Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
6
jiaqiz commited on
Commit
717224d
•
1 Parent(s): f36d93c

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/27.0.7 +3 -0
  3. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/10.6.0 +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.3.0 +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/14.2.0 +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/20.5.0 +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/23.4.0 +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/29.0.0 +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/38.5.0 +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/4.3.0 +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/40.5.0 +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/40.6.0 +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/41.1.0 +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/46.4.0 +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/47.1.0 +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/52.0.0 +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/54.1.0 +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/54.4.0 +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/56.1.0 +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/64.0.0 +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/65.1.0 +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.0.0 +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/69.2.0 +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/72.4.0 +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/75.4.0 +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/9.7.0 +3 -0
.gitattributes CHANGED
@@ -1008,3 +1008,28 @@ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/32.4.0 filte
1008
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/78.7.0 filter=lfs diff=lfs merge=lfs -text
1009
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/48.1.0 filter=lfs diff=lfs merge=lfs -text
1010
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/36.6.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1008
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/78.7.0 filter=lfs diff=lfs merge=lfs -text
1009
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/48.1.0 filter=lfs diff=lfs merge=lfs -text
1010
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/36.6.0 filter=lfs diff=lfs merge=lfs -text
1011
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/40.6.0 filter=lfs diff=lfs merge=lfs -text
1012
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/27.0.7 filter=lfs diff=lfs merge=lfs -text
1013
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/38.5.0 filter=lfs diff=lfs merge=lfs -text
1014
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/54.4.0 filter=lfs diff=lfs merge=lfs -text
1015
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/69.2.0 filter=lfs diff=lfs merge=lfs -text
1016
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/46.4.0 filter=lfs diff=lfs merge=lfs -text
1017
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/64.0.0 filter=lfs diff=lfs merge=lfs -text
1018
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/9.7.0 filter=lfs diff=lfs merge=lfs -text
1019
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/65.1.0 filter=lfs diff=lfs merge=lfs -text
1020
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/23.4.0 filter=lfs diff=lfs merge=lfs -text
1021
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/47.1.0 filter=lfs diff=lfs merge=lfs -text
1022
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.3.0 filter=lfs diff=lfs merge=lfs -text
1023
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/52.0.0 filter=lfs diff=lfs merge=lfs -text
1024
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.0.0 filter=lfs diff=lfs merge=lfs -text
1025
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/56.1.0 filter=lfs diff=lfs merge=lfs -text
1026
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/54.1.0 filter=lfs diff=lfs merge=lfs -text
1027
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/14.2.0 filter=lfs diff=lfs merge=lfs -text
1028
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/10.6.0 filter=lfs diff=lfs merge=lfs -text
1029
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/20.5.0 filter=lfs diff=lfs merge=lfs -text
1030
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/75.4.0 filter=lfs diff=lfs merge=lfs -text
1031
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/29.0.0 filter=lfs diff=lfs merge=lfs -text
1032
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/41.1.0 filter=lfs diff=lfs merge=lfs -text
1033
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/40.5.0 filter=lfs diff=lfs merge=lfs -text
1034
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/4.3.0 filter=lfs diff=lfs merge=lfs -text
1035
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/72.4.0 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.mlp.linear_fc2.weight/27.0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e12c0a4403029d3b0132d4abc7b35ec2ad29ad94cebd2dabe71227105ce0df84
3
+ size 339738624
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/10.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f49e136b7a002cd445399fb3898175777949deaecfa70f696503ccf180dc78fb
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:287a04bab7bc6692c42770e6b1853784e2e774566b050bb0dc4fc13bf10146ce
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/14.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:936db2ca4c62d169cd7d261691bb75105ce601e68186e57ca20f0089b86ec76c
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/20.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbf31db75ff42ce2a02c9a5867c37338fb610321446ea1f879f3c3e4f67f4744
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/23.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6699db806b55e173225bc7f7d896d1c5b7421ed906eec094ec57f8cc28c90f87
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/29.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a63ed94e47bbe2f7c7fe02858b856865d344ebf237e310a33d0bf12b721fe047
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/38.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01c35e75524c38db523bf426512b2b334b53a8c867f3bdad695137f5ac33be55
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/4.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dee625917baed0399ed007bf6799cc52fb620051e7ad875054b25b18990f2c6
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/40.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c22db6bea3f2829e649bd4e45a038e07558ed038246e51d130df187d4c06660
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/40.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b83067767fef2da5b06c72259472398012f4cd5008b9bb54372d6f02488e44b
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/41.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1e9afcc8ab79477e720f2e9e4341b7767f3351f3c37af0021d9d4fa8d1411bd
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/46.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc292aa6411eb1769b692eba1768590f3fe52fa77b56ef9475f034722698e270
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/47.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:457d86e4adc1edfaae50aa1601b4cfca683d4d13922ddcdd255edd29abd596a4
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/52.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a05e66cc3880f37e738f3bf81e324294b78cd440b5c33b77bc4c7362b4b2230
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/54.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e89397eb346d8ff4c2ebba26ec5da831e4a6cb4aff285db17e8f2a5f263cf41
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/54.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da5494b4282eb5effe577536471e21799d1c8676bbd8c478de124e72f32a3510
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/56.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:352627f591e6a566058a1f9cf1fef1446ee1e1bc10099629ff9fd5db4091e912
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/64.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d9ae516aeeb2e5d3d1b9e11ab17fbb80d626afddf72e79095ffa8cc51f98e46
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/65.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a291c93d99fb5f4cfa209a9028b2aa62b39b6c4e49824da4eff03ea782b0bc02
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:facfbc07a38a0248c384551a1a27e254dadaad7b728c91f55f5e9dee016219b3
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/69.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d0bfb64d47bfa6c880dd079e8f9e8087477270d78c1a9537c66ed43dfcb7da
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/72.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db9043cf1326745f41ea61aacd924b812c1fb3277c18f9ff774504d57f8f849c
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/75.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a88f61185d61738ca4a92304dc86c9588ceb9f9c8865f8d8decd380e5434f4c
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/9.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6313dca9509a662e0e99606367a58995bf36f5822f6ceb8d9870d04440964bb5
3
+ size 99090432