danielhanchen commited on
Commit
0b5bb32
·
verified ·
1 Parent(s): 30dbd6b

Upload folder using huggingface_hub

Browse files
Files changed (49) hide show
  1. model-00002-of-00050.safetensors +2 -2
  2. model-00003-of-00050.safetensors +2 -2
  3. model-00004-of-00050.safetensors +2 -2
  4. model-00005-of-00050.safetensors +2 -2
  5. model-00006-of-00050.safetensors +2 -2
  6. model-00007-of-00050.safetensors +2 -2
  7. model-00008-of-00050.safetensors +2 -2
  8. model-00009-of-00050.safetensors +2 -2
  9. model-00010-of-00050.safetensors +2 -2
  10. model-00011-of-00050.safetensors +2 -2
  11. model-00012-of-00050.safetensors +2 -2
  12. model-00013-of-00050.safetensors +2 -2
  13. model-00014-of-00050.safetensors +2 -2
  14. model-00015-of-00050.safetensors +2 -2
  15. model-00016-of-00050.safetensors +2 -2
  16. model-00017-of-00050.safetensors +2 -2
  17. model-00018-of-00050.safetensors +2 -2
  18. model-00019-of-00050.safetensors +2 -2
  19. model-00020-of-00050.safetensors +2 -2
  20. model-00021-of-00050.safetensors +2 -2
  21. model-00022-of-00050.safetensors +2 -2
  22. model-00023-of-00050.safetensors +2 -2
  23. model-00024-of-00050.safetensors +2 -2
  24. model-00025-of-00050.safetensors +2 -2
  25. model-00026-of-00050.safetensors +2 -2
  26. model-00027-of-00050.safetensors +2 -2
  27. model-00028-of-00050.safetensors +2 -2
  28. model-00029-of-00050.safetensors +2 -2
  29. model-00030-of-00050.safetensors +2 -2
  30. model-00031-of-00050.safetensors +2 -2
  31. model-00032-of-00050.safetensors +2 -2
  32. model-00033-of-00050.safetensors +2 -2
  33. model-00034-of-00050.safetensors +2 -2
  34. model-00035-of-00050.safetensors +2 -2
  35. model-00036-of-00050.safetensors +2 -2
  36. model-00037-of-00050.safetensors +2 -2
  37. model-00038-of-00050.safetensors +2 -2
  38. model-00039-of-00050.safetensors +2 -2
  39. model-00040-of-00050.safetensors +2 -2
  40. model-00041-of-00050.safetensors +2 -2
  41. model-00042-of-00050.safetensors +2 -2
  42. model-00043-of-00050.safetensors +2 -2
  43. model-00044-of-00050.safetensors +2 -2
  44. model-00045-of-00050.safetensors +2 -2
  45. model-00046-of-00050.safetensors +2 -2
  46. model-00047-of-00050.safetensors +2 -2
  47. model-00048-of-00050.safetensors +2 -2
  48. model-00049-of-00050.safetensors +2 -2
  49. model.safetensors.index.json +96 -48
model-00002-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1620ca141f702a2e68ef37633d4729d35cce2260bbd36afd3e1c86993e7bd1c7
3
- size 4404205232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09509d0af7d03730bd5ca28be08dc394c1d9830d9023789f0a39cc821b963139
3
+ size 4404205368
model-00003-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bd3989a0520b2ec9a90ceb088a9fb5674ae2cda0cd542bf612f2c973da2491e
3
- size 4404205232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fac079433a6baa44d556154612c3e4f448741c91bdf220dab5b9deb20e0716e1
3
+ size 4404205368
model-00004-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab90e5bf7d202046aa601d1c00ef76983e5f602e04fe0e6eca05357b6f236974
3
- size 4404205232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77e381ee7fae3c6454660276c7c7af3b5075d8a48bafa0404b93a96626feef68
3
+ size 4404205368
model-00005-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:643b34dd6e4b8baf81cce268b2226144cef7e8959e4ba6c5238a0d519b94ab51
3
- size 4404205232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc60f2bca3ef6285f8ab645f7a901085961e3822bb86b25d22015d3eed24323c
3
+ size 4404205368
model-00006-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06f9142c2b67d889dc0521d949f144b40b336bb9776e3465549ab2c55355c608
3
- size 4404205232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:239a1a0176db813744c70efbeb85fe7a08829c804d8f33b86aefe8d764e820e0
3
+ size 4404205368
model-00007-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7f64071b2de9eb18fd3a919dc29c38fdf46804a17b709fbba2a5dcd65a149be
3
- size 4404205232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c1668cecfcaf76be50af40fbfacad6bad4d1cb79be55821b38b9c91b86b7357
3
+ size 4404205368
model-00008-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c086781091a3993921dfd483e19fdb5c8ce4375036858d090775ce754662786
3
- size 4404205232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e7000e335da03fb24eb853d984015d1a3d9aac7ecc54484c0b6e1371a311b75
3
+ size 4404205368
model-00009-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d0ae4554ce11ae48d6cab356e475289b8b37084c9031f84d0a35e585425a3b0
3
- size 4404205232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3030d3095522d3be3e8c41eb0858d930d8e825d87c9e783136a4557f35eb1d1a
3
+ size 4404205368
model-00010-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1eadd6cdf16d6a94b524b86247be1b85666b720fb1e3c6ea7a69c664c52b7853
3
- size 4404205232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56f53a5bf45fe155867d1ee1aa3e81e7749b753c4065e3c568b83158fbd5ea3f
3
+ size 4404205368
model-00011-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6029da11492f4a2a39696b1ca54fddb12b163496ae9fd069a388086372cb5053
3
- size 4404205224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c35653f70df260eecbccb056a743d4884dbf0d6c3009ce32d215f2c2548b626
3
+ size 4404205360
model-00012-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea25383e6a2b3535d44ac895c29c55fb0bd3cfbcdf50de1cb897e6c8acc39943
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c880d1a5de15d4baf256d0c9df761350dcc4a759b7676838b02e65736e805972
3
+ size 4404205384
model-00013-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd805fea2e9d91719d1e98590789b34a627326e923a48d31e29708336176a103
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a224f5d11e29739d69129c2bbc8bff10bc95def02e53a15b2b3cb90f335ad8e
3
+ size 4404205384
model-00014-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ca29a337d0c37484248855d8b360e044122a07c4b87cf7a2cf742e2deed4b42
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a6e957e715d70be76e00fc52210c761dad2371b9028f09b7ad402ca5be5b973
3
+ size 4404205384
model-00015-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a77be93a61e20a2776379c1eed42af70790b6db6c973f44894bb116232f2e7a
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a02ef72ad8f9fa83811daa753d351a63315386335d5f6fe8e2a3d73bea05ee5
3
+ size 4404205384
model-00016-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06f2c24f9f9786a2219d39679c2887812d299ae5b95746425d87816ecb6ac31a
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b63f8c1ef3b79aee68e956d79937076055802458ae9359296266472e3f4cc09f
3
+ size 4404205384
model-00017-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bdaad6fcdf15eefa845d7e5894cff93252df33b3555fba1878f6f5e282bf17c3
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30596825ff671155c8ccf58030e8506d3dcd2526d32fb6110b072b0c7f309834
3
+ size 4404205384
model-00018-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df3d569aa8d29b947c4fff4c159767a922b4138e06f8830baa24be1210c6819d
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca2dd2c45e09e53f811f4636d65dd014628257577df36548d3c20e969c682672
3
+ size 4404205384
model-00019-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca6ff34ba809cd91bf2cd13927c8a21aefe83a41d17e47947b90a55551a3aff2
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6393d51ce06cc94ad668916ef2d92936b56509a238a447a1e838ca3275d9d45c
3
+ size 4404205384
model-00020-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a128fb2b9337b4a6d17179ea26a7946f7fa7711954eb959a87ecab01c77599f9
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:052c18acc2ade73a404b2acaf37818922a06f53cb36311c2b42c9fca3102e31d
3
+ size 4404205384
model-00021-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d375d9f0dda615b5b5f73c0ef596dc6adaec35608c744cdc91dbf31767ab8f38
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ce78ef320f5b715c91e3cba0f55e62360a38f4688048ada159f791d581d3229
3
+ size 4404205384
model-00022-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71f5e1260dd3836d92e21ca01b3398b8ee2e1a5ad282c1a6f1c1675f6dfe2ac4
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bd9b1740cf759bebc18bcf58a455805ac8087df7376bf9fad3f6add5bc73f94
3
+ size 4404205384
model-00023-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f827e303340cbea2f6508249cde0142b9eb25bb62e0357c0ee210edeea149a71
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ffb65918a8d7bb09fb14b5533aabc317911f857d352d7b5f832e1e1942e0258
3
+ size 4404205384
model-00024-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4320ed5a8c10b4cae730673d4b47eb1c2ee3b0242531b632a910d0425319372f
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2365b7d91754a9f724f3e0e28561832d0fe8e87d202e4301a42470b03bf437bd
3
+ size 4404205384
model-00025-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:527d5e68d2a657dd9e0299ac8a037ee7501721ca8dfdfc188f69a2017856ad1d
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:028fcacf73b60b5d2fadaa97c4cc04f692a97e3e05ff4637d3c0c5b4f3f4bf28
3
+ size 4404205384
model-00026-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca932b15ff1afeafc8e86cdd79c3bd04041c3a1d9bfcd4355f04dc1e7a78a1c7
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8aba77d76e0419fa00efba741f920c1bab287396bfb534cf87861978e94f7773
3
+ size 4404205384
model-00027-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be126c3c8b97528c72367b1642a33f7aafee7687d05b8f77448a7bf97df84e71
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7b18333dd26101550d598cb82604d0e5cefd4e4b3db80010ecb36ee42cf8446
3
+ size 4404205384
model-00028-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1b881ef8cdf2d0fe96d3df2b5ca510795aaffdd5f954a12d441264039d12d3e
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f29b9303fe6e6dc18db2f062b1ade98afe3354bb7fcc761a3d50f361a4304ef
3
+ size 4404205384
model-00029-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05486b768dfb44a5d7f9a01026198d117cebad9cebf336837caa8e8a1de1c70f
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eecc1f3507d0238144bbf9e422d2b39ed0c3664c288a051e9e5edf0880b6758
3
+ size 4404205384
model-00030-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a02d69a935e1aa876622784ec22255c08d536c1de6289f84e7cd5aef47317082
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:468843b2c89c2fad3367aeda123325e5b833edf00f96bbfa13daf5942ba94130
3
+ size 4404205384
model-00031-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5cef3ffcf58552d223aa6c8713a17edd9890960a3048c2d12d3e7fefab49e5d
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05b60f9d47eb998f74dc4d5dad22a0a7cc37defab7ca8f1ddcccd622812bb780
3
+ size 4404205384
model-00032-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00d61b63d2c1e2e99cbd448a5d359dc1987bb13df3e7cf9a4b86e9abbecd3566
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76ca5397f76117406dbc3ee13728be63bd54488244ec698805664ab9620b02d
3
+ size 4404205384
model-00033-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cb8c1cfd5c0a15ae5327e7148c2ab49cacf98120e73069c63ba6028600facff
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e1b85384bafb5ac4d6d86f95930e53e5c9397855ef23faa1660868fdaffb867
3
+ size 4404205384
model-00034-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1ca2fdc1ab3ce2df5491e5a0d592c93464a9733d33b5588fc0ff83f8cc5ca96
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30e321a8ceeeac1898748f5601a4e03a2ea7f70df8bb5fbda18228d82330c6fe
3
+ size 4404205384
model-00035-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56a6baf7ea2756ed7c5ce67971d2c256964cdcda8ea755ee2438bb9e70dab399
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc5c2fc29711ce64a0a2ac39c31e119f944de5fd8d4a44e6b4267dda26cc87f2
3
+ size 4404205384
model-00036-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa6f53a0c4103b34bef7f3172f964d16fa6e8395ac3c2638c0cf80b9acf8b39e
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4d91c6f64690550ac069265154ff027772b264d01c7520c43daa049b962a0f5
3
+ size 4404205384
model-00037-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:373007bd9a116d624c1ffc7dc520ba8b51c8e69b9b72cb755470a35da0da304e
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a826ff515fd69d0de1797d306e269d785074d2a0b4cbbb652b8fc2418a3625f2
3
+ size 4404205384
model-00038-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68900f8238c8eee799d38aaec6e61e5fb1e9f9c97d78684acfc9f2a2118e81de
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67c1897f40a475c31e535939782f815d7491bb74fee22359f5c83dae87f7ba49
3
+ size 4404205384
model-00039-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cac54dbfce32247e7e027741edae820a7ebdc4211274afc8609f23836630ed9
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fb00b8badac0c4b3f00dde963559b550a7c3ad251260fab5128762703bbfbef
3
+ size 4404205384
model-00040-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d53967a1e20112ffa31b4d0befdb07d2c373ec271a8bafb9afffc11b20b6aa1d
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6407cb17975246c5a40c1b0cafb030fe9a6391bbd6d2e5881fde06e3a83a28f2
3
+ size 4404205384
model-00041-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ff6c6dd97f02b3123d7800a0aca8751d87bfb8dd4e905d55cd20df92caded5e
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89410cd12f9d48eb209a72aa981d107dddeca1f23ddf7d33d7a09b7f38d9bd47
3
+ size 4404205384
model-00042-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:814ac2d1c3ba063b6fd80c4887d3da103a2b7715325546a54b00660af334d0dd
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29851457b03209f26bf4ddee29999cb50c3eb1214a9cddf057254f8881d36e9a
3
+ size 4404205384
model-00043-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bcfda8acb51b4cc2463ad874a4dab518eb2d62d7700442ef33811ab84de1928
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83f104a5775cd919532b23cc75ed156a07d2b3a263e23e4b2f4f040b6c9dc3b9
3
+ size 4404205384
model-00044-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:815daa300d1b95862a3f37cc472d4ec6da9b6ca60046fa91b56f2c781cd6027a
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39420f548fae137b07ea0768b2f5ea1c55647f8b08d28ce9ac298ad086c3b481
3
+ size 4404205384
model-00045-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c721f31645101c6960a16167f485174c2846fe3882593671875c90afa61548e
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba88094e11dd44b9be97da6bd196d573c0793407a238c96f7c720b7e923fe5d
3
+ size 4404205384
model-00046-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68f549cbcbd862d30c4508ec0822b9af91468b78828246a6f0f8f5fad15c7750
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a2ea7a6d44fc139d8cc6b1e1f6f49062b24bb985016ae407cf04086b1e24d1f
3
+ size 4404205384
model-00047-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bc27db05392ff9f0171042d68f4807d5dab31bb71f3120469d758a229c75f17
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7717f2fb7e1c1bc4dc752c98c4395671e8c9878beaba1de5e8df6fa07aa9d686
3
+ size 4404205384
model-00048-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed9951206be14f15b30ca590b98dcd1c9477d04c0b3c0041163b93502db73e8b
3
- size 4404205240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7f39c687d916066124afd077b9ab6c735ff22a0e5c90a43524b16ff984063e6
3
+ size 4404205384
model-00049-of-00050.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71dcedc4c4de004b2ee19042c0cb56aeaecbadf2ca50f370c160bfbeb45517bb
3
- size 4278385936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b6c24c27fb9a8db27967b1fa3bf1ec3c50c168791278fcff3770172c8194d6d
3
+ size 4278386080
model.safetensors.index.json CHANGED
@@ -6,7 +6,8 @@
6
  "language_model.lm_head.weight": "model-00050-of-00050.safetensors",
7
  "language_model.model.embed_tokens.weight": "model-00001-of-00050.safetensors",
8
  "language_model.model.layers.0.feed_forward.experts.down_proj.weight": "model-00002-of-00050.safetensors",
9
- "language_model.model.layers.0.feed_forward.experts.gate_up_proj.weight": "model-00002-of-00050.safetensors",
 
