Hugging Face's logo

nvidia
/
Nemotron-4-340B-Base

NeMo
nvidia
Model card Files Community
7
jiaqiz commited on
Commit
529a603
·
verified ·
1 Parent(s): 68807a3

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/1.4.0 +3 -0
  3. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/11.7.0 +3 -0
  4. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/12.3.0 +3 -0
  5. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/12.7.0 +3 -0
  6. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.7.0 +3 -0
  7. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/17.3.0 +3 -0
  8. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/18.5.0 +3 -0
  9. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/24.3.0 +3 -0
  10. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/34.7.0 +3 -0
  11. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/36.7.0 +3 -0
  12. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/44.4.0 +3 -0
  13. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/47.5.0 +3 -0
  14. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/47.7.0 +3 -0
  15. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.3.0 +3 -0
  16. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/53.4.0 +3 -0
  17. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/58.6.0 +3 -0
  18. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/64.5.0 +3 -0
  19. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.5.0 +3 -0
  20. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.6.0 +3 -0
  21. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/70.5.0 +3 -0
  22. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/71.7.0 +3 -0
  23. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/75.3.0 +3 -0
  24. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/85.6.0 +3 -0
  25. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/88.0.0 +3 -0
  26. model_weights/model.decoder.layers.self_attention.linear_qkv.weight/90.3.0 +3 -0
.gitattributes CHANGED
@@ -1333,3 +1333,28 @@ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.1.0 filte
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
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
1336
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.7.0 filter=lfs diff=lfs merge=lfs -text
1337
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/70.5.0 filter=lfs diff=lfs merge=lfs -text
1338
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/88.0.0 filter=lfs diff=lfs merge=lfs -text
1339
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/44.4.0 filter=lfs diff=lfs merge=lfs -text
1340
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/47.7.0 filter=lfs diff=lfs merge=lfs -text
1341
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/47.5.0 filter=lfs diff=lfs merge=lfs -text
1342
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/1.4.0 filter=lfs diff=lfs merge=lfs -text
1343
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/53.4.0 filter=lfs diff=lfs merge=lfs -text
1344
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/85.6.0 filter=lfs diff=lfs merge=lfs -text
1345
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.3.0 filter=lfs diff=lfs merge=lfs -text
1346
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/71.7.0 filter=lfs diff=lfs merge=lfs -text
1347
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.5.0 filter=lfs diff=lfs merge=lfs -text
1348
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/58.6.0 filter=lfs diff=lfs merge=lfs -text
1349
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/18.5.0 filter=lfs diff=lfs merge=lfs -text
1350
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/24.3.0 filter=lfs diff=lfs merge=lfs -text
1351
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/12.7.0 filter=lfs diff=lfs merge=lfs -text
1352
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/90.3.0 filter=lfs diff=lfs merge=lfs -text
1353
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/75.3.0 filter=lfs diff=lfs merge=lfs -text
1354
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/34.7.0 filter=lfs diff=lfs merge=lfs -text
1355
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.6.0 filter=lfs diff=lfs merge=lfs -text
1356
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/11.7.0 filter=lfs diff=lfs merge=lfs -text
1357
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/17.3.0 filter=lfs diff=lfs merge=lfs -text
1358
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/64.5.0 filter=lfs diff=lfs merge=lfs -text
1359
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/36.7.0 filter=lfs diff=lfs merge=lfs -text
1360
+ model_weights/model.decoder.layers.self_attention.linear_qkv.weight/12.3.0 filter=lfs diff=lfs merge=lfs -text
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/1.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fe0f7aa8cf8551473310731dc487f67ecf22cfd7634c6274e5da1d85f722d2a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/11.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9418d822734d57d2d80665a98af3954ef965275940c71f7a041cb3b91d718fa
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/12.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:634d5b70dd8ca3cf4e8197d0249c96390c9281b67d43054d9e748a04f37edf14
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/12.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35dfbe2e3a11d70655dff6633069e2b592ffbb91078235b0cc4311ad24dac7d3
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/13.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a758bfaa40c1c84cb2bc4d2cd2543733569245bfbd4ff0e6a89c574acffb1e0f
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/17.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f21d2f09c96a142a2d2c1685b0dfa3144f31103e23c9f6bf36b4a35c51d6637
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/18.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:434b079b8fb1b68d400fb4bb9cfea1ff7ec30a7752dc157120835af0f283a603
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/24.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9ba044f6b3f788c6649f2db395a93e38ccc37c161a27ac7e627f5951d478ef5
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/34.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b541b0d23d068a21a5ca76f8d02cfb21a7001f7b879ad1f8d57cfea1b15d1fac
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/36.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:334c3840d2a5da8785fdfbcdbc7b006b6d91707050a0e1f7aef3c3ae2c5cbc3f
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/44.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7da72b31762c3f93f5435a534fb643a205749e1e98dc8039c7bc647a732fc6a4
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/47.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ec91f01598a7683821f46c6cc69b851f7370f45c432a30a441426ce1a3af6ef
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/47.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bc1fe09ab5f4e7cfa67d90a0733e3dbd2c8ed189116052d12c1f0dbd3d4227a
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/50.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce387701dc4bbf4675d7e92664a3613f967143c680e369d4f3d9ce907d570faf
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/53.4.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c0a7ac0c6e4922e534743557fe6717e1d77660ce54f6dc830cf8b9c3fe44c84
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/58.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f3394159a1e8e58f503bece304dfaa7b1f52b648936168bbdbd75a5c0cd3730
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/64.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdd936b336bae710e8f4f1e753e7ae728554b29dd3f559df3e395eadf783ea12
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bb6d3d749e25e420d73121b93848194fae4ad5ddd6e5ad61226d2a5cba0e0a1
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/66.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:699441703f29ba4203c6aa5333af0c8251f378f56268ff033403062dcf670180
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/70.5.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cbf8fecee60c2a4b498bd3e2ef75b502f9c12633d5aa95d87143a3b501bfdc8
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/71.7.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:289e09d773374e4a99996e5a45d1191afba9dcdec22ec177768dbb5fd185a01f
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/75.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6e7f5625ce8ba8ee9c975553df1d0487a9fc71550ef896257f8a5f9cc6c58ff
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/85.6.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57c183d62725dfa67514d739e58556c14c5fd8a0704957b0778ecba7080565de
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/88.0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1d12b4c12e48e13497b722c414a83e539d0fef327b199d5be8e0d11561a3264
3
+ size 99090432
model_weights/model.decoder.layers.self_attention.linear_qkv.weight/90.3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c03769137174426b4d20c8ff0f7889d58ba4dda7f97c6f97c7a70d2c522a01d9
3
+ size 99090432