Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
7
jiaqiz commited on
Commit
510e9ca
•
1 Parent(s): aaf5aaa

Add files using large-upload tool

Browse files
Files changed (26) hide show
  1. .gitattributes +15 -0
  2. model_weights/model.decoder.final_layernorm.weight/.zarray +14 -0
  3. model_weights/model.decoder.final_layernorm.weight/0 +0 -0
  4. model_weights/model.decoder.layers.mlp.linear_fc2.weight/11.0.1 +3 -0
  5. model_weights/model.decoder.layers.mlp.linear_fc2.weight/2.0.4 +3 -0
  6. model_weights/model.decoder.layers.mlp.linear_fc2.weight/29.0.5 +3 -0
  7. model_weights/model.decoder.layers.mlp.linear_fc2.weight/33.0.7 +3 -0
  8. model_weights/model.decoder.layers.mlp.linear_fc2.weight/4.0.1 +3 -0
  9. model_weights/model.decoder.layers.mlp.linear_fc2.weight/40.0.7 +3 -0
  10. model_weights/model.decoder.layers.mlp.linear_fc2.weight/46.0.1 +3 -0
  11. model_weights/model.decoder.layers.mlp.linear_fc2.weight/58.0.1 +3 -0
  12. model_weights/model.decoder.layers.mlp.linear_fc2.weight/67.0.1 +3 -0
  13. model_weights/model.decoder.layers.mlp.linear_fc2.weight/67.0.6 +3 -0
  14. model_weights/model.decoder.layers.mlp.linear_fc2.weight/72.0.6 +3 -0
  15. model_weights/model.decoder.layers.mlp.linear_fc2.weight/75.0.1 +3 -0
  16. model_weights/model.decoder.layers.mlp.linear_fc2.weight/79.0.4 +3 -0
  17. model_weights/model.decoder.layers.mlp.linear_fc2.weight/89.0.4 +3 -0
  18. model_weights/model.decoder.layers.mlp.linear_fc2.weight/91.0.2 +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_bias/22.0 +0 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_bias/40.0 +0 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_bias/48.0 +0 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_bias/52.0 +0 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_bias/75.0 +0 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_bias/8.0 +0 -0
  25. model_weights/model.embedding.word_embeddings.weight/.zarray +16 -0
  26. model_weights/model.output_layer.weight/.zarray +16 -0
.gitattributes CHANGED
@@ -532,3 +532,18 @@ model_weights/model.decoder.layers.mlp.linear_fc2.weight/21.0.2 filter=lfs diff=
532
  model_weights/model.decoder.layers.mlp.linear_fc2.weight/90.0.6 filter=lfs diff=lfs merge=lfs -text
533
  model_weights/model.decoder.layers.mlp.linear_fc2.weight/35.0.7 filter=lfs diff=lfs merge=lfs -text
534
  model_weights/model.decoder.layers.mlp.linear_fc2.weight/23.0.5 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
532
  model_weights/model.decoder.layers.mlp.linear_fc2.weight/90.0.6 filter=lfs diff=lfs merge=lfs -text
533
  model_weights/model.decoder.layers.mlp.linear_fc2.weight/35.0.7 filter=lfs diff=lfs merge=lfs -text
534
  model_weights/model.decoder.layers.mlp.linear_fc2.weight/23.0.5 filter=lfs diff=lfs merge=lfs -text
535
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/2.0.4 filter=lfs diff=lfs merge=lfs -text
536
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/72.0.6 filter=lfs diff=lfs merge=lfs -text
537
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/29.0.5 filter=lfs diff=lfs merge=lfs -text
538
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/46.0.1 filter=lfs diff=lfs merge=lfs -text
539
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/4.0.1 filter=lfs diff=lfs merge=lfs -text
540
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/33.0.7 filter=lfs diff=lfs merge=lfs -text
541
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/40.0.7 filter=lfs diff=lfs merge=lfs -text
542
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/79.0.4 filter=lfs diff=lfs merge=lfs -text
543
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/11.0.1 filter=lfs diff=lfs merge=lfs -text
544
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/89.0.4 filter=lfs diff=lfs merge=lfs -text
545
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/67.0.6 filter=lfs diff=lfs merge=lfs -text
546
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/58.0.1 filter=lfs diff=lfs merge=lfs -text
547
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/75.0.1 filter=lfs diff=lfs merge=lfs -text
548
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/67.0.1 filter=lfs diff=lfs merge=lfs -text
549
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/91.0.2 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.final_layernorm.weight/.zarray ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunks": [
3
+ 18432
4
+ ],
5
+ "compressor": null,
6
+ "dtype": "bfloat16",
7
+ "fill_value": null,
8
+ "filters": null,
9
+ "order": "C",
10
+ "shape": [
11
+ 18432
12
+ ],
13
+ "zarr_format": 2
14
+ }
model_weights/model.decoder.final_layernorm.weight/0 ADDED
Binary file (36.9 kB). View file
 