10
  "language_model.model.layers.0.feed_forward.router.weight": "model-00002-of-00050.safetensors",
11
  "language_model.model.layers.0.feed_forward.shared_expert.down_proj.weight": "model-00002-of-00050.safetensors",
12
  "language_model.model.layers.0.feed_forward.shared_expert.gate_proj.weight": "model-00002-of-00050.safetensors",
@@ -18,7 +19,8 @@
18
  "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00050.safetensors",
19
  "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00050.safetensors",
20
  "language_model.model.layers.1.feed_forward.experts.down_proj.weight": "model-00003-of-00050.safetensors",
21
- "language_model.model.layers.1.feed_forward.experts.gate_up_proj.weight": "model-00003-of-00050.safetensors",
 
22
  "language_model.model.layers.1.feed_forward.router.weight": "model-00003-of-00050.safetensors",
23
  "language_model.model.layers.1.feed_forward.shared_expert.down_proj.weight": "model-00003-of-00050.safetensors",
24
  "language_model.model.layers.1.feed_forward.shared_expert.gate_proj.weight": "model-00003-of-00050.safetensors",
@@ -30,7 +32,8 @@
30
  "language_model.model.layers.1.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
31
  "language_model.model.layers.1.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
32
  "language_model.model.layers.10.feed_forward.experts.down_proj.weight": "model-00012-of-00050.safetensors",
33
- "language_model.model.layers.10.feed_forward.experts.gate_up_proj.weight": "model-00012-of-00050.safetensors",
 
