Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
6
jiaqiz commited on
Commit
4ddc046
•
1 Parent(s): e8b279e

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/1.3.0 +3 -0
  3. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/10.5.0 +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.4.0 +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/18.3.0 +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/2.1.0 +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/21.1.0 +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/27.4.0 +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/31.3.0 +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/35.0.0 +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/38.7.0 +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/41.5.0 +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/44.3.0 +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/5.5.0 +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/54.0.0 +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/58.5.0 +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/62.1.0 +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/7.5.0 +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/73.0.0 +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/76.5.0 +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/77.0.0 +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.7.0 +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/82.5.0 +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/89.4.0 +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/91.6.0 +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/93.1.0 +3 -0
.gitattributes CHANGED
@@ -1058,3 +1058,28 @@ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/8.0.0 filter
1058
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/91.7.0 filter=lfs diff=lfs merge=lfs -text
1059
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/8.7.0 filter=lfs diff=lfs merge=lfs -text
1060
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/36.0.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1058
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/91.7.0 filter=lfs diff=lfs merge=lfs -text
1059
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/8.7.0 filter=lfs diff=lfs merge=lfs -text
1060
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/36.0.0 filter=lfs diff=lfs merge=lfs -text
1061
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/18.3.0 filter=lfs diff=lfs merge=lfs -text
1062
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/82.5.0 filter=lfs diff=lfs merge=lfs -text
1063
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/77.0.0 filter=lfs diff=lfs merge=lfs -text
1064
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/58.5.0 filter=lfs diff=lfs merge=lfs -text
1065
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.4.0 filter=lfs diff=lfs merge=lfs -text
1066
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.7.0 filter=lfs diff=lfs merge=lfs -text
1067
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/1.3.0 filter=lfs diff=lfs merge=lfs -text
1068
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/2.1.0 filter=lfs diff=lfs merge=lfs -text
1069
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/7.5.0 filter=lfs diff=lfs merge=lfs -text
1070
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/73.0.0 filter=lfs diff=lfs merge=lfs -text
1071
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/76.5.0 filter=lfs diff=lfs merge=lfs -text
1072
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/27.4.0 filter=lfs diff=lfs merge=lfs -text
1073
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/35.0.0 filter=lfs diff=lfs merge=lfs -text
1074
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/31.3.0 filter=lfs diff=lfs merge=lfs -text
1075
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/91.6.0 filter=lfs diff=lfs merge=lfs -text
1076
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/62.1.0 filter=lfs diff=lfs merge=lfs -text
1077
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/21.1.0 filter=lfs diff=lfs merge=lfs -text
1078
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/44.3.0 filter=lfs diff=lfs merge=lfs -text
1079
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/41.5.0 filter=lfs diff=lfs merge=lfs -text
1080
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/38.7.0 filter=lfs diff=lfs merge=lfs -text
1081
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/93.1.0 filter=lfs diff=lfs merge=lfs -text
1082
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/5.5.0 filter=lfs diff=lfs merge=lfs -text
1083
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/54.0.0 filter=lfs diff=lfs merge=lfs -text
1084
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/10.5.0 filter=lfs diff=lfs merge=lfs -text
1085
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/89.4.0 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/1.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3509b22ad8282315d55b5e447f7071c003318ef52bfb5683c4b0d3aaf1747802
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/10.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21f0ae9bf61eb52d83bb59bd20444e0125b784146be5f5b8850f7ea4a2d58003
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:154d6df73942d0ac4fd12c20905e4b954c5f939eb712182dc937cf1c985418a0
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/18.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91149de2907e8760f294f66b7d4a9ffd36243f7890b0762de38ebca250135146
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/2.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff39322db78bd3e63b7c64b4709d368762c4f7391ece6dd174360ef81a350a9a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/21.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f388bb1f228308b1a52820f70a8c4a976dcab20833c6facb4d50ce2147b488c6
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/27.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6da60f4d13245820b8d086542f6be5c45f44c0a2d1616a03d2fa33d4873a1f75
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/31.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c680da04578a42f639dda8fe2a2bc384f1dd90826cdd0bc86c23aff0a83b16d
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/35.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa5b0e6a340bd14c915ff009b68490512c349cea1225da347faa84035e9b2f2e
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/38.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3c154d4cf5a5fd0908397fed2a4846942dc3ad8fa3ec4c12d3fc09c70bf9bec
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/41.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b95587161ea4a909681375ccffbe70dacc9512f023cfe44dfecfc9805cfe5a0
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/44.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0b96962e44510fbfff0e9d4665bddedc8646cb4af1de697d50cc1d692584a29
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/5.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58f75575ebef2bb56b3219af73c89580369b44e558e11ef5472f3dc41e233f0b
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/54.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0b5ceafe9fdc5e229380df378a1dc8ea72ffff11fbbba261c8a244012912d3c
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/58.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83f13bde36e3f2d47071a193dfa8236c9e2cbd745c632582b1798b8d18c6cc54
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/62.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cc930d3615e7680913b6940d3ae28981bff0ef301752a80e97b7361cf8a1ed2
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/7.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f61544216181597b8447a60df0227d3150d07adacfaf881f4b9d0882f4ab788b
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/73.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:814cab0e9b3bc37502ee66caefff4f5bd6189699a254f8347fd1c1f89760a49a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/76.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c094b247f92a87a294a2469389e7245d73d96043efb3715e28d6072208256730
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/77.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c643a50fa7b2900f01fc65270c42732e5445de7fc9a2c3d2098a36c2d1a0ece5
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2db084f1d58c8058533edde603328e7f9e13653d05281de69820f1076a635f1b
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/82.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3689459480bf9591c79fd0f7963171988acb43f654a6728d8343b7df188ed173
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/89.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a34389436a999a97d718d37da01f82c23f2d7a10179d8241b610745ecc59bd6d
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/91.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82f213eadc6fa6506bfe5677c46b4b5cc6a7723914077ae86211f4de17f159f8
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/93.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1017bd55686bea3cd823bcb08ab8f7047fe6b5ecd83f523a3bb32af53f6566d1
3
+ size 99090432