Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
6
jiaqiz commited on
Commit
2ed597d
•
1 Parent(s): c13cbd6

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/30.0.1 +3 -0
  3. model_weights/model.decoder.layers.mlp.linear_fc2.weight/38.0.1 +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.0.0 +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/19.2.0 +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/23.0.0 +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/26.5.0 +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/3.6.0 +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/33.0.0 +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/33.2.0 +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/34.5.0 +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/4.4.0 +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/46.1.0 +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/51.0.0 +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/58.1.0 +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/60.6.0 +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/61.1.0 +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/69.0.0 +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/73.2.0 +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/76.1.0 +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/78.4.0 +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/82.0.0 +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/82.7.0 +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/94.1.0 +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/94.6.0 +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/95.4.0 +3 -0
.gitattributes CHANGED
@@ -808,3 +808,28 @@ model_weights/model.decoder.layers.mlp.linear_fc2.weight/93.0.3 filter=lfs diff=
808
  model_weights/model.decoder.layers.mlp.linear_fc2.weight/95.0.2 filter=lfs diff=lfs merge=lfs -text
809
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/78.1.0 filter=lfs diff=lfs merge=lfs -text
810
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/27.1.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
808
  model_weights/model.decoder.layers.mlp.linear_fc2.weight/95.0.2 filter=lfs diff=lfs merge=lfs -text
809
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/78.1.0 filter=lfs diff=lfs merge=lfs -text
810
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/27.1.0 filter=lfs diff=lfs merge=lfs -text
811
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/61.1.0 filter=lfs diff=lfs merge=lfs -text
812
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/95.4.0 filter=lfs diff=lfs merge=lfs -text
813
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/38.0.1 filter=lfs diff=lfs merge=lfs -text
814
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/33.2.0 filter=lfs diff=lfs merge=lfs -text
815
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/19.2.0 filter=lfs diff=lfs merge=lfs -text
816
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/34.5.0 filter=lfs diff=lfs merge=lfs -text
817
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/73.2.0 filter=lfs diff=lfs merge=lfs -text
818
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.0.0 filter=lfs diff=lfs merge=lfs -text
819
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/46.1.0 filter=lfs diff=lfs merge=lfs -text
820
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/76.1.0 filter=lfs diff=lfs merge=lfs -text
821
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/82.0.0 filter=lfs diff=lfs merge=lfs -text
822
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/33.0.0 filter=lfs diff=lfs merge=lfs -text
823
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/4.4.0 filter=lfs diff=lfs merge=lfs -text
824
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/3.6.0 filter=lfs diff=lfs merge=lfs -text
825
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/58.1.0 filter=lfs diff=lfs merge=lfs -text
826
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/23.0.0 filter=lfs diff=lfs merge=lfs -text
827
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/82.7.0 filter=lfs diff=lfs merge=lfs -text
828
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/26.5.0 filter=lfs diff=lfs merge=lfs -text
829
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/60.6.0 filter=lfs diff=lfs merge=lfs -text
830
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/94.6.0 filter=lfs diff=lfs merge=lfs -text
831
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/78.4.0 filter=lfs diff=lfs merge=lfs -text
832
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/30.0.1 filter=lfs diff=lfs merge=lfs -text
833
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/51.0.0 filter=lfs diff=lfs merge=lfs -text
834
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/69.0.0 filter=lfs diff=lfs merge=lfs -text
835
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/94.1.0 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.mlp.linear_fc2.weight/30.0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02ad9277e81ff10f6bc6380c73e900de5e329bf4365a852de3aeb3abb7910fb6
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/38.0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:768df42ddebfe6f1a42fb467460cbddcb24e0719c4469ba68a96732136c3aedd
3
+ size 339738624
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a5d6c70d12c15c5d0a6cad13c62911ff5e22440a3d4073b53fa40c1d69692a2
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/19.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e762d2560ae75f13863f8e89761ffc3773d63fcbcc2724a257d072a753256a73
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/23.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bf3f692f23aafa23c07d800182f7d2f6a22e9cd82cd3e606c9562bd2056bfda
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/26.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25ef4e6c37e847db06e94fbb75761dce4eb525897b3c75cd84bccf0f360cfd85
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/3.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cbb4c3f85fab2b7ff866cdb149f46994a4357cba9dad7b10da7e08f27246b72
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/33.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccd486b7bfaf19f13e4e0fc4c0a1bbc5fdcb116f337e19a659f022afe9881e37
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/33.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e471b540111b62eeff94c508f42869e8cda08236a64cd34a57578174a6e4465c
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/34.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17a8e0dcf80e398c10f7d5b674542066be2f9c546718ed75da461a108eb5fa27
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/4.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2593ca0992735290f483ace46a82569c55354bea86957824f7dd5611dac96059
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/46.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f6219bae48605784132f135962a6603d12b098993590842fbaeaca7f8e6f2d5
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/51.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa860bd3f2f85f23d9b70825f0c3a4605b3182a80f96001dda7ff17aa7fa665b
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/58.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00e2990192858728a6bc32953f72a403f61a84d8cfbb1b2cc8524423ed6b2bc8
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/60.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3df83701e0ed4aec0b6edbea63b9241369617bf56c8a6e51f5932e791bb2d75
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/61.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d52933e591656d8c6bcaaf6b5181168ed38472820ca6b119d5bdd7cc1ae7d81
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/69.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f86ad2aa60a14159d73a97b06e90c8357c0bb8835d116fb8154391f9d3da1d8
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/73.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:022b5a704c9266b7505c799f0849861682d58b629985aff857170faf098ac649
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/76.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4e73b19af9db152349f2073f52e8030cbda8146fc3a5ffb1d7ed8050d9f100f
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/78.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c487be63d109b4eb80c9f52767893daca7b07bf338f44d3e4f0cb58789ba764e
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/82.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:154e3cd69c934aa2fa96d09bdbb83e3ac128f21c8aacc2ecd1f7eca75fba3840
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/82.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32377b73e660f49a94efa442e23c664c391e25207bcb6edbace6d44e446ec432
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/94.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:402314a47b4777449024fa28bbe914a103b3e3ecae5e8591d6b1e98ef90d2b9f
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/94.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72f8a486443b1c284a2a9f9c899e5a5a09f9ba8d96e1d95bfa9c27b919c0c3ba
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/95.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3fc4472408ceb8400234dcb161a01e773cf186bf60a33f70e3c087b419cf46c
3
+ size 99090432