Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
7
jiaqiz commited on
Commit
c740cde
•
1 Parent(s): a6b6caf

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/83.3.0 +3 -0
  3. model_weights/model.decoder.layers.mlp.linear_fc1.weight/89.1.0 +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_proj.weight/15.0.5 +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_proj.weight/17.0.0 +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_proj.weight/18.0.1 +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_proj.weight/21.0.0 +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_proj.weight/28.0.0 +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_proj.weight/31.0.0 +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_proj.weight/39.0.1 +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_proj.weight/53.0.3 +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_proj.weight/53.0.7 +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_proj.weight/55.0.6 +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_proj.weight/59.0.4 +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_proj.weight/59.0.6 +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_proj.weight/59.0.7 +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_proj.weight/6.0.3 +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_proj.weight/60.0.2 +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_proj.weight/63.0.0 +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_proj.weight/63.0.4 +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_proj.weight/72.0.7 +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_proj.weight/73.0.7 +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_proj.weight/88.0.4 +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_proj.weight/90.0.3 +3 -0
  25. model_weights/model.embedding.word_embeddings.weight/5.0 +3 -0
  26. model_weights/model.output_layer.weight/0.0 +3 -0
.gitattributes CHANGED
@@ -2395,3 +2395,28 @@ model_weights/model.decoder.layers.mlp.linear_fc1.weight/82.2.0 filter=lfs diff=
2395
  model_weights/model.decoder.layers.self_attention.linear_proj.weight/41.0.2 filter=lfs diff=lfs merge=lfs -text
2396
  model_weights/model.decoder.layers.mlp.linear_fc1.weight/37.0.0 filter=lfs diff=lfs merge=lfs -text
2397
  model_weights/model.decoder.layers.self_attention.linear_proj.weight/68.0.2 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2395
  model_weights/model.decoder.layers.self_attention.linear_proj.weight/41.0.2 filter=lfs diff=lfs merge=lfs -text
2396
  model_weights/model.decoder.layers.mlp.linear_fc1.weight/37.0.0 filter=lfs diff=lfs merge=lfs -text
2397
  model_weights/model.decoder.layers.self_attention.linear_proj.weight/68.0.2 filter=lfs diff=lfs merge=lfs -text
2398
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/55.0.6 filter=lfs diff=lfs merge=lfs -text
2399
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/31.0.0 filter=lfs diff=lfs merge=lfs -text
2400
+ model_weights/model.decoder.layers.mlp.linear_fc1.weight/83.3.0 filter=lfs diff=lfs merge=lfs -text
2401
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/88.0.4 filter=lfs diff=lfs merge=lfs -text
2402
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/73.0.7 filter=lfs diff=lfs merge=lfs -text
2403
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/59.0.4 filter=lfs diff=lfs merge=lfs -text
2404
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/90.0.3 filter=lfs diff=lfs merge=lfs -text
2405
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/72.0.7 filter=lfs diff=lfs merge=lfs -text
2406
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/6.0.3 filter=lfs diff=lfs merge=lfs -text
2407
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/59.0.7 filter=lfs diff=lfs merge=lfs -text
2408
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/60.0.2 filter=lfs diff=lfs merge=lfs -text
2409
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/39.0.1 filter=lfs diff=lfs merge=lfs -text
2410
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/28.0.0 filter=lfs diff=lfs merge=lfs -text
2411
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/53.0.7 filter=lfs diff=lfs merge=lfs -text
2412
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/18.0.1 filter=lfs diff=lfs merge=lfs -text
2413
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/15.0.5 filter=lfs diff=lfs merge=lfs -text
2414
+ model_weights/model.embedding.word_embeddings.weight/5.0 filter=lfs diff=lfs merge=lfs -text
2415
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/17.0.0 filter=lfs diff=lfs merge=lfs -text
2416
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/21.0.0 filter=lfs diff=lfs merge=lfs -text
2417
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/63.0.4 filter=lfs diff=lfs merge=lfs -text
2418
+ model_weights/model.output_layer.weight/0.0 filter=lfs diff=lfs merge=lfs -text
