Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
6
jiaqiz commited on
Commit
df3e8d6
•
1 Parent(s): 625a27c

Add files using large-upload tool

Browse files
Files changed (25) hide show
  1. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_10_96.pt +3 -0
  2. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_12_96.pt +3 -0
  3. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_15_96.pt +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_18_96.pt +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_22_96.pt +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_25_96.pt +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_28_96.pt +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_33_96.pt +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_37_96.pt +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_43_96.pt +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_45_96.pt +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_49_96.pt +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_51_96.pt +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_56_96.pt +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_58_96.pt +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_5_96.pt +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_63_96.pt +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_65_96.pt +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_66_96.pt +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_67_96.pt +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_68_96.pt +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_74_96.pt +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_79_96.pt +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_86_96.pt +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_91_96.pt +3 -0
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_10_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5270b9cad94b9e70da156dee79990b621170f7fb8ddbb8e1d58a418f6c27f672
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._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_qkv._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_qkv._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_qkv._extra_state/shard_22_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c833ecab87c2c11bb35635b69b2cfcb1c14b2c67777bfa2d5065e05351cb0fbe
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_25_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d49953deb85f273d8951db8614f12bb6a2df7dfa96b9ae426dad74a9e8460eed
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._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_qkv._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_qkv._extra_state/shard_37_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb3a82897ba8dc68ab402af0b948ae54690e9855b3dbc9f58d88bef858704fed
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_43_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f67a153354d75feb672b47442b5b6b4e05a393ff95b9cf077bae7263f185230
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_45_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ea00ddac278ef7e34b6ec4802544a6b6204c661fcbb0682069f13b181042f3d
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_49_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cabdcbeee1b045eb2bc0e6250a49fd397ab59f81b3495065dd1349cc50050a52
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._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_qkv._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_qkv._extra_state/shard_58_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73b9368e11a3afd56aa6c6026d2f9e43ee3e2e7c02c20b390fba72ba95085eca
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_5_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f42fd66eecd7e6c963f020f21cb951f7012635811641c29d8646b96905e1e0
3
+ size 1836
model_weights/model.decoder.layers.self_attention.linear_qkv._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_qkv._extra_state/shard_65_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f5f205e847bf17a236c61ffd3265b0d4354037d5a4a5867c191f428eb89542c
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._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_qkv._extra_state/shard_67_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5ba43e84b15cd21861c5c82b06043582e89234f1dd5a93a45433855d46acc16
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_68_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07033b70d349490e62e87c37b2c422207efe1e2411b575672ba110bc3c338d55
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._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_qkv._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_qkv._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_qkv._extra_state/shard_91_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01048ad3a21833fd1c3279d20e19d6190d5d695c68f738e3b6401bb8b6601ed3
3
+ size 1840