Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
7
jiaqiz commited on
Commit
68807a3
•
1 Parent(s): 603b69e

Add files using large-upload tool

Browse files
Files changed (26) hide show
  1. .gitattributes +25 -0
  2. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.5.0 +3 -0
  3. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/16.4.0 +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/18.1.0 +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/24.0.0 +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/26.7.0 +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/30.7.0 +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/33.7.0 +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/41.4.0 +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/42.3.0 +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/44.5.0 +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.1.0 +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/56.4.0 +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/59.3.0 +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/61.4.0 +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/64.6.0 +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/68.1.0 +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/69.5.0 +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/73.7.0 +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/74.7.0 +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.1.0 +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/86.5.0 +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/86.6.0 +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/86.7.0 +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/9.3.0 +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/90.6.0 +3 -0
.gitattributes CHANGED
@@ -1308,3 +1308,28 @@ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.4.0 filte
1308
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/54.6.0 filter=lfs diff=lfs merge=lfs -text
1309
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/71.1.0 filter=lfs diff=lfs merge=lfs -text
1310
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/36.2.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1308
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/54.6.0 filter=lfs diff=lfs merge=lfs -text
1309
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/71.1.0 filter=lfs diff=lfs merge=lfs -text
1310
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/36.2.0 filter=lfs diff=lfs merge=lfs -text
1311
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/64.6.0 filter=lfs diff=lfs merge=lfs -text
1312
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/18.1.0 filter=lfs diff=lfs merge=lfs -text
1313
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/73.7.0 filter=lfs diff=lfs merge=lfs -text
1314
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/56.4.0 filter=lfs diff=lfs merge=lfs -text
1315
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/41.4.0 filter=lfs diff=lfs merge=lfs -text
1316
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/86.5.0 filter=lfs diff=lfs merge=lfs -text
1317
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/74.7.0 filter=lfs diff=lfs merge=lfs -text
1318
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/16.4.0 filter=lfs diff=lfs merge=lfs -text
1319
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/59.3.0 filter=lfs diff=lfs merge=lfs -text
1320
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/61.4.0 filter=lfs diff=lfs merge=lfs -text
1321
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/44.5.0 filter=lfs diff=lfs merge=lfs -text
1322
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/90.6.0 filter=lfs diff=lfs merge=lfs -text
1323
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/30.7.0 filter=lfs diff=lfs merge=lfs -text
1324
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.1.0 filter=lfs diff=lfs merge=lfs -text
1325
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/42.3.0 filter=lfs diff=lfs merge=lfs -text
1326
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/86.7.0 filter=lfs diff=lfs merge=lfs -text
1327
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/69.5.0 filter=lfs diff=lfs merge=lfs -text
1328
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/26.7.0 filter=lfs diff=lfs merge=lfs -text
1329
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/9.3.0 filter=lfs diff=lfs merge=lfs -text
1330
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.5.0 filter=lfs diff=lfs merge=lfs -text
1331
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/86.6.0 filter=lfs diff=lfs merge=lfs -text
1332
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.1.0 filter=lfs diff=lfs merge=lfs -text
1333
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/24.0.0 filter=lfs diff=lfs merge=lfs -text
1334
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/33.7.0 filter=lfs diff=lfs merge=lfs -text
1335
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/68.1.0 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2265134fe71b8428e05b62f21eac219c7fcf8254411d303851989e3790214d1
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/16.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cf4b7fb6db5f8dee506c6d312230832eafe655938affc46b066c0da29709faa
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/18.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6b7d44ae2697d0861af8653013a1adc1f773115e4c9918e5d77cc210a2994ef
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/24.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f85115de58246e9845ddc5c8eb185aef81f95fbebd48673b00a8e6897fec11f
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/26.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb40e291d9a7725415210d36fadcfc039d15682e0c4e0c4f9e0b2a129eec6d3c
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/30.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec9f9711994983af09a6ebfe1725eee9141a70fda98b7e406ab96cd83b6737b2
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/33.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79a22f6d54f3195484949c3b1605a9880e3145506c35eeea5ca378a0271c3dc6
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/41.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40bb3607e54d0245541e7dd88e6c656df8b55d53bd0b5fa3fa40bc4e32a2f4de
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/42.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:234b0b04bd0bd00df60c7801f389ade00e838a45d79459c8ebe3bf2f698becd3
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/44.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a046069ab0286893e5e5c30c280a9768654d533580a9d7aa2d527f76f4752ea1
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32959c54a519db0b6d2ee4f04495806a28e88c87823693912e732845766568d5
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/56.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b443441962bd092d016feed4710d8cbe465c590aadca78dbc4198c20ecf0160
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/59.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e533755df46fb5a6801c25ad1767b6cc9fb246600d6e5c63d1d5b3fe827b2a50
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/61.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae6427b6aaf14f0fa1b3e35429d236cafd7ba52b58f9844f1fb6c7b7ffd43549
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/64.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f841ec331d7f9d7c0bc032e107addddf7cf84e4890b9a31180472cee63e7072
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/68.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14147e6799f497e71685b81798e49eb395cb10cbc6e33f97316bd7ce93b1da07
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/69.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e499b3958a52a88cb644649235bae3c9b930afb596e25d688d07be49440d4ae9
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/73.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9390c9be0b28dc5074dbd94cbc2edbdaadadeea95a248355140756d2c5e9ced1
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/74.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d41b648b374d02a90f382178d3de19e2294074860903f14e6ec973b1efab061c
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdf567bede8a0ddada25ff11e23cf08567fde074a373e30a85230f3b280c908a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/86.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65b6dc96b78b0a24762f801c0edb2f7dbffea554bfdc72fc7fee59b070f1ad4c
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/86.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8aff6b544f1f61bda2ff46a9b000b6897a98777a6d5e42ea1b845dc56b4efcc
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/86.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1faac54b789512b6f632ebb26e978edfcae7cad3f65944045bd47dd1698834e1
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/9.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed881c9bd03901c8ad319df409bbe60704873c0a264aef0afac8340346234143
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/90.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02e2dc2cdafc8d59fecd524a7d90da8ff06659035957daca46beec3456f672a6
3
+ size 99090432