model_weights/model.decoder.layers.mlp.linear_fc2.weight/11.0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f32deef4024ec32aa0987d0af5a4c26798417bd81ebe4e0e511ae8703b9a760
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/2.0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5fb82ae819b0885f93cdd1abea9f531be4ef6f5d7421690049734856025506c
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/29.0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5bae87327978a06b4103470e76e69a9faec6dfc41c457997808ca30b015b0a
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/33.0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95ac7a00d0d94d089969400be4b1cf8eebbf7a6a1fba880d7f6a2f12e967b73b
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/4.0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be65d6a83668a2503a6ac2806421f431d3bc9e8d964d1c6439fa8de5282b5b83
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/40.0.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2306b91176bb8b3b306563688a23452dbaf2a3a9f65cc8acab0503a0ae57e7f
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/46.0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70b4a539557c3d31c647a9a6bd3578d418a96bb07e8e7e78c593c8ed4fd5f612
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/58.0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64733f490bdabade2da27e0058079a03ff5247a72c19592c014cedf81d1c5f1a
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/67.0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc722d6022050f8f914d11f3b41bea8c3d8e989682e93560582b937409d06b65
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/67.0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:960a9b1841d7cead87e1294184375478316b54f207a78a55d95c32548f0838da
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/72.0.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac97189a180b625db118d8be67969c9c0e9c2f934179ab72aad5150bdbec3a63
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/75.0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec5f053d76ebf5aee9a8360a79f99c60622c264bc735feaf2fe507c2f22cc705
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/79.0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0d557d87e934f334e410ce4336edc4dfa39c68576105f4cc4c77c619bdac679
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/89.0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf3317786e02ff977438a498d3951d95085635cc843b0ff51f3495b1ea555cb9
3
+ size 339738624
model_weights/model.decoder.layers.mlp.linear_fc2.weight/91.0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1209d719ed30cc60f7110c111cc04ba2ffffec6864a8bb722fb52dd8a53f3ab
3
+ size 339738624
model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_bias/22.0 ADDED
Binary file (36.9 kB). View file
 
model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_bias/40.0 ADDED
Binary file (36.9 kB). View file
 
model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_bias/48.0 ADDED
Binary file (36.9 kB). View file
 
model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_bias/52.0 ADDED
Binary file (36.9 kB). View file
 
model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_bias/75.0 ADDED
Binary file (36.9 kB). View file
 
model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_bias/8.0 ADDED
Binary file (36.9 kB). View file
 
model_weights/model.embedding.word_embeddings.weight/.zarray ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunks": [
3
+ 32000,
4
+ 18432
5
+ ],
6
+ "compressor": null,
7
+ "dtype": "bfloat16",
8
+ "fill_value": null,
9
+ "filters": null,
10
+ "order": "C",
11
+ "shape": [
12
+ 256000,
13
+ 18432
14
+ ],
15
+ "zarr_format": 2
16
+ }
model_weights/model.output_layer.weight/.zarray ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunks": [
3
+ 32000,
4
+ 18432
5
+ ],
6
+ "compressor": null,
7
+ "dtype": "bfloat16",
8
+ "fill_value": null,
9
+ "filters": null,
10
+ "order": "C",
11
+ "shape": [
12
+ 256000,
13
+ 18432
14
+ ],
15
+ "zarr_format": 2
16
+ }