Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
7
jiaqiz commited on
Commit
3ac977d
•
1 Parent(s): 1dce3ed

Add files using large-upload tool

Browse files
Files changed (26) hide show
  1. .gitattributes +25 -0
  2. model_weights/model.decoder.layers.mlp.linear_fc2.weight/26.0.5 +3 -0
  3. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/1.0.0 +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/1.2.0 +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/21.2.0 +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/22.4.0 +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/24.2.0 +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/24.7.0 +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/25.0.0 +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/3.4.0 +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/36.4.0 +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/47.4.0 +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/49.1.0 +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/49.4.0 +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/5.0.0 +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/6.3.0 +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/60.1.0 +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/63.1.0 +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/65.0.0 +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/75.6.0 +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/76.7.0 +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.2.0 +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/80.0.0 +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/81.2.0 +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/84.4.0 +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/84.5.0 +3 -0
.gitattributes CHANGED
@@ -1158,3 +1158,28 @@ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/77.1.0 filte
1158
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/33.4.0 filter=lfs diff=lfs merge=lfs -text
1159
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/51.7.0 filter=lfs diff=lfs merge=lfs -text
1160
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/74.4.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1158
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/33.4.0 filter=lfs diff=lfs merge=lfs -text
1159
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/51.7.0 filter=lfs diff=lfs merge=lfs -text
1160
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/74.4.0 filter=lfs diff=lfs merge=lfs -text
1161
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/22.4.0 filter=lfs diff=lfs merge=lfs -text
1162
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/24.7.0 filter=lfs diff=lfs merge=lfs -text
1163
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/49.1.0 filter=lfs diff=lfs merge=lfs -text
1164
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/3.4.0 filter=lfs diff=lfs merge=lfs -text
1165
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/75.6.0 filter=lfs diff=lfs merge=lfs -text
1166
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/76.7.0 filter=lfs diff=lfs merge=lfs -text
1167
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/26.0.5 filter=lfs diff=lfs merge=lfs -text
1168
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/36.4.0 filter=lfs diff=lfs merge=lfs -text
1169
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/6.3.0 filter=lfs diff=lfs merge=lfs -text
1170
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/63.1.0 filter=lfs diff=lfs merge=lfs -text
1171
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/60.1.0 filter=lfs diff=lfs merge=lfs -text
1172
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/5.0.0 filter=lfs diff=lfs merge=lfs -text
1173
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/25.0.0 filter=lfs diff=lfs merge=lfs -text
1174
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/24.2.0 filter=lfs diff=lfs merge=lfs -text
1175
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/1.0.0 filter=lfs diff=lfs merge=lfs -text
1176
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/84.5.0 filter=lfs diff=lfs merge=lfs -text
1177
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/49.4.0 filter=lfs diff=lfs merge=lfs -text
1178
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.2.0 filter=lfs diff=lfs merge=lfs -text
1179
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/65.0.0 filter=lfs diff=lfs merge=lfs -text
1180
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/47.4.0 filter=lfs diff=lfs merge=lfs -text
1181
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/80.0.0 filter=lfs diff=lfs merge=lfs -text
1182
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/84.4.0 filter=lfs diff=lfs merge=lfs -text
1183
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/81.2.0 filter=lfs diff=lfs merge=lfs -text
1184
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/1.2.0 filter=lfs diff=lfs merge=lfs -text
1185
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/21.2.0 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.mlp.linear_fc2.weight/26.0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92cede426f091ba8682653fb4a3be78df5e0f27912ffc0f63aaef3a305c53fcd
3
+ size 339738624
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/1.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5518a9b5f86d491fc8186989e5717b02d7447ac54118ab0309b7145184af8a53
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/1.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8df39b0a3ae159954eb4877d3c8d721c0042bd9080c88cd93aae3f5d877590a2
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/21.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6c43dc79d0e099f727801ccb26fc74016a77dee9c0bf2b506e1e638b114edde
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/22.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88fd2d0fcf27cd16ec1d6b4a7981fb017dd79297b283fce868375e92fb0996d5
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/24.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:673d7fde3225187b58aec6a0b5904fde16204199ba698d17b471a8969a40a7df
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/24.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc3da9a5604569e64a9904044b22c25546968ea2ad6aea14d172b66a55272661
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/25.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd5b3bc53701fcda04b78c4cba25cd94c739cd36ce8733a8829139437c5049d9
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/3.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce9013f37ba2ceed412b4e8816f7a95d9f09cf794d4d043e92c83e97c8e23563
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/36.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd0562057218fe9ceaffd524c61d0f45d0e1149ffc5830d43af7037245ee81f3
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/47.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:decec7fa16df8fbeab1863a9a2a77d8bfa8e64d50d0ce9b14b5505d0193d3890
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/49.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6709bbe01233461d730d95ec67ca4442c41314ae938cc29bf0c0b569c16b3bad
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/49.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d540e82efe7da16fdb54b728dc030bb9a5dafddb4ba6eab35c263cf17591e5f
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/5.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4bef3c539dd4650d2d588d9ae52b89b5cb36f55174400dac7ff4e219ec55e97
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/6.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aceaf3f7b0ffc44fcbfad9ce5e923aefefb3204ae26c4e5e5b323e931f4e282
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/60.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96d61cfae2249e06d6e975cb7037294b0e4cd2048e0708be281193864b7a2857
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/63.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8463c87d0db5a54e297dd486914027c0f8df923b52ce62e1b5fc8e3d6ecd090c
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/65.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:181e006e59e9fc9948c03c4f2e093aa54e29d709797b3b363dfc667c90e40de6
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/75.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1f2def6a0c2a854f71ff17952f9bd904978e40c6f4353b60d1cf149bf7827a8
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/76.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65b66213f43110c0bbf63d3a1e06fb922f51274569782695f657f52ded400887
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:700241f9399ffa64b6e8cf2104eab5a4ad0f9e5c0ebfc9990e3ae724a9656cf6
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/80.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3b8b810e3603a120f16853a9f0744e0aca27fed4c74e7b53881afd82e9f37a8
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/81.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72c422285e4b55524dc8ed346cb4d441184d530c96cf6294f80e4104da9fb686
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/84.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1641b38fb3c94d233dbb7ca876f41892f6705f11a32ff42fab1be6e9c9d817fc
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/84.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3be15b1e8af4b37212873527c3511f141c33046106947e5270abd3c861942483
3
+ size 99090432