Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
6
jiaqiz commited on
Commit
251c79e
•
1 Parent(s): b7442d1

Add files using large-upload tool

Browse files
Files changed (26) hide show
  1. .gitattributes +25 -0
  2. model_weights/model.decoder.layers.mlp.linear_fc2.weight/45.0.5 +3 -0
  3. model_weights/model.decoder.layers.mlp.linear_fc2.weight/62.0.7 +3 -0
  4. model_weights/model.decoder.layers.mlp.linear_fc2.weight/69.0.7 +3 -0
  5. model_weights/model.decoder.layers.mlp.linear_fc2.weight/87.0.7 +3 -0
  6. model_weights/model.decoder.layers.mlp.linear_fc2.weight/88.0.1 +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/11.3.0 +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/15.5.0 +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/19.5.0 +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/21.3.0 +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/21.6.0 +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/22.5.0 +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/28.1.0 +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/34.0.0 +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/37.5.0 +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/42.2.0 +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/46.3.0 +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.0.0 +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/53.1.0 +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.4.0 +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.7.0 +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/58.2.0 +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/67.3.0 +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/68.7.0 +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/75.0.0 +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/81.1.0 +3 -0
.gitattributes CHANGED
@@ -933,3 +933,28 @@ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/14.7.0 filte
933
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/49.0.0 filter=lfs diff=lfs merge=lfs -text
934
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/94.7.0 filter=lfs diff=lfs merge=lfs -text
935
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/63.5.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
933
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/49.0.0 filter=lfs diff=lfs merge=lfs -text
934
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/94.7.0 filter=lfs diff=lfs merge=lfs -text
935
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/63.5.0 filter=lfs diff=lfs merge=lfs -text
936
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/87.0.7 filter=lfs diff=lfs merge=lfs -text
937
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/15.5.0 filter=lfs diff=lfs merge=lfs -text
938
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/75.0.0 filter=lfs diff=lfs merge=lfs -text
939
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.7.0 filter=lfs diff=lfs merge=lfs -text
940
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/88.0.1 filter=lfs diff=lfs merge=lfs -text
941
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/37.5.0 filter=lfs diff=lfs merge=lfs -text
942
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/69.0.7 filter=lfs diff=lfs merge=lfs -text
943
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.0.0 filter=lfs diff=lfs merge=lfs -text
944
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/53.1.0 filter=lfs diff=lfs merge=lfs -text
945
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/11.3.0 filter=lfs diff=lfs merge=lfs -text
946
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/46.3.0 filter=lfs diff=lfs merge=lfs -text
947
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/19.5.0 filter=lfs diff=lfs merge=lfs -text
948
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/21.3.0 filter=lfs diff=lfs merge=lfs -text
949
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/68.7.0 filter=lfs diff=lfs merge=lfs -text
950
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/62.0.7 filter=lfs diff=lfs merge=lfs -text
951
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/58.2.0 filter=lfs diff=lfs merge=lfs -text
952
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/45.0.5 filter=lfs diff=lfs merge=lfs -text
953
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/34.0.0 filter=lfs diff=lfs merge=lfs -text
954
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/42.2.0 filter=lfs diff=lfs merge=lfs -text
955
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/67.3.0 filter=lfs diff=lfs merge=lfs -text
956
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/21.6.0 filter=lfs diff=lfs merge=lfs -text
957
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/22.5.0 filter=lfs diff=lfs merge=lfs -text
958
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/81.1.0 filter=lfs diff=lfs merge=lfs -text
959
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/28.1.0 filter=lfs diff=lfs merge=lfs -text
960
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.4.0 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.mlp.linear_fc2.weight/45.0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96a8b38c9fd090e94e01633582cd592ae510436d23c59ae3ddc8caf661e18abc
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/62.0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f7145fa5b091ed47445760772c1c14bd474a18f5753f87bf9e63a0c34432057
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/69.0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef36f2e637d63be3af8a130df08421bd31b6d9c163cdd09df7940643bcf843c5
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/87.0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c233d6c0f6015bb79926e3157bcb89a6d5a17ee484a71d2ca94f089a97d3581
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/88.0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fbd985aa8d52160ff5e048d415895fcc4ded3c652285b5a858a090574ec9250
3
+ size 339738624
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/11.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55944a9946fdb3ad5aa04b7ce11b2a2b2d97a63c6c9e189d847141970690ff4c
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/15.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cab33752a2684e22a461285caa48ac395dcc0b3e7a069161380790cd8aaba340
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/19.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6f1a059ce0440531e19f61ddfbae56a502e4c4af00e13e4b536b6f9e781dbff
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/21.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d431a9d3912036ad03ae7be9ba81a4a4eef5c3dc1de6b93ee7dc05741dd806a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/21.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:465bf12b6e0ca8c6996216d4f9e8aa41b6b3804ffc8fce7637cee67be72388ac
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/22.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:759f6fedc6ac32bca2cd3627efe6ab2b67d4715571d3816dee73ae22003491bd
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/28.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b15de28bf18e7134d3a89f70235280201972b20a29efc06ffa81ba35510ee0f
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/34.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc708552ffdf7e26246e0d55165f390b7b21b3285d9082f43002312090b4e7f7
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/37.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d098b62747a520af7b3e334a092774c7d3ec6bd90c641a24965f53d80c7d2a2
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/42.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:134bc94c61c674ded7cc45334f164b80c06ce449c80975eff95722cdff2d67f4
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/46.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3ab80a439f08f551c3e04344326c05cce8421fe336bf53f3aac84d8e6ad85d1
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16df05cf6def0612490b6270b87868af90adc25830340aeb63965866af1323c4
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/53.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8c6fba88b26c2bcb80bf24c65a0966118ec353a0bfa102574c86f69fae241e4
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:904058cd2d81a3b1aa232ddccd2d8b311c635aba93d25eccb1943ecdbd0acb70
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f77c839ad554b098fd8c59ee2d77197198e24de7f09b9e20f0ee23bc7616c9d
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/58.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30197238b1d19d4b53cbe213011b52aaf758c1c32e7e9c04a545418d18808964
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/67.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:887abbd28624063f91207eb9a99ddb8b24400534424870154cd24d8491f7ed5a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/68.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5338c60ae7c3eccd218548add7d45602389d71bd1c3ec515f52b46bc3ea69a56
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/75.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3b7a635cba2432b6d8b2a19b0a875ca6c7cee61870bf1cee4d8826244cbc32f
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/81.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9551c315a134a56b30f4caf744993737e8617a03a071dc72186b4a9c91ea3315
3
+ size 99090432