Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
6
jiaqiz commited on
Commit
b41ac6a
•
1 Parent(s): 251c79e

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/36.0.7 +3 -0
  3. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/1.6.0 +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.1.0 +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/14.0.0 +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/14.6.0 +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/24.1.0 +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/26.3.0 +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/32.3.0 +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/34.6.0 +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/37.4.0 +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/38.0.0 +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/41.3.0 +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/5.2.0 +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/65.3.0 +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/69.4.0 +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/71.5.0 +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/8.2.0 +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/8.6.0 +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/83.1.0 +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/85.0.0 +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/85.2.0 +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/85.4.0 +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/89.6.0 +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/95.0.0 +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/95.1.0 +3 -0
.gitattributes CHANGED
@@ -958,3 +958,28 @@ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/22.5.0 filte
958
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/81.1.0 filter=lfs diff=lfs merge=lfs -text
959
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/28.1.0 filter=lfs diff=lfs merge=lfs -text
960
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.4.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
958
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/81.1.0 filter=lfs diff=lfs merge=lfs -text
959
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/28.1.0 filter=lfs diff=lfs merge=lfs -text
960
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.4.0 filter=lfs diff=lfs merge=lfs -text
961
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/85.0.0 filter=lfs diff=lfs merge=lfs -text
962
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/95.0.0 filter=lfs diff=lfs merge=lfs -text
963
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/37.4.0 filter=lfs diff=lfs merge=lfs -text
964
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/95.1.0 filter=lfs diff=lfs merge=lfs -text
965
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/38.0.0 filter=lfs diff=lfs merge=lfs -text
966
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/69.4.0 filter=lfs diff=lfs merge=lfs -text
967
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.1.0 filter=lfs diff=lfs merge=lfs -text
968
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/26.3.0 filter=lfs diff=lfs merge=lfs -text
969
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/36.0.7 filter=lfs diff=lfs merge=lfs -text
970
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/32.3.0 filter=lfs diff=lfs merge=lfs -text
971
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/83.1.0 filter=lfs diff=lfs merge=lfs -text
972
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/89.6.0 filter=lfs diff=lfs merge=lfs -text
973
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/85.4.0 filter=lfs diff=lfs merge=lfs -text
974
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/1.6.0 filter=lfs diff=lfs merge=lfs -text
975
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/8.2.0 filter=lfs diff=lfs merge=lfs -text
976
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/41.3.0 filter=lfs diff=lfs merge=lfs -text
977
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/65.3.0 filter=lfs diff=lfs merge=lfs -text
978
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/71.5.0 filter=lfs diff=lfs merge=lfs -text
979
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/5.2.0 filter=lfs diff=lfs merge=lfs -text
980
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/24.1.0 filter=lfs diff=lfs merge=lfs -text
981
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/8.6.0 filter=lfs diff=lfs merge=lfs -text
982
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/85.2.0 filter=lfs diff=lfs merge=lfs -text
983
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/14.0.0 filter=lfs diff=lfs merge=lfs -text
984
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/14.6.0 filter=lfs diff=lfs merge=lfs -text
985
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/34.6.0 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.mlp.linear_fc2.weight/36.0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c4a29741c3672845d38da499ec0f98859f6117b9e6b47493be7b0f3a293264f
3
+ size 339738624
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/1.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:138d745a645f2ab2c0ce6ab5b4b759ec3549ea9b188dcfb7c9ff392495a0b3a7
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d4781c0ba8282f1341efbdb699b7402b6d43e5f962693e80746f9b1a4a1c4f7
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/14.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c874fea2c7c7d3c5afab90e82feed8772305089dc97f43743f6120343d59bd09
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/14.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f3626a912bf4581ffdd5df7669c473a10b1784da12740aeb4af3ffd99478016
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/24.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e91bba32b1461c881c6daf6f42570091cfc1ba36b68f7280bb1b1ed245c5782
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/26.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:333ceabc06956f6fb4daaffb2a408d43046da18e20cccc655cb7f771a059f515
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/32.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8df2ef2f040f5c2eb829122c5c67c4de66f3bcbd4d276b3cdf4c548af071acae
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/34.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8979f458cfa3f003e6ad78387fb667469e4c327d17658072cac833a955cbb33e
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/37.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2462673d204249f21e7b276bd6a37b3fe39ff51434a72dbb3e30405a26cfc6b
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/38.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c57b5625e230a04d60ab491a1611214b5418aa88acd8565ea370687a46adeb7
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/41.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c03b94821fa78afdaadbd46f52a1615eaf69899261815c31a93a92c0d602236
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/5.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fc57fee85f59a36ce97b3ea4ddd2282f17a0e81075bc0dde15152eeaf5ced11
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/65.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bf49535b86932111e9b1e0c603a762f1872dbc7a64fcec758618f1e01442481
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/69.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a27489e72c7f5a8368c32fe666b1b9990984cbfef3abaafd8a46646472c8dab6
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/71.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68f93ad88a94cd99c0d39af258c1ca6752f6c5e1fd1d55cce2191ce079086396
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/8.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c50f5aa3d6dc972380131c7a838bd1df6b6eda764be2014b3387af1af2f24302
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/8.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96d26b8995c7c057f5491763a00b49edd1009f2678f278ce6ebca2e613e17f77
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/83.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75fa1e2ce11017ba3314235b62ae91ad07e1d9609e8956a7d4150dc458018f00
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/85.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f72e4e812910a994971307106bafc1b3c96e68da45c0e851dc97ca5289517d6
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/85.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e251dd22e7e5a779bc0bac43036b7819f73271fbad7242020b5db6f57fd2c5e
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/85.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01aad0bc79c7fc74100208d029d0af186684985379744bfe78e8666b439c567a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/89.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8ff30a5c19432a5a0bbf4f3788407bc8331ecc44f40d100ce5e14f33cda89cd
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/95.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89f0b90782465a5dc6418c4acbd203e80ecb507764e7b7f77d8f177b01607ec8
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/95.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:febd42b733932a7da43c2e13541c2d05d536b7f8b1b78a305249c5779eb0c584
3
+ size 99090432