Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
7
jiaqiz commited on
Commit
c523f94
·
verified ·
1 Parent(s): 74c4776

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/11.4.0 +3 -0
  3. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/11.5.0 +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/15.4.0 +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/17.4.0 +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/20.2.0 +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/26.2.0 +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/3.5.0 +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/30.0.0 +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/35.3.0 +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/37.1.0 +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/44.1.0 +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/45.1.0 +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/45.3.0 +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/48.0.0 +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/59.0.0 +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/6.1.0 +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/67.7.0 +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/69.7.0 +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/70.3.0 +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/70.6.0 +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/71.6.0 +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/80.1.0 +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/82.6.0 +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/87.7.0 +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/94.4.0 +3 -0
.gitattributes CHANGED
@@ -1383,3 +1383,28 @@ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/48.7.0 filte
1383
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/54.7.0 filter=lfs diff=lfs merge=lfs -text
1384
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/92.1.0 filter=lfs diff=lfs merge=lfs -text
1385
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/7.2.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1383
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/54.7.0 filter=lfs diff=lfs merge=lfs -text
1384
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/92.1.0 filter=lfs diff=lfs merge=lfs -text
1385
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/7.2.0 filter=lfs diff=lfs merge=lfs -text
1386
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/20.2.0 filter=lfs diff=lfs merge=lfs -text
1387
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/45.1.0 filter=lfs diff=lfs merge=lfs -text
1388
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/59.0.0 filter=lfs diff=lfs merge=lfs -text
1389
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/87.7.0 filter=lfs diff=lfs merge=lfs -text
1390
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/26.2.0 filter=lfs diff=lfs merge=lfs -text
1391
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/11.5.0 filter=lfs diff=lfs merge=lfs -text
1392
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/80.1.0 filter=lfs diff=lfs merge=lfs -text
1393
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/17.4.0 filter=lfs diff=lfs merge=lfs -text
1394
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/71.6.0 filter=lfs diff=lfs merge=lfs -text
1395
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/15.4.0 filter=lfs diff=lfs merge=lfs -text
1396
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/94.4.0 filter=lfs diff=lfs merge=lfs -text
1397
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/6.1.0 filter=lfs diff=lfs merge=lfs -text
1398
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/30.0.0 filter=lfs diff=lfs merge=lfs -text
1399
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/3.5.0 filter=lfs diff=lfs merge=lfs -text
1400
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/70.3.0 filter=lfs diff=lfs merge=lfs -text
1401
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/45.3.0 filter=lfs diff=lfs merge=lfs -text
1402
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/48.0.0 filter=lfs diff=lfs merge=lfs -text
1403
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/69.7.0 filter=lfs diff=lfs merge=lfs -text
1404
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/37.1.0 filter=lfs diff=lfs merge=lfs -text
1405
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/70.6.0 filter=lfs diff=lfs merge=lfs -text
1406
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/67.7.0 filter=lfs diff=lfs merge=lfs -text
1407
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/35.3.0 filter=lfs diff=lfs merge=lfs -text
1408
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/44.1.0 filter=lfs diff=lfs merge=lfs -text
1409
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/82.6.0 filter=lfs diff=lfs merge=lfs -text
1410
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/11.4.0 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/11.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc29a03bd857231617a25f967815abb8fa58a405f5a424a2a20b642969134c31
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/11.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb7f9f1157721f848373264e1c5ddf1d94cca8bd42c49187e09163083076dccd
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/15.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2709f078c06d673665056ee71796fb574d762ec3857f08849712c29359bb0458
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/17.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec175288f1ca5a42806de6bfec170c2c0f9f93b553d84519aadd7b519f5d2c06
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/20.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:287751543689e53fc696780b07c66c5a3cd68436c69313463604c5f83c3e17f6
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/26.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26c8654e639e476fcbccc01410b78350d02604b843a00d93111230eaaeef3d9e
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/3.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abe1bfdd05b7d527f23217f6ba90c42f4448e70b3fbd79b6e99eebb14e0ce209
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/30.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aaf4dd2d01f5e13ca4fcb9af517265f5139d698481b5a5c6bab5c38eb422ac1
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/35.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ee8c7dfb3670eda9c5c95638ce4566f88efb0d5c55cf64da8d07fac3ddf4569
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/37.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8708b4365f5af540c85a79a37b234e3f73e8961fa1c440d3d03c50083cc58a3e
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/44.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5433307cc7dbd41f4a5903fb65580ae7e1774a7292377b9db4c8dc3f10dd9c43
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/45.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6242ddc0429ecafacf9c958d0951caab3d43d4828e494ccbcd372f033c76c37d
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/45.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5b96f63297baf1bc3dc9b2437c211cf70d174b3de1e0df506ec32a972ffa157
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/48.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88a5a7a296bd8b359be7684f019733c3e671d99dac5b3ea0b510ef782c61bbe0
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/59.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1590579c4bb7b1ec83296ad6c8ad898244358a8a8956965252cb9480b3f16a0
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/6.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80a4b3d7f625313c9884fad8d390dc2dd575b7506376a68b7abf96722b7fd1bb
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/67.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9133363cf29811b90a950eb2928c05c8174d7448bf01b15ffebe124f02503fb
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/69.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e8b6fd0e0b2827311e78ece7ac69088357cea4c6ec578fdb7a10c45fa47da7f
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/70.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70f36fa37c0a533bc49dc4604695c65c781221ebc66a07b9b88d50e436b409f5
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/70.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba0e37e52739cad7e87f5174a0688d298385b70c69dc4d6930b68c287b4dc532
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/71.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f763b763a63965f8457d3929422ef7307460718aec39e8a432b4d4dacc4f3991
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/80.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b5146c77e71daa7c97ddfeb3586fb6d62ceba6b1aa899f188e2df92d7f2c463
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/82.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42473d75ad98c749f69fe55d3130dac46cf1b8713b5f746748c37b9b624cfb3f
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/87.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c77c88712eed8c4fd05dded6a23038c72429991c2916eac92082384b791bd6a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/94.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fcdb2a7d863227c383648e7d2e91d49767b262181106361cc4c256177fbd1aa
3
+ size 99090432