Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
7
jiaqiz commited on
Commit
3b67cdf
•
1 Parent(s): 89c2e6d

Add files using large-upload tool

Browse files
Files changed (26) hide show
  1. .gitattributes +8 -0
  2. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_15_96.pt +3 -0
  3. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_25_96.pt +3 -0
  4. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_28_96.pt +3 -0
  5. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_33_96.pt +3 -0
  6. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_37_96.pt +3 -0
  7. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_41_96.pt +3 -0
  8. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_43_96.pt +3 -0
  9. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_48_96.pt +3 -0
  10. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_51_96.pt +3 -0
  11. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_58_96.pt +3 -0
  12. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_5_96.pt +3 -0
  13. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_66_96.pt +3 -0
  14. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_67_96.pt +3 -0
  15. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_68_96.pt +3 -0
  16. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_74_96.pt +3 -0
  17. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_79_96.pt +3 -0
  18. model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_86_96.pt +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/0.3.0 +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/15.3.0 +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/19.7.0 +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/57.1.0 +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/72.1.0 +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/73.1.0 +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/82.2.0 +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/83.3.0 +3 -0
.gitattributes CHANGED
@@ -1529,3 +1529,11 @@ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/26.6.0 filte
1529
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/6.0.0 filter=lfs diff=lfs merge=lfs -text
1530
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/92.0.0 filter=lfs diff=lfs merge=lfs -text
1531
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/1.1.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
1529
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/6.0.0 filter=lfs diff=lfs merge=lfs -text
1530
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/92.0.0 filter=lfs diff=lfs merge=lfs -text
1531
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/1.1.0 filter=lfs diff=lfs merge=lfs -text
1532
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/82.2.0 filter=lfs diff=lfs merge=lfs -text
1533
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/57.1.0 filter=lfs diff=lfs merge=lfs -text
1534
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/83.3.0 filter=lfs diff=lfs merge=lfs -text
1535
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/0.3.0 filter=lfs diff=lfs merge=lfs -text
1536
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/15.3.0 filter=lfs diff=lfs merge=lfs -text
1537
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/72.1.0 filter=lfs diff=lfs merge=lfs -text
1538
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/73.1.0 filter=lfs diff=lfs merge=lfs -text
1539
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/19.7.0 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_15_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7540850e870ca58f5dbe7b6779eadabf69665d3081b3afd3104a278c3dada8e8
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_25_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d49953deb85f273d8951db8614f12bb6a2df7dfa96b9ae426dad74a9e8460eed
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_28_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7fbc6732ed5c9780cbc9050a2da6e62b8dbde7f35b9b72e59aac0b8bbd2f556
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_33_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78ed527fdbf7519df18f2ec08dce8e5dbbd3faa456cf37262d30c88d480035e6
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_37_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb3a82897ba8dc68ab402af0b948ae54690e9855b3dbc9f58d88bef858704fed
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_41_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:214b5869ba1179cdceeff980f2cf65ca7ab650c06b38d2f93b625f2f3a380c58
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_43_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f67a153354d75feb672b47442b5b6b4e05a393ff95b9cf077bae7263f185230
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_48_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb4e3686edebeef34059ccb1a24181f803157ce2fe1ad32327842e52f332f016
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_51_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96b476bf2e0760c9cbc2c6a3921b56833532ce1adc234bb5842a575f27b209a3
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_58_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73b9368e11a3afd56aa6c6026d2f9e43ee3e2e7c02c20b390fba72ba95085eca
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_5_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f42fd66eecd7e6c963f020f21cb951f7012635811641c29d8646b96905e1e0
3
+ size 1836
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_66_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8412872abca334c1531d72b5e29ba333e0254f432b8061ec6902426ad4393de8
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_67_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5ba43e84b15cd21861c5c82b06043582e89234f1dd5a93a45433855d46acc16
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_68_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07033b70d349490e62e87c37b2c422207efe1e2411b575672ba110bc3c338d55
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_74_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00c62a9494edec5a80785562601134480011a9c9d271f0cc98c9eb2f3b397f52
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_79_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbcdcca6c7c76a6af8182f224ae09b269d499a7e1e622db91d78e6a034ad4dd5
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc1._extra_state/shard_86_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faa189c6a89b6c175d8703215d7337418646165f4dc73e847439fc3da5643e06
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/0.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0517cffe76ee3d3e47f99e6d62edcaf85257f96f463c1ff6452dee930b3af6be
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/15.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baeac4f548bab5a6ea6393f9086093f0662a996f632eb39793711e884008fba4
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/19.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd10374d6cd2d3267cc2d2813c98ffc7f7c31d8d00b7752f798b572802c2e4bf
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/57.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2b802b28ad57227a7ff0de5257cff8a92c36a3339243014c14d3b3b55bd54de
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/72.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d70a46e5f05ed00abde915e46aa8c98565db8717873a3db88be184ea3d995a9a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/73.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ecc3cadef1b9e3019d8466800bcad267f34f62c1efd76619a5a0b1e70c99628
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/82.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ebeef494a4af0e7773bd7eae7f0654f31f0f64ae43e2123f289641037984b36
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/83.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a853624a079bd4570f42ecc2fbd94e5f389c23e9b41bbb3eb5a1629b5f7fb62
3
+ size 99090432