Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
6
jiaqiz commited on
Commit
89efb8f
•
1 Parent(s): acab4b6

Add files using large-upload tool

Browse files
Files changed (26) hide show
  1. .gitattributes +18 -0
  2. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_11_96.pt +3 -0
  3. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_16_96.pt +3 -0
  4. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_17_96.pt +3 -0
  5. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_29_96.pt +3 -0
  6. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_39_96.pt +3 -0
  7. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_52_96.pt +3 -0
  8. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_9_96.pt +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/12.4.0 +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/16.7.0 +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/2.4.0 +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/25.4.0 +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/25.7.0 +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/26.6.0 +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/30.3.0 +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/33.5.0 +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/34.4.0 +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/4.6.0 +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.6.0 +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/51.3.0 +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.1.0 +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/69.6.0 +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/70.0.0 +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/80.2.0 +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/81.5.0 +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/9.2.0 +3 -0
.gitattributes CHANGED
@@ -1508,3 +1508,21 @@ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/22.7.0 filte
1508
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/42.4.0 filter=lfs diff=lfs merge=lfs -text
1509
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/12.1.0 filter=lfs diff=lfs merge=lfs -text
1510
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.2.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1508
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/42.4.0 filter=lfs diff=lfs merge=lfs -text
1509
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/12.1.0 filter=lfs diff=lfs merge=lfs -text
1510
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.2.0 filter=lfs diff=lfs merge=lfs -text
1511
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/12.4.0 filter=lfs diff=lfs merge=lfs -text
1512
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/70.0.0 filter=lfs diff=lfs merge=lfs -text
1513
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/16.7.0 filter=lfs diff=lfs merge=lfs -text
1514
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/81.5.0 filter=lfs diff=lfs merge=lfs -text
1515
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/4.6.0 filter=lfs diff=lfs merge=lfs -text
1516
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/34.4.0 filter=lfs diff=lfs merge=lfs -text
1517
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/69.6.0 filter=lfs diff=lfs merge=lfs -text
1518
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/30.3.0 filter=lfs diff=lfs merge=lfs -text
1519
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/2.4.0 filter=lfs diff=lfs merge=lfs -text
1520
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/9.2.0 filter=lfs diff=lfs merge=lfs -text
1521
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/33.5.0 filter=lfs diff=lfs merge=lfs -text
1522
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/25.7.0 filter=lfs diff=lfs merge=lfs -text
1523
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/51.3.0 filter=lfs diff=lfs merge=lfs -text
1524
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/25.4.0 filter=lfs diff=lfs merge=lfs -text
1525
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.1.0 filter=lfs diff=lfs merge=lfs -text
1526
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/80.2.0 filter=lfs diff=lfs merge=lfs -text
1527
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.6.0 filter=lfs diff=lfs merge=lfs -text
1528
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/26.6.0 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_11_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c16ab7e975ec1683fb246b8846d5e3522e81110e097d049d6e7e47968dd0def
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_16_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56380ee5d0a36253c51b016e2a2a6647ebf73727236776bd0107e421f8859f4a
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_17_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abcbc429045a564b70b5b8e6a3aebd65d5c9033d0851500eb76c099f47d78a95
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_29_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93a02cbdcf51abcc861138a79d97d339de3a73e2f095bcdb91b275a69d84e44b
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_39_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b109bc001c35c681140f7729d952690a2e524e10f7f31b66473cd9368535724
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_52_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4da794ebf6d3e382c4d891c6de84821e639d5e3913acd3ce4ce2aabda4a0be5e
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_9_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aee04ee3a9964d7e6d305e5c1ad233bf6ef32b34178cda7bf7c2083c011e4e56
3
+ size 1836
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/12.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3de63fb92c6598c32b72843510e603cf0f83540526c6b8ccf05824deae7fbd13
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/16.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df47fd27cce00d3f59063bcc516accde7f6e85eeec15cee7b51017218ad1547d
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/2.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f543e7d742674909371d569d67e34374e189187045a00ac3ba46eaca8b4c7147
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/25.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b58071bf6dae80c783884ea198f574867bace0d541d1e9cc066af32e61c2753
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/25.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fdb5971b06ccbcb4d2dfe2998128d7dd2c05541e54b06dcf998cbb79588cfc6
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/26.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:239b01fea57329a25bfabcfe29eb3dd6a92ef3f75ba44f1178c557ff9d5aaf8b
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/30.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56d9b439d8c47976ab8826a06e36587218c70bd4a25af4932379c5e678e5e69c
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/33.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79439e0c0d7a7be0acea86dd4dc07971f33f5fdf1e759988ba6a1e397b3be9eb
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/34.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fea8305ba29f0f3d86965cb3c832d797804641b351b6f1a339a443d317b7f65e
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/4.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7650a2390eb4950d988dd64f24e162910935ba41b84fc3cfb478df9b663f62cf
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fbaf1aa7849bec80b9edf2cf8ffcb560beddd87c8990f977471dc309baa5522
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/51.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:691925a922e00a25433c3aa684ccb1037f7e303996ce34d1f0e459e09ae36bdb
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:684632423e9d6f5bd3b4379d8618879a025c88ce215014d9c6c9045d4b057ed1
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/69.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1778666f4654f5d6aa7acb22d4674c83cbe4c73ca0a9130e66307703464fe070
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/70.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ec1994d8f2447a0c58f955900db1f5693d75024d123760ff9c9bc57eb8226f9
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/80.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75a1b6f5bf979ab248401fc8544ba0dd13187c3903c99935bc92487fc0ccff0b
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/81.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce2ddba9af7e311700c3ca052fd1680989c1344a810615545079ad623450beff
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/9.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c66a5f45e4346b4950e283723001df22a07c8e1b8f3b52bcbe74c09446a4b8e4
3
+ size 99090432