Hugging Face's logo

nvidia
/
Nemotron-4-340B-Instruct

NeMo
Model card Files Community
9
okuchaiev commited on
Commit
6602b67
•
1 Parent(s): a0e1914

Add files using large-upload tool

Browse files
Files changed (25) hide show
  1. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_10_96.pt +3 -0
  2. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_13_96.pt +3 -0
  3. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_22_96.pt +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_25_96.pt +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_29_96.pt +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_30_96.pt +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_34_96.pt +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_37_96.pt +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_38_96.pt +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_40_96.pt +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_42_96.pt +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_45_96.pt +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_46_96.pt +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_47_96.pt +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_52_96.pt +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_54_96.pt +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_58_96.pt +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_5_96.pt +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_65_96.pt +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_67_96.pt +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_6_96.pt +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_76_96.pt +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_77_96.pt +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_80_96.pt +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_89_96.pt +3 -0
model_weights/model.decoder.layers.self_attention.linear_proj._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_proj._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_proj._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_proj._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_proj._extra_state/shard_29_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93a02cbdcf51abcc861138a79d97d339de3a73e2f095bcdb91b275a69d84e44b
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_30_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91ceb57c7deb525d11d475ca2d983ac7fa9bdc652d3767e4466a7d2375007a37
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_34_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d91f28f0611694f24e05103be174094e61828d3965d93218f534e54088c98474
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._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_proj._extra_state/shard_38_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed893da9981fc3c965691baa95bcb6d308b355cad5c450adc7446a4fbe8cd9cb
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_40_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:868c6b9c56fc7d84c93ebc415f8033e3f452a9128c71ead043e86cc7922a09fa
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_42_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1d4594227e34abc31864fc5cb5c5bb9de50e213249edc7d1bbee867b43cef4d
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._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_proj._extra_state/shard_46_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad789da70262159664d4eb45ff65671036d3e6b0987e55bb654956053176e08c
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_47_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb26e8966eceaacdf7fccac7ff9047081b4cd8fe765e32957ff8cfe4480f9187
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_52_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4da794ebf6d3e382c4d891c6de84821e639d5e3913acd3ce4ce2aabda4a0be5e
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._extra_state/shard_54_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8863123f96f55dd3b4087785be202cb5ff411f5c651d8ac8e0442c34e7c35437
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_proj._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_proj._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_proj._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_proj._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_proj._extra_state/shard_6_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4dc039da97daf76c738a1e6cadbe5f420e5ae9813fff7d52383f7a8a6607da5
3
+ size 1836
model_weights/model.decoder.layers.self_attention.linear_proj._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_proj._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_proj._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_proj._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