
"decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 261 |
+
"decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 262 |
+
"decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 263 |
+
"decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 264 |
+
"decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 265 |
+
"decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 266 |
+
"decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 267 |
+
"decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 268 |
+
"decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 269 |
+
"decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00006.bin",
|
| 270 |
+
"decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00006.bin",
|
| 271 |
+
"decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
|
| 272 |
+
"decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 273 |
+
"decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 274 |
+
"decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 275 |
+
"decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 276 |
+
"decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 277 |
+
"decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 278 |
+
"decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 279 |
+
"decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 280 |
+
"decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 281 |
+
"decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 282 |
+
"decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 283 |
+
"decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00006.bin",
|
| 284 |
+
"decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00006.bin",
|
| 285 |
+
"decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
|
| 286 |
+
"decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 287 |
+
"decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 288 |
+
"decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 289 |
+
"decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 290 |
+
"decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 291 |
+
"decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 292 |
+
"decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 293 |
+
"decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 294 |
+
"decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 295 |
+
"decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 296 |
+
"decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 297 |
+
"decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00006.bin",
|
| 298 |
+
"decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00006.bin",
|
| 299 |
+
"decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
|
| 300 |
+
"decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 301 |
+
"decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 302 |
+
"decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 303 |
+
"decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 304 |
+
"decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 305 |
+
"decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 306 |
+
"decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 307 |
+
"decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 308 |
+
"decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 309 |
+
"decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 310 |
+
"decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 311 |
+
"decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00006.bin",
|
| 312 |
+
"decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00006.bin",
|
| 313 |
+
"decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
|
| 314 |
+
"decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 315 |
+
"decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 316 |
+
"decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 317 |
+
"decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 318 |
+
"decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 319 |
+
"decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 320 |
+
"decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 321 |
+
"decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 322 |
+
"decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 323 |
+
"decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 324 |
+
"decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 325 |
+
"decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00006.bin",
|
| 326 |
+
"decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00006.bin",
|
| 327 |
+
"decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
|
| 328 |
+
"decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 329 |
+
"decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 330 |
+
"decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 331 |
+
"decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 332 |
+
"decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 333 |
+
"decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 334 |
+
"decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
|
| 335 |
+
"decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
|
| 336 |
+
"decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
|
| 337 |
+
"decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
|
| 338 |
+
"decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 339 |
+
"decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00006.bin",
|
| 340 |
+
"decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00006.bin",
|
| 341 |
+
"decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
|
| 342 |
+
"decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
|
| 343 |
+
"decoder.embed_tokens.weight": "pytorch_model-00003-of-00006.bin",
|
| 344 |
+
"decoder.final_layer_norm.weight": "pytorch_model-00006-of-00006.bin",
|
| 345 |
+
"encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00006.bin",
|
| 346 |
+
"encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00006.bin",
|
| 347 |
+
"encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00006.bin",
|
| 348 |
+
"encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00006.bin",
|
| 349 |
+
"encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00006.bin",
|
| 350 |
+
"encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 351 |
+
"encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00006.bin",
|
| 352 |
+
"encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00006.bin",
|
| 353 |
+
"encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00006.bin",
|
| 354 |
+
"encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 355 |
+
"encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00006.bin",
|
| 356 |
+
"encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00006.bin",
|
| 357 |
+
"encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00006.bin",
|
| 358 |
+
"encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00006.bin",
|
| 359 |
+
"encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 360 |
+
"encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00006.bin",
|
| 361 |
+
"encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00006.bin",
|
| 362 |
+
"encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00006.bin",
|
| 363 |
+
"encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 364 |
+
"encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
|
| 365 |
+
"encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
|
| 366 |
+
"encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
|
| 367 |
+
"encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
|
| 368 |
+
"encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 369 |
+
"encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
|
| 370 |
+
"encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
|
| 371 |
+
"encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
|
| 372 |
+
"encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 373 |
+
"encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
|
| 374 |
+
"encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
|
| 375 |
+
"encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
|
| 376 |
+
"encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
|
| 377 |
+
"encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 378 |
+
"encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
|
| 379 |
+
"encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
|
| 380 |
+
"encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
|
| 381 |
+
"encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 382 |
+
"encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
|
| 383 |
+
"encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
|
| 384 |
+
"encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
|
| 385 |
+
"encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
|
| 386 |
+
"encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 387 |
+
"encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
|
| 388 |
+
"encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
|
| 389 |
+
"encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
|
| 390 |
+
"encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 391 |
+
"encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
|
| 392 |
+
"encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
|
| 393 |
+
"encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
|
| 394 |
+
"encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
|
| 395 |
+
"encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 396 |
+
"encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
|
| 397 |
+
"encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
|
| 398 |
+
"encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
|
| 399 |
+
"encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 400 |
+
"encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
|
| 401 |
+
"encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
|
| 402 |
+
"encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
|
| 403 |
+
"encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
|
| 404 |
+
"encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 405 |
+
"encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
|
| 406 |
+
"encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
|
| 407 |
+
"encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
|
| 408 |
+
"encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 409 |
+
"encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
|
| 410 |
+
"encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
|
| 411 |
+
"encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
|
| 412 |
+
"encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
|
| 413 |
+
"encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 414 |
+
"encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
|
| 415 |
+
"encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
|
| 416 |
+
"encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
|
| 417 |
+
"encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 418 |
+
"encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
|
| 419 |
+
"encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
|
| 420 |
+
"encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
|
| 421 |
+
"encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
|
| 422 |
+
"encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 423 |
+
"encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
|
| 424 |
+
"encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
|
| 425 |
+
"encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
|
| 426 |
+
"encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 427 |
+
"encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
|
| 428 |
+
"encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
|
| 429 |
+
"encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
|
| 430 |
+
"encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
|
| 431 |
+
"encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 432 |
+
"encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
|
| 433 |
+
"encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
|
| 434 |
+
"encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
|
| 435 |
+
"encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 436 |
+
"encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
|
| 437 |
+
"encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
|
| 438 |
+
"encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
|
| 439 |
+
"encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
|
| 440 |
+
"encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 441 |
+
"encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
|
| 442 |
+
"encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
|
| 443 |
+
"encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
|
| 444 |
+
"encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 445 |
+
"encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
|
| 446 |
+
"encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
|
| 447 |
+
"encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
|
| 448 |
+
"encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
|
| 449 |
+
"encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 450 |
+
"encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
|
| 451 |
+
"encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
|
| 452 |
+
"encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
|
| 453 |
+
"encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 454 |
+
"encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00006.bin",
|
| 455 |
+
"encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00006.bin",
|
| 456 |
+
"encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00006.bin",
|
| 457 |
+
"encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00006.bin",
|
| 458 |
+
"encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 459 |
+
"encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00006.bin",
|
| 460 |
+
"encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00006.bin",
|
| 461 |
+
"encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00006.bin",
|
| 462 |
+
"encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 463 |
+
"encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
|
| 464 |
+
"encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
|
| 465 |
+
"encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
|
| 466 |
+
"encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
|
| 467 |
+
"encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 468 |
+
"encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00006.bin",
|
| 469 |
+
"encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00006.bin",
|
| 470 |
+
"encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00006.bin",
|
| 471 |
+
"encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 472 |
+
"encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00006.bin",
|
| 473 |
+
"encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00006.bin",
|
| 474 |
+
"encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00006.bin",
