Hugging Face's logo

nvidia
/
Nemotron-4-340B-Instruct

NeMo
Model card Files Community
12
okuchaiev commited on
Commit
f2fe342
•
1 Parent(s): 6d81254

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_11_96.pt +3 -0
  3. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_12_96.pt +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_14_96.pt +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_18_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_27_96.pt +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_29_96.pt +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_33_96.pt +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_35_96.pt +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_36_96.pt +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_40_96.pt +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_42_96.pt +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_44_96.pt +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_46_96.pt +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_47_96.pt +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_58_96.pt +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_62_96.pt +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_63_96.pt +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_71_96.pt +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_73_96.pt +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_78_96.pt +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_80_96.pt +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_84_96.pt +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_86_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_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_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_14_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9411f9dce48a1d3a9696ced7800e3e952fd83beecc0f2b6789ead864be85342e
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_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_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_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_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_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_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_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_qkv._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_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_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_qkv._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_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_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_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_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_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_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_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_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