34
  "language_model.model.layers.10.feed_forward.router.weight": "model-00012-of-00050.safetensors",
35
  "language_model.model.layers.10.feed_forward.shared_expert.down_proj.weight": "model-00012-of-00050.safetensors",
36
  "language_model.model.layers.10.feed_forward.shared_expert.gate_proj.weight": "model-00012-of-00050.safetensors",
@@ -42,7 +45,8 @@
42
  "language_model.model.layers.10.self_attn.q_proj.weight": "model-00011-of-00050.safetensors",
43
  "language_model.model.layers.10.self_attn.v_proj.weight": "model-00011-of-00050.safetensors",
44
  "language_model.model.layers.11.feed_forward.experts.down_proj.weight": "model-00013-of-00050.safetensors",
45
- "language_model.model.layers.11.feed_forward.experts.gate_up_proj.weight": "model-00013-of-00050.safetensors",
 
46
  "language_model.model.layers.11.feed_forward.router.weight": "model-00013-of-00050.safetensors",
47
  "language_model.model.layers.11.feed_forward.shared_expert.down_proj.weight": "model-00013-of-00050.safetensors",
48
  "language_model.model.layers.11.feed_forward.shared_expert.gate_proj.weight": "model-00013-of-00050.safetensors",
@@ -54,7 +58,8 @@
54
  "language_model.model.layers.11.self_attn.q_proj.weight": "model-00012-of-00050.safetensors",
55
  "language_model.model.layers.11.self_attn.v_proj.weight": "model-00012-of-00050.safetensors",
56
  "language_model.model.layers.12.feed_forward.experts.down_proj.weight": "model-00014-of-00050.safetensors",
57
- "language_model.model.layers.12.feed_forward.experts.gate_up_proj.weight": "model-00014-of-00050.safetensors",
 
58
  "language_model.model.layers.12.feed_forward.router.weight": "model-00014-of-00050.safetensors",
59
  "language_model.model.layers.12.feed_forward.shared_expert.down_proj.weight": "model-00014-of-00050.safetensors",
60
  "language_model.model.layers.12.feed_forward.shared_expert.gate_proj.weight": "model-00014-of-00050.safetensors",
@@ -66,7 +71,8 @@
66
  "language_model.model.layers.12.self_attn.q_proj.weight": "model-00013-of-00050.safetensors",
67
  "language_model.model.layers.12.self_attn.v_proj.weight": "model-00013-of-00050.safetensors",
68
  "language_model.model.layers.13.feed_forward.experts.down_proj.weight": "model-00015-of-00050.safetensors",
69
- "language_model.model.layers.13.feed_forward.experts.gate_up_proj.weight": "model-00015-of-00050.safetensors",
 
70
  "language_model.model.layers.13.feed_forward.router.weight": "model-00015-of-00050.safetensors",
71
  "language_model.model.layers.13.feed_forward.shared_expert.down_proj.weight": "model-00015-of-00050.safetensors",
72
  "language_model.model.layers.13.feed_forward.shared_expert.gate_proj.weight": "model-00015-of-00050.safetensors",
@@ -78,7 +84,8 @@
78
  "language_model.model.layers.13.self_attn.q_proj.weight": "model-00014-of-00050.safetensors",
79
  "language_model.model.layers.13.self_attn.v_proj.weight": "model-00014-of-00050.safetensors",
80
  "language_model.model.layers.14.feed_forward.experts.down_proj.weight": "model-00016-of-00050.safetensors",
81
- "language_model.model.layers.14.feed_forward.experts.gate_up_proj.weight": "model-00016-of-00050.safetensors",
 
82
  "language_model.model.layers.14.feed_forward.router.weight": "model-00016-of-00050.safetensors",
83
  "language_model.model.layers.14.feed_forward.shared_expert.down_proj.weight": "model-00016-of-00050.safetensors",
84
  "language_model.model.layers.14.feed_forward.shared_expert.gate_proj.weight": "model-00016-of-00050.safetensors",
@@ -90,7 +97,8 @@
90
  "language_model.model.layers.14.self_attn.q_proj.weight": "model-00015-of-00050.safetensors",
91
  "language_model.model.layers.14.self_attn.v_proj.weight": "model-00015-of-00050.safetensors",
92
  "language_model.model.layers.15.feed_forward.experts.down_proj.weight": "model-00017-of-00050.safetensors",
93
- "language_model.model.layers.15.feed_forward.experts.gate_up_proj.weight": "model-00017-of-00050.safetensors",
 
94
  "language_model.model.layers.15.feed_forward.router.weight": "model-00017-of-00050.safetensors",
95
  "language_model.model.layers.15.feed_forward.shared_expert.down_proj.weight": "model-00017-of-00050.safetensors",
96
  "language_model.model.layers.15.feed_forward.shared_expert.gate_proj.weight": "model-00017-of-00050.safetensors",
@@ -102,7 +110,8 @@
102
  "language_model.model.layers.15.self_attn.q_proj.weight": "model-00016-of-00050.safetensors",
103
  "language_model.model.layers.15.self_attn.v_proj.weight": "model-00016-of-00050.safetensors",
104
  "language_model.model.layers.16.feed_forward.experts.down_proj.weight": "model-00018-of-00050.safetensors",
105
- "language_model.model.layers.16.feed_forward.experts.gate_up_proj.weight": "model-00018-of-00050.safetensors",
 
106
  "language_model.model.layers.16.feed_forward.router.weight": "model-00018-of-00050.safetensors",
107
  "language_model.model.layers.16.feed_forward.shared_expert.down_proj.weight": "model-00018-of-00050.safetensors",
108
  "language_model.model.layers.16.feed_forward.shared_expert.gate_proj.weight": "model-00018-of-00050.safetensors",
@@ -114,7 +123,8 @@
114
  "language_model.model.layers.16.self_attn.q_proj.weight": "model-00017-of-00050.safetensors",
115
  "language_model.model.layers.16.self_attn.v_proj.weight": "model-00017-of-00050.safetensors",
116
  "language_model.model.layers.17.feed_forward.experts.down_proj.weight": "model-00019-of-00050.safetensors",
117
- "language_model.model.layers.17.feed_forward.experts.gate_up_proj.weight": "model-00019-of-00050.safetensors",
 
118
  "language_model.model.layers.17.feed_forward.router.weight": "model-00019-of-00050.safetensors",
119
  "language_model.model.layers.17.feed_forward.shared_expert.down_proj.weight": "model-00019-of-00050.safetensors",
120
  "language_model.model.layers.17.feed_forward.shared_expert.gate_proj.weight": "model-00019-of-00050.safetensors",
@@ -126,7 +136,8 @@
126
  "language_model.model.layers.17.self_attn.q_proj.weight": "model-00018-of-00050.safetensors",
127
  "language_model.model.layers.17.self_attn.v_proj.weight": "model-00018-of-00050.safetensors",
128
  "language_model.model.layers.18.feed_forward.experts.down_proj.weight": "model-00020-of-00050.safetensors",
129
- "language_model.model.layers.18.feed_forward.experts.gate_up_proj.weight": "model-00020-of-00050.safetensors",
 
130
  "language_model.model.layers.18.feed_forward.router.weight": "model-00020-of-00050.safetensors",
131
  "language_model.model.layers.18.feed_forward.shared_expert.down_proj.weight": "model-00020-of-00050.safetensors",
132
  "language_model.model.layers.18.feed_forward.shared_expert.gate_proj.weight": "model-00020-of-00050.safetensors",
@@ -138,7 +149,8 @@
138
  "language_model.model.layers.18.self_attn.q_proj.weight": "model-00019-of-00050.safetensors",
139
  "language_model.model.layers.18.self_attn.v_proj.weight": "model-00019-of-00050.safetensors",
140
  "language_model.model.layers.19.feed_forward.experts.down_proj.weight": "model-00021-of-00050.safetensors",
141
- "language_model.model.layers.19.feed_forward.experts.gate_up_proj.weight": "model-00021-of-00050.safetensors",
 
