Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
7
jiaqiz commited on
Commit
079f309
·
verified ·
1 Parent(s): 4ddc046

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/12.0.0 +3 -0
  3. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.2.0 +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/20.1.0 +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/29.5.0 +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/3.1.0 +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/30.6.0 +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/31.4.0 +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/35.4.0 +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/38.1.0 +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/40.2.0 +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/5.4.0 +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/54.2.0 +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/57.2.0 +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/58.4.0 +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/59.6.0 +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/63.6.0 +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.2.0 +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/67.2.0 +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/76.3.0 +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/76.4.0 +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.3.0 +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/87.3.0 +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/94.0.0 +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/94.2.0 +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/95.7.0 +3 -0
.gitattributes CHANGED
@@ -1083,3 +1083,28 @@ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/5.5.0 filter
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
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
1086
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/63.6.0 filter=lfs diff=lfs merge=lfs -text
1087
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/57.2.0 filter=lfs diff=lfs merge=lfs -text
1088
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/94.2.0 filter=lfs diff=lfs merge=lfs -text
1089
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/20.1.0 filter=lfs diff=lfs merge=lfs -text
1090
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/40.2.0 filter=lfs diff=lfs merge=lfs -text
1091
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/67.2.0 filter=lfs diff=lfs merge=lfs -text
1092
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/5.4.0 filter=lfs diff=lfs merge=lfs -text
1093
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/29.5.0 filter=lfs diff=lfs merge=lfs -text
1094
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/12.0.0 filter=lfs diff=lfs merge=lfs -text
1095
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.3.0 filter=lfs diff=lfs merge=lfs -text
1096
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/31.4.0 filter=lfs diff=lfs merge=lfs -text
1097
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/76.4.0 filter=lfs diff=lfs merge=lfs -text
1098
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/30.6.0 filter=lfs diff=lfs merge=lfs -text
1099
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.2.0 filter=lfs diff=lfs merge=lfs -text
1100
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/95.7.0 filter=lfs diff=lfs merge=lfs -text
1101
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/94.0.0 filter=lfs diff=lfs merge=lfs -text
1102
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/59.6.0 filter=lfs diff=lfs merge=lfs -text
1103
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/58.4.0 filter=lfs diff=lfs merge=lfs -text
1104
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/3.1.0 filter=lfs diff=lfs merge=lfs -text
1105
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/35.4.0 filter=lfs diff=lfs merge=lfs -text
1106
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/38.1.0 filter=lfs diff=lfs merge=lfs -text
1107
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/87.3.0 filter=lfs diff=lfs merge=lfs -text
1108
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.2.0 filter=lfs diff=lfs merge=lfs -text
1109
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/54.2.0 filter=lfs diff=lfs merge=lfs -text
1110
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/76.3.0 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/12.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2db5ffa5f4e3b99e25d830506c229adb8315f586cff5f72eb1e088253462179d
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a30cd5cbdd1393a3337dd391c5fd27359116c18a39458f0ca268864d0dc8b23
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/20.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c99abc59be5d7ebbeb97a86ea4e90fc39b9763f226a12a9a76af09bb33a74e57
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/29.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8b212d8ef2fa4c00ca698ebe2a74cb814fa38443e9eb0cb8e9b575a7f1b8586
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/3.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01274a7acd98cae830bc4ac09911a8dd98fa8e9e89cdb84f3255b89338a2ba7e
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/30.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:955e727995f5c51fb66341a1a360ac5dd58113a9a777fafc3d454701fb57c067
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/31.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:480b1977a5435b15a334781634f7a7ba5177b2d067d734623159f69daa58b4be
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/35.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f8ab4f85fac2138f674fb9c792cec7cd2f15aa400cc63bea3d72fbdaadfa6cd
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/38.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59858ec511b75bf3968b10adbcf590045c00e2ac71e2fb8a142b5dd1bcc389b1
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/40.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d829014462f2a1c2837269ab72b840c0c5555c3cb1a254ed3799ddd6d4aed46e
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/5.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:012b8e7c1e01f84e31cd7ead326ba718f5288701f60d2721dadf3c1978f9a181
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/54.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b45e530a7f46e251bd72e8bc46dd68b9c63a2c4b5da8a7c843c00a10025355d4
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/57.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30732df0932e2f7532e2a746add8bb16249c4172c993a444d9ae2cb4b6c4834c
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/58.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6beb95617dc093739f73ca53e99588066c1e6bf6d5dc58a1146ff6761e1e3a69
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/59.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50b22b1a35ef270b18316b1c7daf30f94fddffcbb2a5a1177a0b2c06be39465c
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/63.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:935ea782a33685c7ad7b70ee8729e9ea769680c452177852f682a109aeea3709
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:501eafa0ea39e8160e1fb15f795e4e4e4a5902008c85f9c1165579d1ebe6bc29
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/67.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44b7c4956fb6ed1867d9844640197f80c16c1c06c1f2c8283cd455115bd6d13a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/76.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d878d9f2218f285874ef41c92f8e7906da558d0a1fc62b827eab108b13a56451
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/76.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aca9a1daa7aed6cbcf291a1cbd65f39f46754f418fde3cf36ac2d61bfbb5f75d
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa11ff72566d5c3de2d9e13e33a0886fba9d5dd13ea474e7a69421a78a7f943b
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/87.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e88eb95395b433e62caa4c19020a74b8920b48843d3cf84e65872a9b7e3ccb9a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/94.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5199912dc78a38d190392fb2d020318cf9da577170b855988ea720f895e640f
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/94.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a9c4937e223303b893ca2bd40c98cf82553e35a2afe7aa410eb2d5a0c254f8b
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/95.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c8dac9c259d2af972ee8df10a1ce439ecad3e4960410b4c83ece9a53b9c1812
3
+ size 99090432