Hugging Face's logo

nvidia
/
Nemotron-4-340B-Instruct

NeMo
Model card Files Community
12
okuchaiev commited on
Commit
44eaec7
•
1 Parent(s): a317464

Add files using large-upload tool

Browse files
Files changed (26) hide show
  1. .gitattributes +9 -0
  2. model_weights/model.decoder.layers.self_attention.linear_proj.weight/19.0.3 +3 -0
  3. model_weights/model.decoder.layers.self_attention.linear_proj.weight/38.0.3 +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_proj.weight/38.0.5 +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_proj.weight/51.0.0 +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_proj.weight/52.0.3 +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_proj.weight/57.0.2 +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_proj.weight/72.0.1 +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_proj.weight/72.0.4 +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_proj.weight/8.0.0 +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_0_96.pt +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_13_96.pt +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_16_96.pt +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_22_96.pt +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_23_96.pt +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_28_96.pt +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_34_96.pt +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_54_96.pt +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_57_96.pt +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_5_96.pt +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_65_96.pt +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_66_96.pt +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_72_96.pt +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_76_96.pt +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_7_96.pt +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_8_96.pt +3 -0
.gitattributes CHANGED
@@ -1534,3 +1534,12 @@ model_weights/model.decoder.layers.self_attention.linear_proj.weight/85.0.6 filt
1534
  model_weights/model.decoder.layers.self_attention.linear_proj.weight/86.0.5 filter=lfs diff=lfs merge=lfs -text
1535
  model_weights/model.decoder.layers.self_attention.linear_proj.weight/10.0.5 filter=lfs diff=lfs merge=lfs -text
1536
  model_weights/model.decoder.layers.self_attention.linear_proj.weight/71.0.2 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
1534
  model_weights/model.decoder.layers.self_attention.linear_proj.weight/86.0.5 filter=lfs diff=lfs merge=lfs -text
1535
  model_weights/model.decoder.layers.self_attention.linear_proj.weight/10.0.5 filter=lfs diff=lfs merge=lfs -text
1536
  model_weights/model.decoder.layers.self_attention.linear_proj.weight/71.0.2 filter=lfs diff=lfs merge=lfs -text
1537
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/38.0.3 filter=lfs diff=lfs merge=lfs -text
1538
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/8.0.0 filter=lfs diff=lfs merge=lfs -text
1539
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/19.0.3 filter=lfs diff=lfs merge=lfs -text
1540
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/72.0.1 filter=lfs diff=lfs merge=lfs -text
1541
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/57.0.2 filter=lfs diff=lfs merge=lfs -text
1542
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/51.0.0 filter=lfs diff=lfs merge=lfs -text
1543
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/72.0.4 filter=lfs diff=lfs merge=lfs -text
1544
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/52.0.3 filter=lfs diff=lfs merge=lfs -text
1545
+ model_weights/model.decoder.layers.self_attention.linear_proj.weight/38.0.5 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.self_attention.linear_proj.weight/19.0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd437c86422ffc1f363a4c85455c0ee8981a85b50154738d19724e98b0a1745e
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/38.0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4efe1cf12211c90a97a49306d4dc2634c8f32f31b1562abde1449b6a185dcc85
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/38.0.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebe7560362924cb099c15be421da7ef1fb138448bca10676b18bad45840f0f42
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/51.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3d93f6e2674fc9bd26021db24f20e7776c5ef127cee055005e9b776fe373cc6
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/52.0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27cedcc6b95ef3511fe86d5994f0b84a5c662136d89561b885dd32a2894c51c4
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/57.0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f26f11a798084f097be1f02b2e277b2260d42629678d6ef5151d68166df8504e
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/72.0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4734406280edcc054d32a08cc912b7698410e699ec76a6032363964e7e86a8c3
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/72.0.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07579aa165e09768b9fdaf48fad233ae55c37e904d4eece65ea40e28fb508aff
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_proj.weight/8.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d29e355a268db601f228120ed01929814cd9ea5a23e35fa3c07162d18176b3cf
3
+ size 84934656
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_0_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdc3d2b4de551828617fd47b96ac7c52e318644919c6e5971e59dd5af2e8eb76
3
+ size 1836
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_13_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57570292febf0a0a75c54006bef3d68391031abad1dca4dd3a589d78f4633aa0
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._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.self_attention.linear_qkv._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.self_attention.linear_qkv._extra_state/shard_23_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86d70087fe5bd0019d9847df5a138621415c0f577e4aa73ffa746494c0a51c33
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._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.self_attention.linear_qkv._extra_state/shard_34_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d91f28f0611694f24e05103be174094e61828d3965d93218f534e54088c98474
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_54_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8863123f96f55dd3b4087785be202cb5ff411f5c651d8ac8e0442c34e7c35437
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._extra_state/shard_57_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7f4da70f660e067b374328723d75babc567a6cd4a3a1f223d73775e6c89b800
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._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.self_attention.linear_qkv._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.self_attention.linear_qkv._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.self_attention.linear_qkv._extra_state/shard_72_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce281fff94d3e8b57565271ccec2ee98d6e8f6ce97f487d6c4d83859db078079
3
+ size 1840
model_weights/model.decoder.layers.self_attention.linear_qkv._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.self_attention.linear_qkv._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.self_attention.linear_qkv._extra_state/shard_8_96.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79b05b5e7449cacc1b575cb6f9a5a09f210e53f64d2764a59ae613b6629c466c
3
+ size 1836