142
  "language_model.model.layers.19.feed_forward.router.weight": "model-00021-of-00050.safetensors",
143
  "language_model.model.layers.19.feed_forward.shared_expert.down_proj.weight": "model-00021-of-00050.safetensors",
144
  "language_model.model.layers.19.feed_forward.shared_expert.gate_proj.weight": "model-00021-of-00050.safetensors",
@@ -150,7 +162,8 @@
150
  "language_model.model.layers.19.self_attn.q_proj.weight": "model-00020-of-00050.safetensors",
151
  "language_model.model.layers.19.self_attn.v_proj.weight": "model-00020-of-00050.safetensors",
152
  "language_model.model.layers.2.feed_forward.experts.down_proj.weight": "model-00004-of-00050.safetensors",
153
- "language_model.model.layers.2.feed_forward.experts.gate_up_proj.weight": "model-00004-of-00050.safetensors",
 
154
  "language_model.model.layers.2.feed_forward.router.weight": "model-00004-of-00050.safetensors",
155
  "language_model.model.layers.2.feed_forward.shared_expert.down_proj.weight": "model-00004-of-00050.safetensors",
156
  "language_model.model.layers.2.feed_forward.shared_expert.gate_proj.weight": "model-00004-of-00050.safetensors",
@@ -162,7 +175,8 @@
162
  "language_model.model.layers.2.self_attn.q_proj.weight": "model-00003-of-00050.safetensors",
163
  "language_model.model.layers.2.self_attn.v_proj.weight": "model-00003-of-00050.safetensors",
164
  "language_model.model.layers.20.feed_forward.experts.down_proj.weight": "model-00022-of-00050.safetensors",
165
- "language_model.model.layers.20.feed_forward.experts.gate_up_proj.weight": "model-00022-of-00050.safetensors",
 
166
  "language_model.model.layers.20.feed_forward.router.weight": "model-00022-of-00050.safetensors",
167
  "language_model.model.layers.20.feed_forward.shared_expert.down_proj.weight": "model-00022-of-00050.safetensors",
168
  "language_model.model.layers.20.feed_forward.shared_expert.gate_proj.weight": "model-00022-of-00050.safetensors",
@@ -174,7 +188,8 @@
174
  "language_model.model.layers.20.self_attn.q_proj.weight": "model-00021-of-00050.safetensors",
175
  "language_model.model.layers.20.self_attn.v_proj.weight": "model-00021-of-00050.safetensors",
176
  "language_model.model.layers.21.feed_forward.experts.down_proj.weight": "model-00023-of-00050.safetensors",
177
- "language_model.model.layers.21.feed_forward.experts.gate_up_proj.weight": "model-00023-of-00050.safetensors",
 
178
  "language_model.model.layers.21.feed_forward.router.weight": "model-00023-of-00050.safetensors",
179
  "language_model.model.layers.21.feed_forward.shared_expert.down_proj.weight": "model-00023-of-00050.safetensors",
180
  "language_model.model.layers.21.feed_forward.shared_expert.gate_proj.weight": "model-00023-of-00050.safetensors",
@@ -186,7 +201,8 @@
186
  "language_model.model.layers.21.self_attn.q_proj.weight": "model-00022-of-00050.safetensors",
187
  "language_model.model.layers.21.self_attn.v_proj.weight": "model-00022-of-00050.safetensors",
188
  "language_model.model.layers.22.feed_forward.experts.down_proj.weight": "model-00024-of-00050.safetensors",
189
- "language_model.model.layers.22.feed_forward.experts.gate_up_proj.weight": "model-00024-of-00050.safetensors",
 
190
  "language_model.model.layers.22.feed_forward.router.weight": "model-00024-of-00050.safetensors",
191
  "language_model.model.layers.22.feed_forward.shared_expert.down_proj.weight": "model-00024-of-00050.safetensors",
192
  "language_model.model.layers.22.feed_forward.shared_expert.gate_proj.weight": "model-00024-of-00050.safetensors",
@@ -198,7 +214,8 @@
198
  "language_model.model.layers.22.self_attn.q_proj.weight": "model-00023-of-00050.safetensors",
199
  "language_model.model.layers.22.self_attn.v_proj.weight": "model-00023-of-00050.safetensors",
200
  "language_model.model.layers.23.feed_forward.experts.down_proj.weight": "model-00025-of-00050.safetensors",
201
- "language_model.model.layers.23.feed_forward.experts.gate_up_proj.weight": "model-00025-of-00050.safetensors",
 
202
  "language_model.model.layers.23.feed_forward.router.weight": "model-00025-of-00050.safetensors",
203
  "language_model.model.layers.23.feed_forward.shared_expert.down_proj.weight": "model-00025-of-00050.safetensors",
204
  "language_model.model.layers.23.feed_forward.shared_expert.gate_proj.weight": "model-00025-of-00050.safetensors",
@@ -210,7 +227,8 @@
210
  "language_model.model.layers.23.self_attn.q_proj.weight": "model-00024-of-00050.safetensors",
211
  "language_model.model.layers.23.self_attn.v_proj.weight": "model-00024-of-00050.safetensors",
212
  "language_model.model.layers.24.feed_forward.experts.down_proj.weight": "model-00026-of-00050.safetensors",
213
- "language_model.model.layers.24.feed_forward.experts.gate_up_proj.weight": "model-00026-of-00050.safetensors",
 
214
  "language_model.model.layers.24.feed_forward.router.weight": "model-00026-of-00050.safetensors",
215
  "language_model.model.layers.24.feed_forward.shared_expert.down_proj.weight": "model-00026-of-00050.safetensors",
216
  "language_model.model.layers.24.feed_forward.shared_expert.gate_proj.weight": "model-00026-of-00050.safetensors",
@@ -222,7 +240,8 @@
222
  "language_model.model.layers.24.self_attn.q_proj.weight": "model-00025-of-00050.safetensors",
223
  "language_model.model.layers.24.self_attn.v_proj.weight": "model-00025-of-00050.safetensors",
224
  "language_model.model.layers.25.feed_forward.experts.down_proj.weight": "model-00027-of-00050.safetensors",
225
- "language_model.model.layers.25.feed_forward.experts.gate_up_proj.weight": "model-00027-of-00050.safetensors",
 
226
  "language_model.model.layers.25.feed_forward.router.weight": "model-00027-of-00050.safetensors",
227
  "language_model.model.layers.25.feed_forward.shared_expert.down_proj.weight": "model-00027-of-00050.safetensors",
228
  "language_model.model.layers.25.feed_forward.shared_expert.gate_proj.weight": "model-00027-of-00050.safetensors",
@@ -234,7 +253,8 @@
234
  "language_model.model.layers.25.self_attn.q_proj.weight": "model-00026-of-00050.safetensors",
235
  "language_model.model.layers.25.self_attn.v_proj.weight": "model-00026-of-00050.safetensors",
236
  "language_model.model.layers.26.feed_forward.experts.down_proj.weight": "model-00028-of-00050.safetensors",
237
- "language_model.model.layers.26.feed_forward.experts.gate_up_proj.weight": "model-00028-of-00050.safetensors",
 
238
  "language_model.model.layers.26.feed_forward.router.weight": "model-00028-of-00050.safetensors",
239
  "language_model.model.layers.26.feed_forward.shared_expert.down_proj.weight": "model-00028-of-00050.safetensors",
240
  "language_model.model.layers.26.feed_forward.shared_expert.gate_proj.weight": "model-00028-of-00050.safetensors",
@@ -246,7 +266,8 @@
246
  "language_model.model.layers.26.self_attn.q_proj.weight": "model-00027-of-00050.safetensors",
247
  "language_model.model.layers.26.self_attn.v_proj.weight": "model-00027-of-00050.safetensors",
248
  "language_model.model.layers.27.feed_forward.experts.down_proj.weight": "model-00029-of-00050.safetensors",
249
- "language_model.model.layers.27.feed_forward.experts.gate_up_proj.weight": "model-00029-of-00050.safetensors",
 
250
  "language_model.model.layers.27.feed_forward.router.weight": "model-00029-of-00050.safetensors",
251
  "language_model.model.layers.27.feed_forward.shared_expert.down_proj.weight": "model-00029-of-00050.safetensors",
252
  "language_model.model.layers.27.feed_forward.shared_expert.gate_proj.weight": "model-00029-of-00050.safetensors",
@@ -258,7 +279,8 @@
258
  "language_model.model.layers.27.self_attn.q_proj.weight": "model-00028-of-00050.safetensors",
259
  "language_model.model.layers.27.self_attn.v_proj.weight": "model-00028-of-00050.safetensors",
260
  "language_model.model.layers.28.feed_forward.experts.down_proj.weight": "model-00030-of-00050.safetensors",
261
- "language_model.model.layers.28.feed_forward.experts.gate_up_proj.weight": "model-00030-of-00050.safetensors",
 
