Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
6
jiaqiz commited on
Commit
b002296
•
1 Parent(s): 46ef9d5

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/5.0.5 +3 -0
  3. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/10.7.0 +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/11.6.0 +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/18.0.0 +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/19.4.0 +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/19.6.0 +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/22.1.0 +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/31.1.0 +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/38.2.0 +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/42.7.0 +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/51.5.0 +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/53.0.0 +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/53.6.0 +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.3.0 +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/62.4.0 +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/70.4.0 +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/70.7.0 +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/71.2.0 +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/72.0.0 +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/72.3.0 +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/74.6.0 +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/75.7.0 +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/77.6.0 +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/86.2.0 +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/88.3.0 +3 -0
.gitattributes CHANGED
@@ -883,3 +883,28 @@ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/60.4.0 filte
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
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
886
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/19.6.0 filter=lfs diff=lfs merge=lfs -text
887
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/77.6.0 filter=lfs diff=lfs merge=lfs -text
888
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/22.1.0 filter=lfs diff=lfs merge=lfs -text
889
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/62.4.0 filter=lfs diff=lfs merge=lfs -text
890
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/10.7.0 filter=lfs diff=lfs merge=lfs -text
891
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/72.0.0 filter=lfs diff=lfs merge=lfs -text
892
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/38.2.0 filter=lfs diff=lfs merge=lfs -text
893
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.3.0 filter=lfs diff=lfs merge=lfs -text
894
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/19.4.0 filter=lfs diff=lfs merge=lfs -text
895
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/86.2.0 filter=lfs diff=lfs merge=lfs -text
896
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/70.4.0 filter=lfs diff=lfs merge=lfs -text
897
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/88.3.0 filter=lfs diff=lfs merge=lfs -text
898
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/75.7.0 filter=lfs diff=lfs merge=lfs -text
899
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/53.0.0 filter=lfs diff=lfs merge=lfs -text
900
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/42.7.0 filter=lfs diff=lfs merge=lfs -text
901
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/5.0.5 filter=lfs diff=lfs merge=lfs -text
902
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/74.6.0 filter=lfs diff=lfs merge=lfs -text
903
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/18.0.0 filter=lfs diff=lfs merge=lfs -text
904
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/53.6.0 filter=lfs diff=lfs merge=lfs -text
905
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/11.6.0 filter=lfs diff=lfs merge=lfs -text
906
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/51.5.0 filter=lfs diff=lfs merge=lfs -text
907
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/71.2.0 filter=lfs diff=lfs merge=lfs -text
908
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/70.7.0 filter=lfs diff=lfs merge=lfs -text
909
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/72.3.0 filter=lfs diff=lfs merge=lfs -text
910
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/31.1.0 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.mlp.linear_fc2.weight/5.0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54ee64d27b373d075e3a2aebf0c0126036533a1d848ef4be0327485de20086f5
3
+ size 339738624
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/10.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a597705bfb9af282d1680ab6fec3510034328ffb316ce8edb996aa9be441298a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/11.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:634a4bf3cdd8ada828b8a1b7ea9c16eab11e655a521d17d40845c4580f380502
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/18.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0f869186057ddb0dcb27f78ed65908575d7ad19807d358d27d3477d3291ef82
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/19.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7905c39964eea4dd4dfa329c7477989303537ae7f63fa90c801244e149c01d2
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/19.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad9839420034f63562f9f9683fdf12e456cd207a0718bf5ecc3846ec8270850a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/22.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cc51d9431cce81ea18d1c7472e1797498e4dca64a679e4c58917069fbaab64d
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/31.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d600f04b826bb26ea7b469ba603f8c0f2007b09372a845ceb1ea82a2e2836dde
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/38.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1201b6b626b4afcc4583b1ca4734e09d19006016cc08dbc4fb209dd9edf1de3c
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/42.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad70a164c872f0acac8b13bb19172ba3429e40209d2a8fee34bd40d52a4f7703
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/51.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea654196bdd8e8ced6a9a0ec5be71441a9fed7f048d0249fe291bda84b5d85b1
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/53.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50288dd8c61b47d3fa6ce095666ac3bb6863612ea591a8576761e392a553830b
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/53.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dd1f09c81d838ecd00d94e8cccf22c96b6c20a131b078c434de63d77eba249c
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00c752495ce75de716cb6efc036d7e632f309b209a1aa6586c7d8d5668f26d00
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/62.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c56ead0504a55d38c426afadc3c558506117d896baf6b78245552dcd88405e80
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/70.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4783ca0af807ec927e2e30b930eae9561cf29bae278ba4ecb636dbfd50b03947
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/70.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24491b6d95249b417c0fe2282018877202aa4e5ab5a015f3ddfd22e17a74feed
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/71.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b281708543abd54ca953c4ff1ec0e2f6b06d533cd3d20310843bdc0bafc65e2
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/72.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:776273ab121356800732fb82d8f0e0c9175e5133ba64274cd5ee3fc0112d13e7
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/72.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20d1d32c74282cc2e70e296f3708c11b7e960bd381f7b3fb8708c04dd4d4a6df
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/74.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cef9c505065970b71278f7899066d755e93d7166a4fefbfeb670c2e9247b5a1a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/75.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4791d90205f33e522c65841adbf78866c18ac54dc777c780f49a3b0dc16528eb
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/77.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a605194e10d67ac85fd72450f04e2f127eeb69668e73f3f73639a27d6bd46af6
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/86.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f14f11c982ded1980a284b781cbf3063f81d7b56fa4c045fcf13d2de283a0d40
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/88.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:204a1b1fc2e64f0fe0752373e827f520c949ebd97e0c97d3892878a565e3043f
3
+ size 99090432