Hugging Face's logo

nvidia
/
Nemotron-4-340B-Instruct

NeMo
Model card Files Community
12
okuchaiev commited on
Commit
9f9e0d9
•
1 Parent(s): 1480a67

Add files using large-upload tool

Browse files
Files changed (25) hide show
  1. eb5528fdec5c4083affa2c97958eeef7_megatron_2.model +3 -0
  2. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_15_96.pt +3 -0
  3. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_18_96.pt +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_1_96.pt +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_28_96.pt +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_32_96.pt +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_35_96.pt +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_3_96.pt +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_56_96.pt +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_61_96.pt +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_62_96.pt +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_63_96.pt +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_64_96.pt +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_69_96.pt +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_72_96.pt +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_73_96.pt +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_79_96.pt +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_7_96.pt +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_83_96.pt +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_84_96.pt +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_85_96.pt +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_86_96.pt +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_87_96.pt +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_90_96.pt +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_95_96.pt +3 -0
eb5528fdec5c4083affa2c97958eeef7_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_15_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7540850e870ca58f5dbe7b6779eadabf69665d3081b3afd3104a278c3dada8e8
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_18_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f1fa7a8a005c4055031eb0925ab684c9f9cecd43f2aaf47f87a21e665d98ba9
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._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_proj._extra_state/shard_28_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7fbc6732ed5c9780cbc9050a2da6e62b8dbde7f35b9b72e59aac0b8bbd2f556
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_32_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3ec2b18d724a72b6d794099f2440a62e2a76b0b343eb8562c7307923609080b
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_35_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71fdf56e296aed9d8bfc5206799e1d1ac43f582d43ed30f515dbab40112ba258
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_3_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:728bd75592958705378d69f35359d640cda1f742ee5dc7197edc708d86e458b3
3
+ size 1836
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_56_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8ca19127b984ea748cd60fd108954c7dd846a8621056e256f53f3c7682bff95
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._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_proj._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_proj._extra_state/shard_63_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f59797ea4a116134eeeec0ed550b516a625d6cbcd0fc9243aab48c817b31cecc
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_64_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2ec57d9b44038ebea927087321c80b4dfab6365b9485fc4d4d165431a5aea47
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_69_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3693816819b2ae665b43c0df95814b66c5d56af7f1fd8b5870887118b2ce0bf9
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_72_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce281fff94d3e8b57565271ccec2ee98d6e8f6ce97f487d6c4d83859db078079
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._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_proj._extra_state/shard_79_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbcdcca6c7c76a6af8182f224ae09b269d499a7e1e622db91d78e6a034ad4dd5
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_7_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc81ecc1aa4cb51e01abc074e013df21f411e0036c1e63d587bfbd62f30ff52c
3
+ size 1836
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_83_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9afd69b274ff9b5d4b11ca94ecbd70d53374ca5d0adcc8f752ab4eebe2092be
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_84_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34365f11d7adccafc1361ec686a1f1fd8089864a95f0cd952986437aef82b8e3
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_85_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc4edfcb2c11792b55ddf7c83de62c3bb26d09db3990f5e703c0a864bf1d9635
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_86_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faa189c6a89b6c175d8703215d7337418646165f4dc73e847439fc3da5643e06
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._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_proj._extra_state/shard_90_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1784707fcd135c45e6816dddceadc9820f25df2fb07797c61727ad5897929465
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_95_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ed9b0e88ea003e4694006347597bbf59fbaec88fec35807929aadf816051d8e
3
+ size 1840