Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
6
jiaqiz commited on
Commit
2eadc64
•
1 Parent(s): adec83b

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_fc1.weight/27.0.0 +3 -0
  3. model_weights/model.decoder.layers.mlp.linear_fc1.weight/52.1.0 +3 -0
  4. model_weights/model.decoder.layers.mlp.linear_fc1.weight/70.0.0 +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_proj.weight/13.0.4 +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_proj.weight/16.0.6 +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_proj.weight/20.0.4 +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_proj.weight/20.0.6 +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_proj.weight/22.0.1 +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_proj.weight/24.0.2 +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_proj.weight/27.0.2 +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_proj.weight/34.0.3 +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_proj.weight/38.0.0 +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_proj.weight/41.0.7 +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_proj.weight/42.0.3 +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_proj.weight/44.0.5 +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_proj.weight/55.0.7 +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_proj.weight/61.0.7 +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_proj.weight/67.0.3 +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_proj.weight/67.0.5 +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_proj.weight/69.0.1 +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_proj.weight/7.0.2 +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_proj.weight/88.0.6 +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_proj.weight/91.0.1 +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_proj.weight/92.0.6 +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_proj.weight/93.0.2 +3 -0
.gitattributes CHANGED
@@ -2470,3 +2470,28 @@ model_weights/model.decoder.layers.self_attention.linear_proj.weight/51.0.1 filt
2470
  model_weights/model.decoder.layers.self_attention.linear_proj.weight/57.0.2 filter=lfs diff=lfs merge=lfs -text
2471
  model_weights/model.decoder.layers.self_attention.linear_proj.weight/3.0.7 filter=lfs diff=lfs merge=lfs -text
2472
  model_weights/model.decoder.layers.self_attention.linear_proj.weight/68.0.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2470
  model_weights/model.decoder.layers.self_attention.linear_proj.weight/57.0.2 filter=lfs diff=lfs merge=lfs -text
2471
  model_weights/model.decoder.layers.self_attention.linear_proj.weight/3.0.7 filter=lfs diff=lfs merge=lfs -text
2472
  model_weights/model.decoder.layers.self_attention.linear_proj.weight/68.0.0 filter=lfs diff=lfs merge=lfs -text
2473
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/91.0.1 filter=lfs diff=lfs merge=lfs -text
2474
+ model_weights/model.decoder.layers.mlp.linear_fc1.weight/27.0.0 filter=lfs diff=lfs merge=lfs -text
2475
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/20.0.6 filter=lfs diff=lfs merge=lfs -text
2476
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/22.0.1 filter=lfs diff=lfs merge=lfs -text
2477
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/69.0.1 filter=lfs diff=lfs merge=lfs -text
2478
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/16.0.6 filter=lfs diff=lfs merge=lfs -text
2479
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/38.0.0 filter=lfs diff=lfs merge=lfs -text
2480
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/44.0.5 filter=lfs diff=lfs merge=lfs -text
2481
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/93.0.2 filter=lfs diff=lfs merge=lfs -text
2482
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/20.0.4 filter=lfs diff=lfs merge=lfs -text
2483
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/34.0.3 filter=lfs diff=lfs merge=lfs -text
2484
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/92.0.6 filter=lfs diff=lfs merge=lfs -text
2485
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/24.0.2 filter=lfs diff=lfs merge=lfs -text
2486
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/67.0.3 filter=lfs diff=lfs merge=lfs -text
2487
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/13.0.4 filter=lfs diff=lfs merge=lfs -text
2488
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/61.0.7 filter=lfs diff=lfs merge=lfs -text
2489
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/42.0.3 filter=lfs diff=lfs merge=lfs -text
2490
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/67.0.5 filter=lfs diff=lfs merge=lfs -text
2491
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/27.0.2 filter=lfs diff=lfs merge=lfs -text
2492
+ model_weights/model.decoder.layers.mlp.linear_fc1.weight/52.1.0 filter=lfs diff=lfs merge=lfs -text
2493
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/7.0.2 filter=lfs diff=lfs merge=lfs -text
2494
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/41.0.7 filter=lfs diff=lfs merge=lfs -text
2495
+ model_weights/model.decoder.layers.mlp.linear_fc1.weight/70.0.0 filter=lfs diff=lfs merge=lfs -text
2496
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/55.0.7 filter=lfs diff=lfs merge=lfs -text
2497
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/88.0.6 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.mlp.linear_fc1.weight/27.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b95b304b7b3a074c6fced6559f247a7594695fe72471e7cb22ae842c4f9788b4
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc1.weight/52.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a429b4d0df3cf2d67ddc06acc5aa7c3a1c148cb956b32bccc053f69885bccf07
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc1.weight/70.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:053b87a549b1edf2e0e15d6688f3efb5229581229a66f634dc175f174f04d555
3
+ size 339738624
model_weights/model.decoder.layers.self_attention.linear_proj.weight/13.0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c2be22e7052d2f6d584a86e9a6a2cd39253e43b6d1429a307cb44bdd42d09e4
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/16.0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b662d67d830c89b047c64a888a8fee347a2ca4dfae7c257560eedf3993586821
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/20.0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f51a6f305a7491b36b49997011aef0922bebbc8d1259504c9884ca9577cb0c40
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/20.0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:154d832a83e8389cd71b48042ab809e97560961b52a4a728fabdb15416ae1e9d
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/22.0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b8e0d024d2e2b5b9d14b944c3e225260240cbdd72682a106096361dcb71d94e
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/24.0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77d6b50e83dc6e9f92d336b8966f81d184519d17853e17a834d8f29591cf6d54
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/27.0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7805236cd062c4c1650568a84ed36b3d0e27af50ba82256552c2e0c2e6a1e9c4
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/34.0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d77f712b78d88f856ba5cec5416ba484bfc7bb39802b1c158b1671de5a4fa182
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/38.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f60078727a58e49bd8cdc12e2be15b8f82e881dd56a2111d36faebeba4bf1c1
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/41.0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea9425b30d6441df2df84ccd4f17f3610d9250a7e2023b8ccdcd8e6eac1dc93c
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/42.0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0885b667b9b89fd20e77216f278327a2715843305d74720c86e1ff580355d0fb
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/44.0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39f0a9518cce394c998265dc25ffc1d741698a9559148368bbbd3fdb8b016893
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/55.0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6a28a55d09b4d318e661c924d2bb0658c60f43fd24021a74118c3c31b191aaf
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/61.0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a0f8c0260d07df4a4224885f24bb52947ef94a294d8a8bb093b4ff191bf2a86
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/67.0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63d24ba77473e8327e9176e792ba8bc6c09aab351eb411173b79279953a2d320
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/67.0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a856b1166034237219e0ae981fc1522e96814b23cd10e3dce4d2949f104a5f08
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/69.0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d64948696d4c096e80ec90b7ac7c214a4a7ba795d47bb86bdc74423531fd15e
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/7.0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e232dc6d352ad887642b17a26b65ba1a6c207ef7b158d5295139cd724eb0ff1
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/88.0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:813d2a568b6e45bb1f4b97f4905f296710f09193b401cc382ee7fcde8a32eb68
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/91.0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fbd96e0c8a564d20ea78107b1fff7f3870639de3a5933a97eff511481946707
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/92.0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a24498041a378a6f493e67f9c8bd9defde3bcacbbc6712e7a0d8e0495ff29fc
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/93.0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e358d5c002bd1f06239abac9b67cd1ab287019c31343af0434e0432f00225da7
3
+ size 84934656