Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
6
jiaqiz commited on
Commit
6754076
•
1 Parent(s): f7f2182

Add files using large-upload tool

Browse files
Files changed (25) hide show
  1. d6b0ba93e9734b138f5fc61f5652efbd_nemotron_2_256k.model +3 -0
  2. model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_22_96.pt +3 -0
  3. model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_26_96.pt +3 -0
  4. model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_27_96.pt +3 -0
  5. model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_35_96.pt +3 -0
  6. model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_44_96.pt +3 -0
  7. model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_47_96.pt +3 -0
  8. model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_55_96.pt +3 -0
  9. model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_61_96.pt +3 -0
  10. model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_65_96.pt +3 -0
  11. model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_70_96.pt +3 -0
  12. model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_73_96.pt +3 -0
  13. model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_76_96.pt +3 -0
  14. model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_7_96.pt +3 -0
  15. model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_91_96.pt +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_weight/12.0 +0 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_weight/13.0 +0 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_weight/54.0 +0 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_weight/61.0 +0 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_weight/67.0 +0 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_weight/73.0 +0 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_weight/80.0 +0 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_weight/82.0 +0 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_weight/83.0 +0 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_weight/93.0 +0 -0
d6b0ba93e9734b138f5fc61f5652efbd_nemotron_2_256k.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dfd8b970f437002fc445214304969fe59e64d4f48500bd0b77ba55340f2d811
3
+ size 4545602
model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_22_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c833ecab87c2c11bb35635b69b2cfcb1c14b2c67777bfa2d5065e05351cb0fbe
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_26_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b86f7738144dd46ad4ffe4c912a086e12834afbbaebe129b22051ddbe796be2
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_27_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6357b4f12640ee695324cdc441d8d5cdc98fa00fb63d5591657e56973674326
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_35_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71fdf56e296aed9d8bfc5206799e1d1ac43f582d43ed30f515dbab40112ba258
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_44_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aa01a903b4d8af01de2b1ed6a74a5d108252523cd389187716cc17022da5719
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_47_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb26e8966eceaacdf7fccac7ff9047081b4cd8fe765e32957ff8cfe4480f9187
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_55_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:933b45a0255ffbf603631df86198c897aed451e359ea27c8dbab3a43ce6eb6eb
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_61_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1e75f5e6cf3b5158698777317233c81b32327d4d64a20bed579a68da3d8df85
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_65_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f5f205e847bf17a236c61ffd3265b0d4354037d5a4a5867c191f428eb89542c
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_70_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ba952db94faa05deee32656353d5863405c51b2db00d2765429a94e5176d4bd
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_73_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bce1ccfc4b24e9618b1ef50d816b3e6fb79f45b8b5eaeaf309ea1004bf9d620
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_76_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a619445c71978910406d1fd76c100b14a38375fd7051198c1226ac41b581dfc
3
+ size 1840
model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_7_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc81ecc1aa4cb51e01abc074e013df21f411e0036c1e63d587bfbd62f30ff52c
3
+ size 1836
model_weights/model.decoder.layers.mlp.linear_fc2._extra_state/shard_91_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01048ad3a21833fd1c3279d20e19d6190d5d695c68f738e3b6401bb8b6601ed3
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_weight/12.0 ADDED
Binary file (36.9 kB). View file
 
model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_weight/13.0 ADDED
Binary file (36.9 kB). View file
 
model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_weight/54.0 ADDED
Binary file (36.9 kB). View file
 
model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_weight/61.0 ADDED
Binary file (36.9 kB). View file
 
model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_weight/67.0 ADDED
Binary file (36.9 kB). View file
 
model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_weight/73.0 ADDED
Binary file (36.9 kB). View file
 
model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_weight/80.0 ADDED
Binary file (36.9 kB). View file
 
model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_weight/82.0 ADDED
Binary file (36.9 kB). View file
 
model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_weight/83.0 ADDED
Binary file (36.9 kB). View file
 
model_weights/model.decoder.layers.self_attention.linear_qkv.layer_norm_weight/93.0 ADDED
Binary file (36.9 kB). View file