262
  "language_model.model.layers.28.feed_forward.router.weight": "model-00030-of-00050.safetensors",
263
  "language_model.model.layers.28.feed_forward.shared_expert.down_proj.weight": "model-00030-of-00050.safetensors",
264
  "language_model.model.layers.28.feed_forward.shared_expert.gate_proj.weight": "model-00030-of-00050.safetensors",
@@ -270,7 +292,8 @@
270
  "language_model.model.layers.28.self_attn.q_proj.weight": "model-00029-of-00050.safetensors",
271
  "language_model.model.layers.28.self_attn.v_proj.weight": "model-00029-of-00050.safetensors",
272
  "language_model.model.layers.29.feed_forward.experts.down_proj.weight": "model-00031-of-00050.safetensors",
273
- "language_model.model.layers.29.feed_forward.experts.gate_up_proj.weight": "model-00031-of-00050.safetensors",
 
274
  "language_model.model.layers.29.feed_forward.router.weight": "model-00031-of-00050.safetensors",
275
  "language_model.model.layers.29.feed_forward.shared_expert.down_proj.weight": "model-00031-of-00050.safetensors",
276
  "language_model.model.layers.29.feed_forward.shared_expert.gate_proj.weight": "model-00031-of-00050.safetensors",
@@ -282,7 +305,8 @@
282
  "language_model.model.layers.29.self_attn.q_proj.weight": "model-00030-of-00050.safetensors",
283
  "language_model.model.layers.29.self_attn.v_proj.weight": "model-00030-of-00050.safetensors",
284
  "language_model.model.layers.3.feed_forward.experts.down_proj.weight": "model-00005-of-00050.safetensors",
285
- "language_model.model.layers.3.feed_forward.experts.gate_up_proj.weight": "model-00005-of-00050.safetensors",
 
286
  "language_model.model.layers.3.feed_forward.router.weight": "model-00005-of-00050.safetensors",
287
  "language_model.model.layers.3.feed_forward.shared_expert.down_proj.weight": "model-00005-of-00050.safetensors",
288
  "language_model.model.layers.3.feed_forward.shared_expert.gate_proj.weight": "model-00005-of-00050.safetensors",
@@ -294,7 +318,8 @@
294
  "language_model.model.layers.3.self_attn.q_proj.weight": "model-00004-of-00050.safetensors",
295
  "language_model.model.layers.3.self_attn.v_proj.weight": "model-00004-of-00050.safetensors",
296
  "language_model.model.layers.30.feed_forward.experts.down_proj.weight": "model-00032-of-00050.safetensors",
297
- "language_model.model.layers.30.feed_forward.experts.gate_up_proj.weight": "model-00032-of-00050.safetensors",
 
298
  "language_model.model.layers.30.feed_forward.router.weight": "model-00032-of-00050.safetensors",
299
  "language_model.model.layers.30.feed_forward.shared_expert.down_proj.weight": "model-00032-of-00050.safetensors",
300
  "language_model.model.layers.30.feed_forward.shared_expert.gate_proj.weight": "model-00032-of-00050.safetensors",
@@ -306,7 +331,8 @@
306
  "language_model.model.layers.30.self_attn.q_proj.weight": "model-00031-of-00050.safetensors",
307
  "language_model.model.layers.30.self_attn.v_proj.weight": "model-00031-of-00050.safetensors",
308
  "language_model.model.layers.31.feed_forward.experts.down_proj.weight": "model-00033-of-00050.safetensors",
309
- "language_model.model.layers.31.feed_forward.experts.gate_up_proj.weight": "model-00033-of-00050.safetensors",
 
310
  "language_model.model.layers.31.feed_forward.router.weight": "model-00033-of-00050.safetensors",
311
  "language_model.model.layers.31.feed_forward.shared_expert.down_proj.weight": "model-00033-of-00050.safetensors",
312
  "language_model.model.layers.31.feed_forward.shared_expert.gate_proj.weight": "model-00033-of-00050.safetensors",
@@ -318,7 +344,8 @@
318
  "language_model.model.layers.31.self_attn.q_proj.weight": "model-00032-of-00050.safetensors",
319
  "language_model.model.layers.31.self_attn.v_proj.weight": "model-00032-of-00050.safetensors",
320
  "language_model.model.layers.32.feed_forward.experts.down_proj.weight": "model-00034-of-00050.safetensors",
321
- "language_model.model.layers.32.feed_forward.experts.gate_up_proj.weight": "model-00034-of-00050.safetensors",
 
322
  "language_model.model.layers.32.feed_forward.router.weight": "model-00034-of-00050.safetensors",
323
  "language_model.model.layers.32.feed_forward.shared_expert.down_proj.weight": "model-00034-of-00050.safetensors",
324
  "language_model.model.layers.32.feed_forward.shared_expert.gate_proj.weight": "model-00034-of-00050.safetensors",
@@ -330,7 +357,8 @@
330
  "language_model.model.layers.32.self_attn.q_proj.weight": "model-00033-of-00050.safetensors",
331
  "language_model.model.layers.32.self_attn.v_proj.weight": "model-00033-of-00050.safetensors",
332
  "language_model.model.layers.33.feed_forward.experts.down_proj.weight": "model-00035-of-00050.safetensors",
333
- "language_model.model.layers.33.feed_forward.experts.gate_up_proj.weight": "model-00035-of-00050.safetensors",
 
334
  "language_model.model.layers.33.feed_forward.router.weight": "model-00035-of-00050.safetensors",
335
  "language_model.model.layers.33.feed_forward.shared_expert.down_proj.weight": "model-00035-of-00050.safetensors",
336
  "language_model.model.layers.33.feed_forward.shared_expert.gate_proj.weight": "model-00035-of-00050.safetensors",
@@ -342,7 +370,8 @@
342
  "language_model.model.layers.33.self_attn.q_proj.weight": "model-00034-of-00050.safetensors",
343
  "language_model.model.layers.33.self_attn.v_proj.weight": "model-00034-of-00050.safetensors",
344
  "language_model.model.layers.34.feed_forward.experts.down_proj.weight": "model-00036-of-00050.safetensors",
345
- "language_model.model.layers.34.feed_forward.experts.gate_up_proj.weight": "model-00036-of-00050.safetensors",
 
346
  "language_model.model.layers.34.feed_forward.router.weight": "model-00036-of-00050.safetensors",
347
  "language_model.model.layers.34.feed_forward.shared_expert.down_proj.weight": "model-00036-of-00050.safetensors",
348
  "language_model.model.layers.34.feed_forward.shared_expert.gate_proj.weight": "model-00036-of-00050.safetensors",
@@ -354,7 +383,8 @@
354
  "language_model.model.layers.34.self_attn.q_proj.weight": "model-00035-of-00050.safetensors",
355
  "language_model.model.layers.34.self_attn.v_proj.weight": "model-00035-of-00050.safetensors",
356
  "language_model.model.layers.35.feed_forward.experts.down_proj.weight": "model-00037-of-00050.safetensors",
357
- "language_model.model.layers.35.feed_forward.experts.gate_up_proj.weight": "model-00037-of-00050.safetensors",
 
358
  "language_model.model.layers.35.feed_forward.router.weight": "model-00037-of-00050.safetensors",
359
  "language_model.model.layers.35.feed_forward.shared_expert.down_proj.weight": "model-00037-of-00050.safetensors",
360
  "language_model.model.layers.35.feed_forward.shared_expert.gate_proj.weight": "model-00037-of-00050.safetensors",
@@ -366,7 +396,8 @@
366
  "language_model.model.layers.35.self_attn.q_proj.weight": "model-00036-of-00050.safetensors",
367
  "language_model.model.layers.35.self_attn.v_proj.weight": "model-00036-of-00050.safetensors",
368
  "language_model.model.layers.36.feed_forward.experts.down_proj.weight": "model-00038-of-00050.safetensors",
369
- "language_model.model.layers.36.feed_forward.experts.gate_up_proj.weight": "model-00038-of-00050.safetensors",
 
370
  "language_model.model.layers.36.feed_forward.router.weight": "model-00038-of-00050.safetensors",
371
  "language_model.model.layers.36.feed_forward.shared_expert.down_proj.weight": "model-00038-of-00050.safetensors",
372
  "language_model.model.layers.36.feed_forward.shared_expert.gate_proj.weight": "model-00038-of-00050.safetensors",
@@ -378,7 +409,8 @@
378
  "language_model.model.layers.36.self_attn.q_proj.weight": "model-00037-of-00050.safetensors",
379
  "language_model.model.layers.36.self_attn.v_proj.weight": "model-00037-of-00050.safetensors",
380
  "language_model.model.layers.37.feed_forward.experts.down_proj.weight": "model-00039-of-00050.safetensors",
381
- "language_model.model.layers.37.feed_forward.experts.gate_up_proj.weight": "model-00039-of-00050.safetensors",
 
