Hugging Face's logo

nvidia
/
Nemotron-4-340B-Instruct

NeMo
Model card Files Community
12
okuchaiev commited on
Commit
1480a67
•
1 Parent(s): 6602b67

Add files using large-upload tool

Browse files
Files changed (25) hide show
  1. 8223bf8eaa194eb8920af568bb52e2d0_megatron_2.model +3 -0
  2. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_0_96.pt +3 -0
  3. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_11_96.pt +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_12_96.pt +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_16_96.pt +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_20_96.pt +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_21_96.pt +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_23_96.pt +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_24_96.pt +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_26_96.pt +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_27_96.pt +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_2_96.pt +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_33_96.pt +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_41_96.pt +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_44_96.pt +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_51_96.pt +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_53_96.pt +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_57_96.pt +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_66_96.pt +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_70_96.pt +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_71_96.pt +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_74_96.pt +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_88_96.pt +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_8_96.pt +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_92_96.pt +3 -0
8223bf8eaa194eb8920af568bb52e2d0_megatron_2.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dfd8b970f437002fc445214304969fe59e64d4f48500bd0b77ba55340f2d811
3
+ size 4545602
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_0_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdc3d2b4de551828617fd47b96ac7c52e318644919c6e5971e59dd5af2e8eb76
3
+ size 1836
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_11_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c16ab7e975ec1683fb246b8846d5e3522e81110e097d049d6e7e47968dd0def
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_12_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbddc936f63a9e74256190446eddceda05f3ca9c0dd11133f69d014d82d97729
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_16_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56380ee5d0a36253c51b016e2a2a6647ebf73727236776bd0107e421f8859f4a
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._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_proj._extra_state/shard_21_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba9cf0aa9d4ba429fca6ef4999cab7c3f23988bd11cb2d64d61d0ff667cf45ba
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_23_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86d70087fe5bd0019d9847df5a138621415c0f577e4aa73ffa746494c0a51c33
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_24_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5179bed2b5c6e388ef22488356cbfa2ad38fad93d26689f5d1931fb21a15f18
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._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_proj._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_proj._extra_state/shard_2_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d577e00499f440dc15d0548a709f723869bdf605e0545cac77c538f86be47d79
3
+ size 1836
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_33_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78ed527fdbf7519df18f2ec08dce8e5dbbd3faa456cf37262d30c88d480035e6
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_41_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:214b5869ba1179cdceeff980f2cf65ca7ab650c06b38d2f93b625f2f3a380c58
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._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_proj._extra_state/shard_51_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96b476bf2e0760c9cbc2c6a3921b56833532ce1adc234bb5842a575f27b209a3
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_53_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f3cba55163f9cb2eb4ef8ef5e6bed32df6701f2ee0ecf5e9e8768eece137ceb
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_57_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7f4da70f660e067b374328723d75babc567a6cd4a3a1f223d73775e6c89b800
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_66_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8412872abca334c1531d72b5e29ba333e0254f432b8061ec6902426ad4393de8
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._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_proj._extra_state/shard_71_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc22fd1bd6a75ad5bf28b3d839e81fa367a5ade592e6d13686255d9e7638997f
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_74_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00c62a9494edec5a80785562601134480011a9c9d271f0cc98c9eb2f3b397f52
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_88_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:882291292bd8fa87f3cc5efb0b518fb98a28f78d991be5774119ecaaa2bd41b7
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_8_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79b05b5e7449cacc1b575cb6f9a5a09f210e53f64d2764a59ae613b6629c466c
3
+ size 1836
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_92_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67846f3f0937c288adde34ffff89074cb52bf3d754c97aa8e129de0a0eaa33fd
3
+ size 1840