Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
6
jiaqiz commited on
Commit
8e2f546
•
1 Parent(s): 3ac977d

Add files using large-upload tool

Browse files
Files changed (26) hide show
  1. .gitattributes +25 -0
  2. model_weights/model.decoder.layers.mlp.linear_fc2.weight/28.0.2 +3 -0
  3. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/14.3.0 +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/16.3.0 +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/16.5.0 +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/17.7.0 +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/23.7.0 +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/26.0.0 +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/36.1.0 +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/39.7.0 +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/41.2.0 +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/44.6.0 +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/45.5.0 +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/45.6.0 +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/47.3.0 +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.5.0 +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.7.0 +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.0.0 +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/62.7.0 +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/65.2.0 +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/65.7.0 +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.3.0 +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/77.5.0 +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/81.4.0 +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/87.1.0 +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/91.4.0 +3 -0
.gitattributes CHANGED
@@ -1183,3 +1183,28 @@ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/84.4.0 filte
1183
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/81.2.0 filter=lfs diff=lfs merge=lfs -text
1184
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/1.2.0 filter=lfs diff=lfs merge=lfs -text
1185
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/21.2.0 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1183
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/81.2.0 filter=lfs diff=lfs merge=lfs -text
1184
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/1.2.0 filter=lfs diff=lfs merge=lfs -text
1185
  model_weights/model.decoder.layers.self_attention.linear_qkv.weight/21.2.0 filter=lfs diff=lfs merge=lfs -text
1186
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/47.3.0 filter=lfs diff=lfs merge=lfs -text
1187
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/45.5.0 filter=lfs diff=lfs merge=lfs -text
1188
+ model_weights/model.decoder.layers.mlp.linear_fc2.weight/28.0.2 filter=lfs diff=lfs merge=lfs -text
1189
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/16.5.0 filter=lfs diff=lfs merge=lfs -text
1190
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/16.3.0 filter=lfs diff=lfs merge=lfs -text
1191
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.0.0 filter=lfs diff=lfs merge=lfs -text
1192
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.5.0 filter=lfs diff=lfs merge=lfs -text
1193
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/65.7.0 filter=lfs diff=lfs merge=lfs -text
1194
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/41.2.0 filter=lfs diff=lfs merge=lfs -text
1195
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/17.7.0 filter=lfs diff=lfs merge=lfs -text
1196
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/91.4.0 filter=lfs diff=lfs merge=lfs -text
1197
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/44.6.0 filter=lfs diff=lfs merge=lfs -text
1198
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/36.1.0 filter=lfs diff=lfs merge=lfs -text
1199
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.3.0 filter=lfs diff=lfs merge=lfs -text
1200
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/65.2.0 filter=lfs diff=lfs merge=lfs -text
1201
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/26.0.0 filter=lfs diff=lfs merge=lfs -text
1202
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/77.5.0 filter=lfs diff=lfs merge=lfs -text
1203
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/23.7.0 filter=lfs diff=lfs merge=lfs -text
1204
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/81.4.0 filter=lfs diff=lfs merge=lfs -text
1205
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.7.0 filter=lfs diff=lfs merge=lfs -text
1206
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/14.3.0 filter=lfs diff=lfs merge=lfs -text
1207
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/45.6.0 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
model_weights/model.decoder.layers.mlp.linear_fc2.weight/28.0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb0f47484d8a036a0ab5aed58e7f2881cda25b0d6ca78414e823c05fbaf899ba
3
+ size 339738624
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/14.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4849a1bbd00b0f176589e84077f8530bbdc02bfb9984a468f12944cc22d40ea7
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/16.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26c6bc3a4f27cb95cc6ba2c7be537323a6f5f4ae94b7dea07ee131ffee39826c
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/16.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d1e96dfcbc7a90830f599976b38d09bd65670486bde11dc5317edcf356020ea
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/17.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74681a9e9129ca174b904a453acb8619cc8cc67d88309e3f6ae6f0cd1a201a7b
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/23.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da4002fb94db38871b48753e283225889ce46f73a954e2f0bb5e1b812be34184
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/26.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:594dcaf62babf76bcc53540c6ef622431d5c0a1681051b9c2d66a5420e15bead
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/36.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca43cf93aa7ba32e9e69debe8e91bfa5984e6c63810c6cfdb47afca5277ab36b
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/39.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71c83e856ee4e42d17a12475660747c4ba6ac6e26c16f3f74cd920f7bacd258a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/41.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5fc6f6f4e498e2b251c502ed8e186e01c94696074afe9f2904bee447f269de0
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/44.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ebca425c1805dedea464fcf8e0a6ae3b0b4ca38c8353ae3e45f548eb6239d4a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/45.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27913cc850754be87cd82c13ef926f0a70fa5d58b4f6419e2e372e13d06d3e27
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/45.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18feff007adb7dc493d2d13edb72e77859087b7b0b386b2588f4609681642e97
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/47.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:324755c13ce2d6b2702053f71d381cb85f68d631b05275c1aaa32a9dff40bb1b
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15b9ac0660987450ff7d0fd2ad66c0cc208b6440d1fbac6bc4f6b667a677ddd6
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deec8fe5411abfa39c93bbe1dc2eb143179362b0739ab76e82c1dc2421f00d5c
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/55.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d495ca2bacd27ce2c346ce603de7f070934b3f9287195f102cdf03e32e4e2cf1
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/62.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfaff7767687b2adca128a5896411359cd8b506c9b4f59c91d11de23d6aa58cc
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/65.2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ebc1014b1416a9274fa34dd917c08fbc8226b1d03e6a1ce90ab80c21b8d350
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/65.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c20dd4a343f4ee19d8f8227405a52931548ab38e9f9b4c81b4e83e893fafd11e
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27952082cf003b2cd920ef008467cf3427cefc353a7dc1c0f26022b1c119780b
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/77.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:038e00eda96e5072a5c5f21b25dcabda7e41972e25e819f22866a1278e471025
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/81.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0434bf616f73f3faa4d29bdb8761409fc54ed2df2196ddd2197552c6840eeab
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/87.1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db00f22675515e269168caacbff16bb493c6bd93e8f39acbea6afe9c73af6a19
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/91.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0905906ded5e62a90066db5217ab259df39f4c3095c29fabf89c56c9e892e5fe
3
+ size 99090432