Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
7
jiaqiz commited on
Commit
46ef9d5
•
1 Parent(s): 336d7ee

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/15.0.2 +3 -0
  3. model_weights/model.decoder.layers.mlp.linear_fc2.weight/54.0.2 +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/17.0.0 +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/17.5.0 +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/21.0.0 +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/25.6.0 +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/27.2.0 +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/27.5.0 +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/29.4.0 +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/30.5.0 +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/36.5.0 +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/39.2.0 +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/4.0.0 +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/48.5.0 +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/51.4.0 +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.6.0 +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/6.5.0 +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/60.4.0 +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/63.0.0 +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/7.1.0 +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/74.1.0 +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/8.4.0 +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/80.5.0 +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/92.7.0 +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/93.4.0 +3 -0
.gitattributes CHANGED
@@ -858,3 +858,28 @@ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/86.3.0 filte
858
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/78.2.0 filter=lfs diff=lfs merge=lfs -text
859
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/37.3.0 filter=lfs diff=lfs merge=lfs -text
860
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/61.0.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
858
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/78.2.0 filter=lfs diff=lfs merge=lfs -text
859
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/37.3.0 filter=lfs diff=lfs merge=lfs -text
860
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/61.0.0 filter=lfs diff=lfs merge=lfs -text
861
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/54.0.2 filter=lfs diff=lfs merge=lfs -text
862
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/17.0.0 filter=lfs diff=lfs merge=lfs -text
863
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/80.5.0 filter=lfs diff=lfs merge=lfs -text
864
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/21.0.0 filter=lfs diff=lfs merge=lfs -text
865
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/30.5.0 filter=lfs diff=lfs merge=lfs -text
866
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/93.4.0 filter=lfs diff=lfs merge=lfs -text
867
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/74.1.0 filter=lfs diff=lfs merge=lfs -text
868
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/63.0.0 filter=lfs diff=lfs merge=lfs -text
869
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/4.0.0 filter=lfs diff=lfs merge=lfs -text
870
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/17.5.0 filter=lfs diff=lfs merge=lfs -text
871
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/29.4.0 filter=lfs diff=lfs merge=lfs -text
872
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/39.2.0 filter=lfs diff=lfs merge=lfs -text
873
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/8.4.0 filter=lfs diff=lfs merge=lfs -text
874
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.6.0 filter=lfs diff=lfs merge=lfs -text
875
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/7.1.0 filter=lfs diff=lfs merge=lfs -text
876
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/27.2.0 filter=lfs diff=lfs merge=lfs -text
877
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/36.5.0 filter=lfs diff=lfs merge=lfs -text
878
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/48.5.0 filter=lfs diff=lfs merge=lfs -text
879
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/6.5.0 filter=lfs diff=lfs merge=lfs -text
880
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/51.4.0 filter=lfs diff=lfs merge=lfs -text
881
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/27.5.0 filter=lfs diff=lfs merge=lfs -text
882
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/60.4.0 filter=lfs diff=lfs merge=lfs -text
883
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/15.0.2 filter=lfs diff=lfs merge=lfs -text
884
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/25.6.0 filter=lfs diff=lfs merge=lfs -text
885
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/92.7.0 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.mlp.linear_fc2.weight/15.0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b1271a2534df7a497bd6e538bff4462efb6a4170497c1d81ad465f3714b8e5a
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/54.0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c2ee60c61404bd1ac25b5dc1f719879e1c13cf54d95853360322bea3bb079ac
3
+ size 339738624
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/17.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:469f100e26b42a71b4c89744241252763c55146eca4b9b7d88a3230115109036
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/17.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a84193ecf24d925e3d2823e06ae8bd47f71dfacdf0bd140e6c774a8c975204eb
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/21.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e612371f91087439979274738746be64ff280e3b4220bbd2f69bbda722742ee2
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/25.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0958afeca02e60a344ae3faf9717fb9a91438b725673ab8d8027ca81a5939ace
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/27.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b2e103a89967e6963d3fbd105960a77040b34c3973d623f5a6f92a55e1e9112
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/27.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91030af3c6ea9ac43d5e9f486dde565174541272a6ea53edd88118b2881e3be9
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/29.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8881153663da859a5ea1a4c42c522367fa6abc34eb83bd87d93f1281bfff995e
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/30.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68e0c2b51201b55625c6822e7e8edec1b5c51fd0a5f0b4e38539e0aee80362d5
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/36.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe35286347080610dc213d2cffcf1841a98dbc191ce62af0787c4c896e6fe161
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/39.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e74ab546cc3f6540b9107eba79087ce1fed311f22e1d44f76ee3bf28f71d8c86
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/4.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdad89bca2571582907bfa7dc0eb7bb2f43140294b4c2e8dfcc229fcc8bee65e
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/48.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a59ce9b2fbd771e3e3f1b8b8c5fe8f08653e061ac9187a503623a6969a6e737d
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/51.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e357b25d0962644b3648ac3cd7c141ae83ae47aa38cca8ffbd9a53c08f078988
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:192b5db7daa588f7413e8ba27a7577b6c38eab4809817f408de755bf4867d4ce
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/6.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d8e295ba883417d4a215e203f5051bc5fb92c54d56eeff36079bd8072b40998
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/60.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e9b57a72e9dffa83f737c62c9bd131b325f210273b70673563b76dc69c56e38
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/63.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:723359ae658d3b99c3075904bedbfb60de5d29fc76d7165b404a59cbb302f9fc
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/7.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c66183bf769582432a6bcfa70ff784e566d5da7b9dd01d8541f2e88581c47d12
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/74.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d84ecbe62232e4e140736d3a581ff67f9d32b405eae46ac4b8d09519b7209105
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/8.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:531813408a91796a4d2c3c4985c9af17543aa97c80d28f66a5c5e277dd58dd27
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/80.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dc1a8a78773fe3eadb67786a7cc82947bac61a2f36394d14883da30e3c23eb0
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/92.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ad7d024b6c7d856889230ec467b78496c7f949f90e2557db1d7b0547ff5de95
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/93.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06cf70f0eafa2f2ecface1e6539b174b54c52c7956e4f71b065d7a75b9ee4acd
3
+ size 99090432