382
  "language_model.model.layers.37.feed_forward.router.weight": "model-00039-of-00050.safetensors",
383
  "language_model.model.layers.37.feed_forward.shared_expert.down_proj.weight": "model-00039-of-00050.safetensors",
384
  "language_model.model.layers.37.feed_forward.shared_expert.gate_proj.weight": "model-00039-of-00050.safetensors",
@@ -390,7 +422,8 @@
390
  "language_model.model.layers.37.self_attn.q_proj.weight": "model-00038-of-00050.safetensors",
391
  "language_model.model.layers.37.self_attn.v_proj.weight": "model-00038-of-00050.safetensors",
392
  "language_model.model.layers.38.feed_forward.experts.down_proj.weight": "model-00040-of-00050.safetensors",
393
- "language_model.model.layers.38.feed_forward.experts.gate_up_proj.weight": "model-00040-of-00050.safetensors",
 
394
  "language_model.model.layers.38.feed_forward.router.weight": "model-00040-of-00050.safetensors",
395
  "language_model.model.layers.38.feed_forward.shared_expert.down_proj.weight": "model-00040-of-00050.safetensors",
396
  "language_model.model.layers.38.feed_forward.shared_expert.gate_proj.weight": "model-00040-of-00050.safetensors",
@@ -402,7 +435,8 @@
402
  "language_model.model.layers.38.self_attn.q_proj.weight": "model-00039-of-00050.safetensors",
403
  "language_model.model.layers.38.self_attn.v_proj.weight": "model-00039-of-00050.safetensors",
404
  "language_model.model.layers.39.feed_forward.experts.down_proj.weight": "model-00041-of-00050.safetensors",
405
- "language_model.model.layers.39.feed_forward.experts.gate_up_proj.weight": "model-00041-of-00050.safetensors",
 
406
  "language_model.model.layers.39.feed_forward.router.weight": "model-00041-of-00050.safetensors",
407
  "language_model.model.layers.39.feed_forward.shared_expert.down_proj.weight": "model-00041-of-00050.safetensors",
408
  "language_model.model.layers.39.feed_forward.shared_expert.gate_proj.weight": "model-00041-of-00050.safetensors",
@@ -414,7 +448,8 @@
414
  "language_model.model.layers.39.self_attn.q_proj.weight": "model-00040-of-00050.safetensors",
415
  "language_model.model.layers.39.self_attn.v_proj.weight": "model-00040-of-00050.safetensors",
416
  "language_model.model.layers.4.feed_forward.experts.down_proj.weight": "model-00006-of-00050.safetensors",
417
- "language_model.model.layers.4.feed_forward.experts.gate_up_proj.weight": "model-00006-of-00050.safetensors",
 
418
  "language_model.model.layers.4.feed_forward.router.weight": "model-00006-of-00050.safetensors",
419
  "language_model.model.layers.4.feed_forward.shared_expert.down_proj.weight": "model-00006-of-00050.safetensors",
420
  "language_model.model.layers.4.feed_forward.shared_expert.gate_proj.weight": "model-00006-of-00050.safetensors",
@@ -426,7 +461,8 @@
426
  "language_model.model.layers.4.self_attn.q_proj.weight": "model-00005-of-00050.safetensors",
427
  "language_model.model.layers.4.self_attn.v_proj.weight": "model-00005-of-00050.safetensors",
428
  "language_model.model.layers.40.feed_forward.experts.down_proj.weight": "model-00042-of-00050.safetensors",
429
- "language_model.model.layers.40.feed_forward.experts.gate_up_proj.weight": "model-00042-of-00050.safetensors",
 
430
  "language_model.model.layers.40.feed_forward.router.weight": "model-00042-of-00050.safetensors",
431
  "language_model.model.layers.40.feed_forward.shared_expert.down_proj.weight": "model-00042-of-00050.safetensors",
432
  "language_model.model.layers.40.feed_forward.shared_expert.gate_proj.weight": "model-00042-of-00050.safetensors",
@@ -438,7 +474,8 @@
438
  "language_model.model.layers.40.self_attn.q_proj.weight": "model-00041-of-00050.safetensors",
439
  "language_model.model.layers.40.self_attn.v_proj.weight": "model-00041-of-00050.safetensors",
440
  "language_model.model.layers.41.feed_forward.experts.down_proj.weight": "model-00043-of-00050.safetensors",
441
- "language_model.model.layers.41.feed_forward.experts.gate_up_proj.weight": "model-00043-of-00050.safetensors",
 
442
  "language_model.model.layers.41.feed_forward.router.weight": "model-00043-of-00050.safetensors",
443
  "language_model.model.layers.41.feed_forward.shared_expert.down_proj.weight": "model-00043-of-00050.safetensors",
444
  "language_model.model.layers.41.feed_forward.shared_expert.gate_proj.weight": "model-00043-of-00050.safetensors",
@@ -450,7 +487,8 @@
450
  "language_model.model.layers.41.self_attn.q_proj.weight": "model-00042-of-00050.safetensors",
451
  "language_model.model.layers.41.self_attn.v_proj.weight": "model-00042-of-00050.safetensors",
452
  "language_model.model.layers.42.feed_forward.experts.down_proj.weight": "model-00044-of-00050.safetensors",
453
- "language_model.model.layers.42.feed_forward.experts.gate_up_proj.weight": "model-00044-of-00050.safetensors",
 
454
  "language_model.model.layers.42.feed_forward.router.weight": "model-00044-of-00050.safetensors",
455
  "language_model.model.layers.42.feed_forward.shared_expert.down_proj.weight": "model-00044-of-00050.safetensors",
456
  "language_model.model.layers.42.feed_forward.shared_expert.gate_proj.weight": "model-00044-of-00050.safetensors",
@@ -462,7 +500,8 @@
462
  "language_model.model.layers.42.self_attn.q_proj.weight": "model-00043-of-00050.safetensors",
463
  "language_model.model.layers.42.self_attn.v_proj.weight": "model-00043-of-00050.safetensors",
464
  "language_model.model.layers.43.feed_forward.experts.down_proj.weight": "model-00045-of-00050.safetensors",
465
- "language_model.model.layers.43.feed_forward.experts.gate_up_proj.weight": "model-00045-of-00050.safetensors",
 
466
  "language_model.model.layers.43.feed_forward.router.weight": "model-00045-of-00050.safetensors",
467
  "language_model.model.layers.43.feed_forward.shared_expert.down_proj.weight": "model-00045-of-00050.safetensors",
468
  "language_model.model.layers.43.feed_forward.shared_expert.gate_proj.weight": "model-00045-of-00050.safetensors",
@@ -474,7 +513,8 @@
474
  "language_model.model.layers.43.self_attn.q_proj.weight": "model-00044-of-00050.safetensors",
475
  "language_model.model.layers.43.self_attn.v_proj.weight": "model-00044-of-00050.safetensors",
476
  "language_model.model.layers.44.feed_forward.experts.down_proj.weight": "model-00046-of-00050.safetensors",
477
- "language_model.model.layers.44.feed_forward.experts.gate_up_proj.weight": "model-00046-of-00050.safetensors",
 
478
  "language_model.model.layers.44.feed_forward.router.weight": "model-00046-of-00050.safetensors",
479
  "language_model.model.layers.44.feed_forward.shared_expert.down_proj.weight": "model-00046-of-00050.safetensors",
480
  "language_model.model.layers.44.feed_forward.shared_expert.gate_proj.weight": "model-00046-of-00050.safetensors",
@@ -486,7 +526,8 @@
486
  "language_model.model.layers.44.self_attn.q_proj.weight": "model-00045-of-00050.safetensors",
487
  "language_model.model.layers.44.self_attn.v_proj.weight": "model-00045-of-00050.safetensors",
488
  "language_model.model.layers.45.feed_forward.experts.down_proj.weight": "model-00047-of-00050.safetensors",
489
- "language_model.model.layers.45.feed_forward.experts.gate_up_proj.weight": "model-00047-of-00050.safetensors",
 
490
  "language_model.model.layers.45.feed_forward.router.weight": "model-00047-of-00050.safetensors",
491
  "language_model.model.layers.45.feed_forward.shared_expert.down_proj.weight": "model-00047-of-00050.safetensors",
492
  "language_model.model.layers.45.feed_forward.shared_expert.gate_proj.weight": "model-00047-of-00050.safetensors",
@@ -498,7 +539,8 @@
498
  "language_model.model.layers.45.self_attn.q_proj.weight": "model-00046-of-00050.safetensors",
499
  "language_model.model.layers.45.self_attn.v_proj.weight": "model-00046-of-00050.safetensors",
500
  "language_model.model.layers.46.feed_forward.experts.down_proj.weight": "model-00048-of-00050.safetensors",
501
- "language_model.model.layers.46.feed_forward.experts.gate_up_proj.weight": "model-00048-of-00050.safetensors",
 
