Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
7
jiaqiz commited on
Commit
cf3ad27
·
verified ·
1 Parent(s): 8e2f546

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/13.6.0 +3 -0
  3. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/14.4.0 +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/19.3.0 +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/20.3.0 +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/34.1.0 +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/37.7.0 +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/42.6.0 +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/49.2.0 +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/5.1.0 +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.2.0 +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/57.4.0 +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/59.5.0 +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/6.7.0 +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/64.1.0 +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/7.3.0 +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/73.4.0 +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/77.7.0 +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.0.0 +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.4.0 +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/86.1.0 +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/86.4.0 +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/89.5.0 +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/90.0.0 +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/93.5.0 +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/93.6.0 +3 -0
.gitattributes CHANGED
@@ -1208,3 +1208,28 @@ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/45.6.0 filte
1208
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/87.1.0 filter=lfs diff=lfs merge=lfs -text
1209
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/62.7.0 filter=lfs diff=lfs merge=lfs -text
1210
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/39.7.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1208
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/87.1.0 filter=lfs diff=lfs merge=lfs -text
1209
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/62.7.0 filter=lfs diff=lfs merge=lfs -text
1210
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/39.7.0 filter=lfs diff=lfs merge=lfs -text
1211
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/90.0.0 filter=lfs diff=lfs merge=lfs -text
1212
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/77.7.0 filter=lfs diff=lfs merge=lfs -text
1213
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/6.7.0 filter=lfs diff=lfs merge=lfs -text
1214
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/64.1.0 filter=lfs diff=lfs merge=lfs -text
1215
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.4.0 filter=lfs diff=lfs merge=lfs -text
1216
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.0.0 filter=lfs diff=lfs merge=lfs -text
1217
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/49.2.0 filter=lfs diff=lfs merge=lfs -text
1218
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.2.0 filter=lfs diff=lfs merge=lfs -text
1219
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/86.1.0 filter=lfs diff=lfs merge=lfs -text
1220
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/19.3.0 filter=lfs diff=lfs merge=lfs -text
1221
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/14.4.0 filter=lfs diff=lfs merge=lfs -text
1222
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/42.6.0 filter=lfs diff=lfs merge=lfs -text
1223
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.6.0 filter=lfs diff=lfs merge=lfs -text
1224
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/34.1.0 filter=lfs diff=lfs merge=lfs -text
1225
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/7.3.0 filter=lfs diff=lfs merge=lfs -text
1226
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/86.4.0 filter=lfs diff=lfs merge=lfs -text
1227
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/37.7.0 filter=lfs diff=lfs merge=lfs -text
1228
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/89.5.0 filter=lfs diff=lfs merge=lfs -text
1229
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/59.5.0 filter=lfs diff=lfs merge=lfs -text
1230
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/93.5.0 filter=lfs diff=lfs merge=lfs -text
1231
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/20.3.0 filter=lfs diff=lfs merge=lfs -text
1232
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/5.1.0 filter=lfs diff=lfs merge=lfs -text
1233
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/73.4.0 filter=lfs diff=lfs merge=lfs -text
1234
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/93.6.0 filter=lfs diff=lfs merge=lfs -text
1235
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/57.4.0 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f41dd1c0ebccea07b15fa7427d1805763e39bfd9bd4390d23d26b08fe5e50922
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/14.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95bd24a487eabf827f7d3a6429e7d25c272a07f8442c4e25e7a1c441a3bc8ce2
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/19.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87493fef961ab82fc3f0e3da8c9c1b10ecc96ebae9e81b3fb575316f865deaea
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/20.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:661e0e2000139e05a17d59107fb47c43f08b9c136d7c2ea1d0a552714ec272f5
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/34.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60e70516393fcc88cd4ed8872659f7a15a736cd8dd104292fe7d7f1c8863c8bd
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/37.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98977698151e847f001c3afbaabb1e97877f8536bdf2f5c0fffd0e804b144e19
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/42.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb1b0b30589e51a383777bd5ec7453682433eee027053ac3ed943834a9a47294
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/49.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e0e312e2803fe9ab82cc76355e09a341f5a6e7d68c0d1c226d82df50c679d0f
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/5.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25d81ebec693eed8d60e543531af575e97259ced0ac0524231143387227eb510
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999d6923e06dfba5a755f5c906b8ed9ac382248ecce6c44924dcc51f4561180a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/57.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:355399fec297827098ab22538027c6b6aa4a3c6bb177d6f1dab2ea48dd9077c7
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/59.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a62fa1a35f01e3c3d4069b1298ff12ea81136d6dc92ea209a0a6fe35b215e9d
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/6.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ab8a901ee1a0dc43cb96da1079b11d6f7dab076018886d9fb03e02bb967219f
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/64.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7e4c9705ea11c98fc3af48f871ec6529eeeacbad2310ca67b1edafda56f5464
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/7.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ca4ad8f025e02d2ded5fcaac6e34baeb51149f5512ecbbf84c1552de73ec2b9
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/73.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:306487e21869fe14e43c7de0881bff45b2c6414c826ab55f4fab0717a3289a88
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/77.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1db390e09ea381e1de8ed6d15b7bd742fa0979d73690041dcd6be9848f0e73d4
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86cdb9b90f80a780aaf2ffff13b8ca6850fd9659438a258c903f1e0b0c192deb
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/79.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba31fb78fbe34c36b510048dd7cdca170fe0950108398493c4a59e96ac3df30c
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/86.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4fd21c279b4c315cd6a99e6b4a340703aaec89116353126a7473cf20bb278b6
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/86.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99c120642cdde0043d7c30e39ec90c6d1018501823dd5bb62123433491b7d3a6
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/89.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c960d016e44213494625e4f13fae5d630a61ee9a5382d2aa092abc4be02048b3
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/90.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34c40f6e8129d24e60e769fed210e97bc4aedbc999591170111e8fdab4fc42c0
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/93.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b477b52564c63ce2559d93698d70cb78b5307c3d000a5d7cf39fc44627b54e0
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/93.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd39aeaeca84254a67d5c4a532e2bc2200f7a0afb524d6171ca29a3051a7fb9a
3
+ size 99090432