Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
6
jiaqiz commited on
Commit
c13cbd6
•
1 Parent(s): f104603

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/42.0.2 +3 -0
  3. model_weights/model.decoder.layers.mlp.linear_fc2.weight/66.0.6 +3 -0
  4. model_weights/model.decoder.layers.mlp.linear_fc2.weight/77.0.6 +3 -0
  5. model_weights/model.decoder.layers.mlp.linear_fc2.weight/8.0.2 +3 -0
  6. model_weights/model.decoder.layers.mlp.linear_fc2.weight/82.0.3 +3 -0
  7. model_weights/model.decoder.layers.mlp.linear_fc2.weight/93.0.3 +3 -0
  8. model_weights/model.decoder.layers.mlp.linear_fc2.weight/95.0.2 +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/0.1.0 +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/0.2.0 +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/20.7.0 +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/23.3.0 +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/23.6.0 +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/27.1.0 +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/44.0.0 +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/48.2.0 +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/49.5.0 +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/5.7.0 +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/53.2.0 +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/58.0.0 +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/61.6.0 +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/63.2.0 +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.1.0 +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/78.1.0 +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/83.4.0 +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/83.6.0 +3 -0
.gitattributes CHANGED
@@ -783,3 +783,28 @@ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/71.4.0 filte
783
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/95.2.0 filter=lfs diff=lfs merge=lfs -text
784
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/90.5.0 filter=lfs diff=lfs merge=lfs -text
785
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/19.0.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
783
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/95.2.0 filter=lfs diff=lfs merge=lfs -text
784
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/90.5.0 filter=lfs diff=lfs merge=lfs -text
785
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/19.0.0 filter=lfs diff=lfs merge=lfs -text
786
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/0.1.0 filter=lfs diff=lfs merge=lfs -text
787
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/42.0.2 filter=lfs diff=lfs merge=lfs -text
788
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/44.0.0 filter=lfs diff=lfs merge=lfs -text
789
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/66.0.6 filter=lfs diff=lfs merge=lfs -text
790
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/83.6.0 filter=lfs diff=lfs merge=lfs -text
791
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/0.2.0 filter=lfs diff=lfs merge=lfs -text
792
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/77.0.6 filter=lfs diff=lfs merge=lfs -text
793
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/53.2.0 filter=lfs diff=lfs merge=lfs -text
794
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/63.2.0 filter=lfs diff=lfs merge=lfs -text
795
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/58.0.0 filter=lfs diff=lfs merge=lfs -text
796
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/82.0.3 filter=lfs diff=lfs merge=lfs -text
797
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.1.0 filter=lfs diff=lfs merge=lfs -text
798
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/83.4.0 filter=lfs diff=lfs merge=lfs -text
799
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/23.3.0 filter=lfs diff=lfs merge=lfs -text
800
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/5.7.0 filter=lfs diff=lfs merge=lfs -text
801
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/49.5.0 filter=lfs diff=lfs merge=lfs -text
802
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/48.2.0 filter=lfs diff=lfs merge=lfs -text
803
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/8.0.2 filter=lfs diff=lfs merge=lfs -text
804
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/61.6.0 filter=lfs diff=lfs merge=lfs -text
805
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/20.7.0 filter=lfs diff=lfs merge=lfs -text
806
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/23.6.0 filter=lfs diff=lfs merge=lfs -text
807
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/93.0.3 filter=lfs diff=lfs merge=lfs -text
808
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/95.0.2 filter=lfs diff=lfs merge=lfs -text
809
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/78.1.0 filter=lfs diff=lfs merge=lfs -text
810
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/27.1.0 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.mlp.linear_fc2.weight/42.0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a12272746554a4c0aef683be1e6314e212185b440d1fb70428833b3ed7cff3a7
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/66.0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bb7be34bc76e44e3e5e341c23b9ff10dce173deae2a8bf5fa70040bbc786f1a
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/77.0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aedf61ff1783bbb4d1be792c0b9918686fcc20d7e6a7284c66c7cf8f367f5bf2
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/8.0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4bd9fe6126cf4f4744edd24280e75de5665151820b951c620310aa0e6eb7851
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/82.0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e36bf62a1c58d1eaa63dab1137017f3e86cb995fa20e62fa8edbdc881888b23
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/93.0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3924dec5d744767d60a0615c0c543129cec3f3a8343a3ab633b3298a97b6179
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/95.0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02d42cfebcaa53f38aaf7e8b7fd92e07d3e65bffa5f2211b551100e25cc647b
3
+ size 339738624
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/0.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21be2586e2b5a563ac7c333a55be037cba42ce54f4a0dc66a308f08ec6125320
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/0.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28fc0523487862571d314c5d07f2fa850bd5e66b79d6c617b0e682a784bbf278
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/20.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b5a579b1fb096457777e2553ef7358634dd9abefb6ac0399cbcafd51c4f708d
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/23.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a565fa64150543a06953f4ab5c8211f992a0aa5f22eafc94a89be05a7d4bc17
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/23.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc150feb15569f6eae5b28577dfa4c290196efe7c8bfef5681cb21e8dfe26cbd
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/27.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4421343c750af3b0a24ceb1ad104032fdcab655617d23f87aaa052da2ac471cf
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/44.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51485b012727fbd6be096b116b4bbdbc8bb2f7c78105174f4fc2845aca709fad
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/48.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999860273c7922b96fba4b7883e04c5083f9c09de3fab7900639028836e3004b
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/49.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b51511608c3571f61891b006e1ff6405949c299a6f856cf955a44e16119786c8
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/5.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b61b800ac3f614bac884137a5eac32a026c00336b1ced5ba7d2ef941dc9872a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/53.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:391b360d70973ca8a296a744f1346a79869aafc7a1d2f81e6359a85bff6f2731
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/58.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a139fef175817e514653eb1140d71fcfac1b0afaf533f7fe0bd97d527e4358a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/61.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49bd69e5946d151e3a045849b1427e578d69926e736a37c349742719abf0b094
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/63.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:080a5018011cf7bf5115c1d95f8de6fa11b9deacc2d78c67c5e2ef97dbb7c8eb
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f0692098052d250e73afd6188624da8353104426ba07926ccb854db50d0c0c5
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/78.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c7f2ebc43985c8c889be3be77279921d1effd08433bce15b372a1581be4e62a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/83.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb53eaf8e8d6d0d98641edb29eff6efff0d36c672e7dd7e040f8b5b7d804400f
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/83.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05939f1012c67362ad1872525fe5bae5aa276254b565a9ad768145c7aaafae25
3
+ size 99090432