502
  "language_model.model.layers.46.feed_forward.router.weight": "model-00048-of-00050.safetensors",
503
  "language_model.model.layers.46.feed_forward.shared_expert.down_proj.weight": "model-00048-of-00050.safetensors",
504
  "language_model.model.layers.46.feed_forward.shared_expert.gate_proj.weight": "model-00048-of-00050.safetensors",
@@ -510,7 +552,8 @@
510
  "language_model.model.layers.46.self_attn.q_proj.weight": "model-00047-of-00050.safetensors",
511
  "language_model.model.layers.46.self_attn.v_proj.weight": "model-00047-of-00050.safetensors",
512
  "language_model.model.layers.47.feed_forward.experts.down_proj.weight": "model-00049-of-00050.safetensors",
513
- "language_model.model.layers.47.feed_forward.experts.gate_up_proj.weight": "model-00049-of-00050.safetensors",
 
514
  "language_model.model.layers.47.feed_forward.router.weight": "model-00049-of-00050.safetensors",
515
  "language_model.model.layers.47.feed_forward.shared_expert.down_proj.weight": "model-00049-of-00050.safetensors",
516
  "language_model.model.layers.47.feed_forward.shared_expert.gate_proj.weight": "model-00049-of-00050.safetensors",
@@ -522,7 +565,8 @@
522
  "language_model.model.layers.47.self_attn.q_proj.weight": "model-00048-of-00050.safetensors",
523
  "language_model.model.layers.47.self_attn.v_proj.weight": "model-00048-of-00050.safetensors",
524
  "language_model.model.layers.5.feed_forward.experts.down_proj.weight": "model-00007-of-00050.safetensors",
525
- "language_model.model.layers.5.feed_forward.experts.gate_up_proj.weight": "model-00007-of-00050.safetensors",
 
526
  "language_model.model.layers.5.feed_forward.router.weight": "model-00007-of-00050.safetensors",
527
  "language_model.model.layers.5.feed_forward.shared_expert.down_proj.weight": "model-00007-of-00050.safetensors",
528
  "language_model.model.layers.5.feed_forward.shared_expert.gate_proj.weight": "model-00007-of-00050.safetensors",
@@ -534,7 +578,8 @@
534
  "language_model.model.layers.5.self_attn.q_proj.weight": "model-00006-of-00050.safetensors",
535
  "language_model.model.layers.5.self_attn.v_proj.weight": "model-00006-of-00050.safetensors",
536
  "language_model.model.layers.6.feed_forward.experts.down_proj.weight": "model-00008-of-00050.safetensors",
537
- "language_model.model.layers.6.feed_forward.experts.gate_up_proj.weight": "model-00008-of-00050.safetensors",
 
538
  "language_model.model.layers.6.feed_forward.router.weight": "model-00008-of-00050.safetensors",
539
  "language_model.model.layers.6.feed_forward.shared_expert.down_proj.weight": "model-00008-of-00050.safetensors",
540
  "language_model.model.layers.6.feed_forward.shared_expert.gate_proj.weight": "model-00008-of-00050.safetensors",
@@ -546,7 +591,8 @@
546
  "language_model.model.layers.6.self_attn.q_proj.weight": "model-00007-of-00050.safetensors",
547
  "language_model.model.layers.6.self_attn.v_proj.weight": "model-00007-of-00050.safetensors",
548
  "language_model.model.layers.7.feed_forward.experts.down_proj.weight": "model-00009-of-00050.safetensors",
549
- "language_model.model.layers.7.feed_forward.experts.gate_up_proj.weight": "model-00009-of-00050.safetensors",
 
550
  "language_model.model.layers.7.feed_forward.router.weight": "model-00009-of-00050.safetensors",
551
  "language_model.model.layers.7.feed_forward.shared_expert.down_proj.weight": "model-00009-of-00050.safetensors",
552
  "language_model.model.layers.7.feed_forward.shared_expert.gate_proj.weight": "model-00009-of-00050.safetensors",
@@ -558,7 +604,8 @@
558
  "language_model.model.layers.7.self_attn.q_proj.weight": "model-00008-of-00050.safetensors",
559
  "language_model.model.layers.7.self_attn.v_proj.weight": "model-00008-of-00050.safetensors",
560
  "language_model.model.layers.8.feed_forward.experts.down_proj.weight": "model-00010-of-00050.safetensors",
561
- "language_model.model.layers.8.feed_forward.experts.gate_up_proj.weight": "model-00010-of-00050.safetensors",
 
562
  "language_model.model.layers.8.feed_forward.router.weight": "model-00010-of-00050.safetensors",
563
  "language_model.model.layers.8.feed_forward.shared_expert.down_proj.weight": "model-00010-of-00050.safetensors",
564
  "language_model.model.layers.8.feed_forward.shared_expert.gate_proj.weight": "model-00010-of-00050.safetensors",
@@ -570,7 +617,8 @@
570
  "language_model.model.layers.8.self_attn.q_proj.weight": "model-00009-of-00050.safetensors",
571
  "language_model.model.layers.8.self_attn.v_proj.weight": "model-00009-of-00050.safetensors",
572
  "language_model.model.layers.9.feed_forward.experts.down_proj.weight": "model-00011-of-00050.safetensors",
573
- "language_model.model.layers.9.feed_forward.experts.gate_up_proj.weight": "model-00011-of-00050.safetensors",
 
574
  "language_model.model.layers.9.feed_forward.router.weight": "model-00011-of-00050.safetensors",
575
  "language_model.model.layers.9.feed_forward.shared_expert.down_proj.weight": "model-00011-of-00050.safetensors",
576
  "language_model.model.layers.9.feed_forward.shared_expert.gate_proj.weight": "model-00011-of-00050.safetensors",
 
6
  "language_model.lm_head.weight": "model-00050-of-00050.safetensors",
7
  "language_model.model.embed_tokens.weight": "model-00001-of-00050.safetensors",
8
  "language_model.model.layers.0.feed_forward.experts.down_proj.weight": "model-00002-of-00050.safetensors",
9
+ "language_model.model.layers.0.feed_forward.experts.gate_proj.weight": "model-00002-of-00050.safetensors",
10
+ "language_model.model.layers.0.feed_forward.experts.up_proj.weight": "model-00002-of-00050.safetensors",
11
  "language_model.model.layers.0.feed_forward.router.weight": "model-00002-of-00050.safetensors",
12
  "language_model.model.layers.0.feed_forward.shared_expert.down_proj.weight": "model-00002-of-00050.safetensors",
13
  "language_model.model.layers.0.feed_forward.shared_expert.gate_proj.weight": "model-00002-of-00050.safetensors",
 
19
  "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00050.safetensors",
20
  "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00050.safetensors",
21
  "language_model.model.layers.1.feed_forward.experts.down_proj.weight": "model-00003-of-00050.safetensors",
22
+ "language_model.model.layers.1.feed_forward.experts.gate_proj.weight": "model-00003-of-00050.safetensors",
23
+ "language_model.model.layers.1.feed_forward.experts.up_proj.weight": "model-00003-of-00050.safetensors",
24
  "language_model.model.layers.1.feed_forward.router.weight": "model-00003-of-00050.safetensors",
25
  "language_model.model.layers.1.feed_forward.shared_expert.down_proj.weight": "model-00003-of-00050.safetensors",
26
  "language_model.model.layers.1.feed_forward.shared_expert.gate_proj.weight": "model-00003-of-00050.safetensors",
 
32
  "language_model.model.layers.1.self_attn.q_proj.weight": "model-00002-of-00050.safetensors",
33
  "language_model.model.layers.1.self_attn.v_proj.weight": "model-00002-of-00050.safetensors",
34
  "language_model.model.layers.10.feed_forward.experts.down_proj.weight": "model-00012-of-00050.safetensors",
35
+ "language_model.model.layers.10.feed_forward.experts.gate_proj.weight": "model-00012-of-00050.safetensors",
36
+ "language_model.model.layers.10.feed_forward.experts.up_proj.weight": "model-00012-of-00050.safetensors",
37
  "language_model.model.layers.10.feed_forward.router.weight": "model-00012-of-00050.safetensors",
38
  "language_model.model.layers.10.feed_forward.shared_expert.down_proj.weight": "model-00012-of-00050.safetensors",
39
  "language_model.model.layers.10.feed_forward.shared_expert.gate_proj.weight": "model-00012-of-00050.safetensors",
 
