Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
6
jiaqiz commited on
Commit
625a27c
•
1 Parent(s): bb3257c

Add files using large-upload tool

Browse files
Files changed (26) hide show
  1. .gitattributes +1 -0
  2. model_weights/model.decoder.layers.mlp.linear_fc1.weight/48.3.0 +3 -0
  3. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_13_96.pt +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_19_96.pt +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_1_96.pt +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_20_96.pt +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_26_96.pt +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_27_96.pt +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_31_96.pt +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_36_96.pt +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_44_96.pt +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_4_96.pt +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_55_96.pt +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_59_96.pt +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_61_96.pt +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_62_96.pt +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_70_96.pt +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_73_96.pt +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_76_96.pt +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_77_96.pt +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_78_96.pt +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_80_96.pt +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_82_96.pt +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_87_96.pt +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_89_96.pt +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_93_96.pt +3 -0
.gitattributes CHANGED
@@ -2296,3 +2296,4 @@ model_weights/model.decoder.layers.mlp.linear_fc1.weight/6.0.0 filter=lfs diff=l
2296
  model_weights/model.decoder.layers.mlp.linear_fc1.weight/73.1.0 filter=lfs diff=lfs merge=lfs -text
2297
  model_weights/model.decoder.layers.mlp.linear_fc1.weight/47.0.0 filter=lfs diff=lfs merge=lfs -text
2298
  model_weights/model.decoder.layers.mlp.linear_fc1.weight/18.4.0 filter=lfs diff=lfs merge=lfs -text
 
 
2296
  model_weights/model.decoder.layers.mlp.linear_fc1.weight/73.1.0 filter=lfs diff=lfs merge=lfs -text
2297
  model_weights/model.decoder.layers.mlp.linear_fc1.weight/47.0.0 filter=lfs diff=lfs merge=lfs -text
2298
  model_weights/model.decoder.layers.mlp.linear_fc1.weight/18.4.0 filter=lfs diff=lfs merge=lfs -text
2299
+ model_weights/model.decoder.layers.mlp.linear_fc1.weight/48.3.0 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.mlp.linear_fc1.weight/48.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9857a3954a2c230f4285135522f6f1e2fa8dcaba846b333c2cbdba7c1c98b2e2
3
+ size 339738624
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_13_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57570292febf0a0a75c54006bef3d68391031abad1dca4dd3a589d78f4633aa0
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_19_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2f56efedb6748e4ff2a0e6a118ad77842e265a67f44e3f1448ce39549f7cc07
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_1_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:960e32a119248151d4cfcc38d1ee9aeaff2c5dcfc6acbd7947127c3886bccebd
3
+ size 1836
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_20_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1805133c804db005b1f4a478e07588a88f548880e2fc453f83e7644f8c0f2db8
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_26_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b86f7738144dd46ad4ffe4c912a086e12834afbbaebe129b22051ddbe796be2
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_27_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6357b4f12640ee695324cdc441d8d5cdc98fa00fb63d5591657e56973674326
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_31_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a0d4b9cdf13a1eba2ed93d85a2982360212cddc77d53c576022e3cbe189615f
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_36_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf56314f019f97c0fd50b64f933a6af12207a4f46d2ff4cb03172248709e85bc
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_44_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aa01a903b4d8af01de2b1ed6a74a5d108252523cd389187716cc17022da5719
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_4_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:461f0daf5250e8e0f6a0d98a3936729d35c8fe255985e7824b06c8b5680cce96
3
+ size 1836
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_55_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:933b45a0255ffbf603631df86198c897aed451e359ea27c8dbab3a43ce6eb6eb
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_59_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:318589273676b17854619902806c202d0e2313dd0f9b335247e78421e3f8fee0
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_61_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1e75f5e6cf3b5158698777317233c81b32327d4d64a20bed579a68da3d8df85
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_62_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcbcfff0cb930a19ae3ee2067f5a9d7c8f01fecdb47e392803f98d550887e9d7
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_70_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ba952db94faa05deee32656353d5863405c51b2db00d2765429a94e5176d4bd
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_73_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bce1ccfc4b24e9618b1ef50d816b3e6fb79f45b8b5eaeaf309ea1004bf9d620
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_76_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a619445c71978910406d1fd76c100b14a38375fd7051198c1226ac41b581dfc
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_77_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ed64539a20733154f17cd57e606a3aab79606fa54fe7c7220cd57d79c6a5c43
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_78_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3266a9256519aec23042c13c73f48061e100e831d06dddb600c039f15926b8c
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_80_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db21718d46912162b654cec2480f049c631f0979c980aa91da91e9421e72576f
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_82_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d981dae8c5c3b6dad6c9f2fe25f26e4c445772ee9d9850c359b836ac8f6ae64
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_87_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b05019f3b231fd0abf8b970f1dc9fe9c9258e169604f125c8aa4defb579a697b
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_89_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:973b9eac5c2f2012525ea4b78ed498c34a1294b3c1c7e6e7f2ea0453c6e9ea07
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_93_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c9154e83763b85c469f90fbd98d7d81388deca2aa97cdf867e343d61f026055
3
+ size 1840