|
| 475 |
+
"encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00006.bin",
|
| 476 |
+
"encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 477 |
+
"encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00006.bin",
|
| 478 |
+
"encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00006.bin",
|
| 479 |
+
"encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00006.bin",
|
| 480 |
+
"encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 481 |
+
"encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00006.bin",
|
| 482 |
+
"encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00006.bin",
|
| 483 |
+
"encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00006.bin",
|
| 484 |
+
"encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00006.bin",
|
| 485 |
+
"encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 486 |
+
"encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00006.bin",
|
| 487 |
+
"encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00006.bin",
|
| 488 |
+
"encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00006.bin",
|
| 489 |
+
"encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 490 |
+
"encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00006.bin",
|
| 491 |
+
"encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00006.bin",
|
| 492 |
+
"encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00006.bin",
|
| 493 |
+
"encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00006.bin",
|
| 494 |
+
"encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 495 |
+
"encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00006.bin",
|
| 496 |
+
"encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00006.bin",
|
| 497 |
+
"encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00006.bin",
|
| 498 |
+
"encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 499 |
+
"encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00006.bin",
|
| 500 |
+
"encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00006.bin",
|
| 501 |
+
"encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00006.bin",
|
| 502 |
+
"encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00006.bin",
|
| 503 |
+
"encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 504 |
+
"encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00006.bin",
|
| 505 |
+
"encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00006.bin",
|
| 506 |
+
"encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00006.bin",
|
| 507 |
+
"encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 508 |
+
"encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00006.bin",
|
| 509 |
+
"encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00006.bin",
|
| 510 |
+
"encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00006.bin",
|
| 511 |
+
"encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00006.bin",
|
| 512 |
+
"encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 513 |
+
"encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00006.bin",
|
| 514 |
+
"encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00006.bin",
|
| 515 |
+
"encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00006.bin",
|
| 516 |
+
"encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 517 |
+
"encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00006.bin",
|
| 518 |
+
"encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00006.bin",
|
| 519 |
+
"encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00006.bin",
|
| 520 |
+
"encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00006.bin",
|
| 521 |
+
"encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 522 |
+
"encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00006.bin",
|
| 523 |
+
"encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00006.bin",
|
| 524 |
+
"encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00006.bin",
|
| 525 |
+
"encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 526 |
+
"encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00006.bin",
|
| 527 |
+
"encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00006.bin",
|
| 528 |
+
"encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00006.bin",
|
| 529 |
+
"encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00006.bin",
|
| 530 |
+
"encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 531 |
+
"encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00006.bin",
|
| 532 |
+
"encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00006.bin",
|
| 533 |
+
"encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00006.bin",
|
| 534 |
+
"encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 535 |
+
"encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00006.bin",
|
| 536 |
+
"encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00006.bin",
|
| 537 |
+
"encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00006.bin",
|
| 538 |
+
"encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00006.bin",
|
| 539 |
+
"encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
|
| 540 |
+
"encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00006.bin",
|
| 541 |
+
"encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
|
| 542 |
+
"encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
|
| 543 |
+
"encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 544 |
+
"encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
|
| 545 |
+
"encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
|
| 546 |
+
"encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
|
| 547 |
+
"encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
|
| 548 |
+
"encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 549 |
+
"encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
|
| 550 |
+
"encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
|
| 551 |
+
"encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
|
| 552 |
+
"encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 553 |
+
"encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
|
| 554 |
+
"encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
|
| 555 |
+
"encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
|
| 556 |
+
"encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
|
| 557 |
+
"encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 558 |
+
"encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
|
| 559 |
+
"encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
|
| 560 |
+
"encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
|
| 561 |
+
"encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
|
| 562 |
+
"encoder.final_layer_norm.weight": "pytorch_model-00003-of-00006.bin",
|
| 563 |
+
"lm_head.weight": "pytorch_model-00006-of-00006.bin",
|
| 564 |
+
"shared.weight": "pytorch_model-00001-of-00006.bin"
|
| 565 |
+
}
|
| 566 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "</s>",
|
| 3 |
+
"pad_token": "<pad>",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
| 3 |
+
size 4309802
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93c3578052e1605d8332eb961bc08d72e246071974e4cc54aa6991826b802aa5
|
| 3 |
+
size 16330369
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": null,
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"extra_ids": 0,
|
| 5 |
+
"name_or_path": "google/mt5-xxl",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"sp_model_kwargs": {},
|
| 8 |
+
"special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
|
| 9 |
+
"tokenizer_class": "T5Tokenizer",
|
| 10 |
+
"unk_token": "<unk>"
|
| 11 |
+
}
|