Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
6
jiaqiz commited on
Commit
2d4ac14
•
1 Parent(s): d9526ad

Add files using large-upload tool

Browse files
Files changed (26) hide show
  1. .gitattributes +25 -0
  2. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/10.1.0 +3 -0
  3. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/18.6.0 +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/2.7.0 +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/24.6.0 +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/30.4.0 +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/31.2.0 +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/33.3.0 +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/33.6.0 +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/39.3.0 +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/4.7.0 +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/52.7.0 +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/60.2.0 +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/62.5.0 +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/64.2.0 +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/64.4.0 +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.4.0 +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/68.2.0 +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/68.3.0 +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/74.2.0 +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/75.1.0 +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/78.5.0 +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.6.0 +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/80.6.0 +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/81.3.0 +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/91.5.0 +3 -0
.gitattributes CHANGED
@@ -1433,3 +1433,28 @@ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/53.3.0 filte
1433
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/92.2.0 filter=lfs diff=lfs merge=lfs -text
1434
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/88.6.0 filter=lfs diff=lfs merge=lfs -text
1435
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/56.7.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1433
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/92.2.0 filter=lfs diff=lfs merge=lfs -text
1434
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/88.6.0 filter=lfs diff=lfs merge=lfs -text
1435
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/56.7.0 filter=lfs diff=lfs merge=lfs -text
1436
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.4.0 filter=lfs diff=lfs merge=lfs -text
1437
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/64.4.0 filter=lfs diff=lfs merge=lfs -text
1438
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/60.2.0 filter=lfs diff=lfs merge=lfs -text
1439
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/91.5.0 filter=lfs diff=lfs merge=lfs -text
1440
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/64.2.0 filter=lfs diff=lfs merge=lfs -text
1441
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/74.2.0 filter=lfs diff=lfs merge=lfs -text
1442
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/81.3.0 filter=lfs diff=lfs merge=lfs -text
1443
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/39.3.0 filter=lfs diff=lfs merge=lfs -text
1444
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/62.5.0 filter=lfs diff=lfs merge=lfs -text
1445
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/33.3.0 filter=lfs diff=lfs merge=lfs -text
1446
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/75.1.0 filter=lfs diff=lfs merge=lfs -text
1447
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/52.7.0 filter=lfs diff=lfs merge=lfs -text
1448
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/68.3.0 filter=lfs diff=lfs merge=lfs -text
1449
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/4.7.0 filter=lfs diff=lfs merge=lfs -text
1450
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/33.6.0 filter=lfs diff=lfs merge=lfs -text
1451
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/78.5.0 filter=lfs diff=lfs merge=lfs -text
1452
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/68.2.0 filter=lfs diff=lfs merge=lfs -text
1453
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/18.6.0 filter=lfs diff=lfs merge=lfs -text
1454
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/10.1.0 filter=lfs diff=lfs merge=lfs -text
1455
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/30.4.0 filter=lfs diff=lfs merge=lfs -text
1456
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/31.2.0 filter=lfs diff=lfs merge=lfs -text
1457
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/80.6.0 filter=lfs diff=lfs merge=lfs -text
1458
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/2.7.0 filter=lfs diff=lfs merge=lfs -text
1459
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.6.0 filter=lfs diff=lfs merge=lfs -text
1460
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/24.6.0 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/10.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf121bf7a23d7786e602db4082e9e93564e41c7169eea3598fdb229bdd4a4d28
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/18.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4778276b07d74b053f3362959fb77bf1899931a426af6c5accdd05e27f7f3b35
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/2.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a9c62243bdbf8c48755362cb32d0357314433b39f55a67b462362b3a2c40766
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/24.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:911307bd95714d1c007874295b130c6afc3c621b2bdab0bb7f8a03afa8c7a491
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/30.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a624050dc0a8a7189e13f69d23a96dc7e1ede0a5e14461fbc0b63ea7fa4a3a0a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/31.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7117811a863b894a3d8fc2369a0b83838676a92c8774fedeb78d9b2d7ba594dd
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/33.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d328a38516e5f42678a55afcb5467f80a6d4b112c49de6c07b1dd239af1b9e3
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/33.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccdfebdd78d124f9ff5141e0ad04ba803100fa44a8fc47514506ea310312e29f
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/39.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a13260c225c9f3555cba8221888fc0da674d6044ea0348836e3c0ea247db077a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/4.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69604f74283a845d769b39030d1c63e535908a380c160f0d1d45b6d0da065c89
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/52.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e250aae076358a1d6231d0f6c04ad7371cc7f4fb56466ec12473f79d1095e20
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/60.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c323d60c6c7c4b1836cecfc78f097f47245560aacecf7075199d70ae9ca95f7
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/62.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff554008d66bad7170d93ff4abdf0eab724789a07d77f7a2ff17fcbfe0b432ff
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/64.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:139a87f5f4dfb6cfc1c10499b43ad1d388c740a154b462f24d5b46ddd15b0dee
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/64.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8794f05293f8952d37ea167a8974f9458d266c790fce5e6cd7d0591fb6f9325
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c84aea89b108d623fb867cc8e978d8445633f657d9f28c15b6f1b3580b93cb1
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/68.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f39caf7c67ae5cf72a4760bbb0a84417666cb3f959a11ea80e710c9a6271cbe
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/68.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c838632f2b367f9b9750a9145d1729e121115c608df31613a13d571acbbd34f
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/74.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4be7513e59d6b56cb6b9878ae9979652c6d11ebcbf9805c8a4374e3161118ef
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/75.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b094be1c1066213e3ce60bbc8e73db643ab23257f870bbb3497790c759bc35f4
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/78.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7582c8deaa94f9268467a80fb9a4a780caba39b0174f3d2df19c79e3c02da6ed
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:782a66acc79c691c7da74607b390b369721a9f6c70869b15e1b08ebb5c2e1c0b
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/80.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7edbb6c82fc586f35b37579bd84ce88e541a4034c3cd336e8f3b1cdfa9fc6c59
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/81.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b33d99d91933651efbd6d2f22ac303a19f2d4a4e2e48f69753c08accb5fe75be
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/91.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d768ef8b512e80f17315843fb23664f08a079f523bedbdb9ff8302171d92655e
3
+ size 99090432