2419
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/59.0.6 filter=lfs diff=lfs merge=lfs -text
2420
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/53.0.3 filter=lfs diff=lfs merge=lfs -text
2421
+ model_weights/model.decoder.layers.mlp.linear_fc1.weight/89.1.0 filter=lfs diff=lfs merge=lfs -text
2422
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/63.0.0 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.mlp.linear_fc1.weight/83.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c73a5f91a3599cefca6553f9774bca4c9ac2a25cf693cbea74c320f761c475a9
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc1.weight/89.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:261835f04f71dd21e97824d44c98b4f2c2cdd77f15bf0d910c0cc25676e4e8af
3
+ size 339738624
model_weights/model.decoder.layers.self_attention.linear_proj.weight/15.0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:009b2437e6b6d4a5128643b0a0e09b540ed7ee82fa62a18303f2bda25efade07
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/17.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15121f9ade06dafe2bff66bfd1d09d9bb068c636ce2b69866a6f5911815d3892
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/18.0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:365df33ad73c343267e02ed812cb4978663e1e7ac12e86acb909657cf2a5c4d7
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/21.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26f6afca8fe3d15930ec70f13ee7beea9008b280a20f252f1c7f896f8d2f77d4
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/28.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4916fb9324fe586929439b50a7bcd1a7852b118a12ff8ef2b416fed9db1c6ede
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/31.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57c56343ae50d5167e550266a960f7abd12b1d2f3bf2716e8118d8356e939f37
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/39.0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:131c52406b7dec686049a9f57a38eb0aaa8790c477f2d336107a98d27e2ecbec
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/53.0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43d8280c246a665b0bf80b0928acb8d735a91d331e16e21f96f5598d89121961
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/53.0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1f233d15ef19ba23c263a70fcff300c48f2cc7bff8493d6ecff852b5cc7cbbf
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/55.0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aecc3c2a76a1103689dc566bdf4192d9fbf4e96cbf847a35003f58a35e240c62
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/59.0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82f4ae167ed4fca534aa494d9bdcd89128eb9549a6924745568499f2823a93ec
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/59.0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22ce0ad5a8de9bf1bafaaddb8e98520b11d23710e5fb19a36e4ca5af1ad6225c
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/59.0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64fb6039c2bb941fbb1a2fc62b3a58ca6fde38665b19d48b59a3783a33959c07
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/6.0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69e5260c2dce1fc1a952f7e9059da41e7bb2e792f8e4fb3ced09bb69cd65d477
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/60.0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fa5588db3e440e1f47369736f8f3550188781a1a77fcb94b0ec80ef7ce12fde
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/63.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e05fd222de52c0734d24155f23840a3c9a66b0ce6f9aa305c1f04e017d3b2747
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/63.0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad273585752fec960e1037bcba9defdced8c0337a41129ce4f609244175b63f8
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/72.0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e43dc9a6dcc6edfad180cbcd58e60556bfc631035a6b5f5b1b4f4bd8fd044b43
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/73.0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca31f551020965789cc8f8837e6e83ef4019aa450b179b6f09f31df83562e111
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/88.0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7366bd960507d35cec31326a951fde0ba8c53c56d6a7bd866db673d4d729d402
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/90.0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee789f531cb544c7c34390f659114b4cfd8240513778c623c53530e474494016
3
+ size 84934656
model_weights/model.embedding.word_embeddings.weight/5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df054ca5637e1b91de85a0958509d2d514d100400806caac53a667b4a8d9a83b
3
+ size 1179648000
model_weights/model.output_layer.weight/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0d423805223fd694c6bf9827066c22f0bc1ec76cb3126eb9362f79b845d34c4
3
+ size 1179648000