45
  "language_model.model.layers.10.self_attn.q_proj.weight": "model-00011-of-00050.safetensors",
46
  "language_model.model.layers.10.self_attn.v_proj.weight": "model-00011-of-00050.safetensors",
47
  "language_model.model.layers.11.feed_forward.experts.down_proj.weight": "model-00013-of-00050.safetensors",
48
+ "language_model.model.layers.11.feed_forward.experts.gate_proj.weight": "model-00013-of-00050.safetensors",
49
+ "language_model.model.layers.11.feed_forward.experts.up_proj.weight": "model-00013-of-00050.safetensors",
50
  "language_model.model.layers.11.feed_forward.router.weight": "model-00013-of-00050.safetensors",
51
  "language_model.model.layers.11.feed_forward.shared_expert.down_proj.weight": "model-00013-of-00050.safetensors",
52
  "language_model.model.layers.11.feed_forward.shared_expert.gate_proj.weight": "model-00013-of-00050.safetensors",
 
58
  "language_model.model.layers.11.self_attn.q_proj.weight": "model-00012-of-00050.safetensors",
59
  "language_model.model.layers.11.self_attn.v_proj.weight": "model-00012-of-00050.safetensors",
60
  "language_model.model.layers.12.feed_forward.experts.down_proj.weight": "model-00014-of-00050.safetensors",
61
+ "language_model.model.layers.12.feed_forward.experts.gate_proj.weight": "model-00014-of-00050.safetensors",
62
+ "language_model.model.layers.12.feed_forward.experts.up_proj.weight": "model-00014-of-00050.safetensors",
63
  "language_model.model.layers.12.feed_forward.router.weight": "model-00014-of-00050.safetensors",
64
  "language_model.model.layers.12.feed_forward.shared_expert.down_proj.weight": "model-00014-of-00050.safetensors",
65
  "language_model.model.layers.12.feed_forward.shared_expert.gate_proj.weight": "model-00014-of-00050.safetensors",
 
71
  "language_model.model.layers.12.self_attn.q_proj.weight": "model-00013-of-00050.safetensors",
72
  "language_model.model.layers.12.self_attn.v_proj.weight": "model-00013-of-00050.safetensors",
73
  "language_model.model.layers.13.feed_forward.experts.down_proj.weight": "model-00015-of-00050.safetensors",
74
+ "language_model.model.layers.13.feed_forward.experts.gate_proj.weight": "model-00015-of-00050.safetensors",
75
+ "language_model.model.layers.13.feed_forward.experts.up_proj.weight": "model-00015-of-00050.safetensors",
76
  "language_model.model.layers.13.feed_forward.router.weight": "model-00015-of-00050.safetensors",
77
  "language_model.model.layers.13.feed_forward.shared_expert.down_proj.weight": "model-00015-of-00050.safetensors",
78
  "language_model.model.layers.13.feed_forward.shared_expert.gate_proj.weight": "model-00015-of-00050.safetensors",
 
84
  "language_model.model.layers.13.self_attn.q_proj.weight": "model-00014-of-00050.safetensors",
85
  "language_model.model.layers.13.self_attn.v_proj.weight": "model-00014-of-00050.safetensors",
86
  "language_model.model.layers.14.feed_forward.experts.down_proj.weight": "model-00016-of-00050.safetensors",
87
+ "language_model.model.layers.14.feed_forward.experts.gate_proj.weight": "model-00016-of-00050.safetensors",
88
+ "language_model.model.layers.14.feed_forward.experts.up_proj.weight": "model-00016-of-00050.safetensors",
89
  "language_model.model.layers.14.feed_forward.router.weight": "model-00016-of-00050.safetensors",
90
  "language_model.model.layers.14.feed_forward.shared_expert.down_proj.weight": "model-00016-of-00050.safetensors",
91
  "language_model.model.layers.14.feed_forward.shared_expert.gate_proj.weight": "model-00016-of-00050.safetensors",
 
97
  "language_model.model.layers.14.self_attn.q_proj.weight": "model-00015-of-00050.safetensors",
98
  "language_model.model.layers.14.self_attn.v_proj.weight": "model-00015-of-00050.safetensors",
99
  "language_model.model.layers.15.feed_forward.experts.down_proj.weight": "model-00017-of-00050.safetensors",
100
+ "language_model.model.layers.15.feed_forward.experts.gate_proj.weight": "model-00017-of-00050.safetensors",
101
+ "language_model.model.layers.15.feed_forward.experts.up_proj.weight": "model-00017-of-00050.safetensors",
102
  "language_model.model.layers.15.feed_forward.router.weight": "model-00017-of-00050.safetensors",
103
  "language_model.model.layers.15.feed_forward.shared_expert.down_proj.weight": "model-00017-of-00050.safetensors",
104
  "language_model.model.layers.15.feed_forward.shared_expert.gate_proj.weight": "model-00017-of-00050.safetensors",
 
110
  "language_model.model.layers.15.self_attn.q_proj.weight": "model-00016-of-00050.safetensors",
111
  "language_model.model.layers.15.self_attn.v_proj.weight": "model-00016-of-00050.safetensors",
112
  "language_model.model.layers.16.feed_forward.experts.down_proj.weight": "model-00018-of-00050.safetensors",
113
+ "language_model.model.layers.16.feed_forward.experts.gate_proj.weight": "model-00018-of-00050.safetensors",
114
+ "language_model.model.layers.16.feed_forward.experts.up_proj.weight": "model-00018-of-00050.safetensors",
115
  "language_model.model.layers.16.feed_forward.router.weight": "model-00018-of-00050.safetensors",
116
  "language_model.model.layers.16.feed_forward.shared_expert.down_proj.weight": "model-00018-of-00050.safetensors",
117
  "language_model.model.layers.16.feed_forward.shared_expert.gate_proj.weight": "model-00018-of-00050.safetensors",
 
123
  "language_model.model.layers.16.self_attn.q_proj.weight": "model-00017-of-00050.safetensors",
124
  "language_model.model.layers.16.self_attn.v_proj.weight": "model-00017-of-00050.safetensors",
125
  "language_model.model.layers.17.feed_forward.experts.down_proj.weight": "model-00019-of-00050.safetensors",
126
+ "language_model.model.layers.17.feed_forward.experts.gate_proj.weight": "model-00019-of-00050.safetensors",
127
+ "language_model.model.layers.17.feed_forward.experts.up_proj.weight": "model-00019-of-00050.safetensors",
128
  "language_model.model.layers.17.feed_forward.router.weight": "model-00019-of-00050.safetensors",
129
  "language_model.model.layers.17.feed_forward.shared_expert.down_proj.weight": "model-00019-of-00050.safetensors",
130
  "language_model.model.layers.17.feed_forward.shared_expert.gate_proj.weight": "model-00019-of-00050.safetensors",
 
136
  "language_model.model.layers.17.self_attn.q_proj.weight": "model-00018-of-00050.safetensors",
137
  "language_model.model.layers.17.self_attn.v_proj.weight": "model-00018-of-00050.safetensors",
138
  "language_model.model.layers.18.feed_forward.experts.down_proj.weight": "model-00020-of-00050.safetensors",
139
+ "language_model.model.layers.18.feed_forward.experts.gate_proj.weight": "model-00020-of-00050.safetensors",
140
+ "language_model.model.layers.18.feed_forward.experts.up_proj.weight": "model-00020-of-00050.safetensors",
141
  "language_model.model.layers.18.feed_forward.router.weight": "model-00020-of-00050.safetensors",
142
  "language_model.model.layers.18.feed_forward.shared_expert.down_proj.weight": "model-00020-of-00050.safetensors",
143
  "language_model.model.layers.18.feed_forward.shared_expert.gate_proj.weight": "model-00020-of-00050.safetensors",
 
149
  "language_model.model.layers.18.self_attn.q_proj.weight": "model-00019-of-00050.safetensors",
150
  "language_model.model.layers.18.self_attn.v_proj.weight": "model-00019-of-00050.safetensors",
151
  "language_model.model.layers.19.feed_forward.experts.down_proj.weight": "model-00021-of-00050.safetensors",
152
+ "language_model.model.layers.19.feed_forward.experts.gate_proj.weight": "model-00021-of-00050.safetensors",
153
+ "language_model.model.layers.19.feed_forward.experts.up_proj.weight": "model-00021-of-00050.safetensors",
154
  "language_model.model.layers.19.feed_forward.router.weight": "model-00021-of-00050.safetensors",
155
  "language_model.model.layers.19.feed_forward.shared_expert.down_proj.weight": "model-00021-of-00050.safetensors",
156
  "language_model.model.layers.19.feed_forward.shared_expert.gate_proj.weight": "model-00021-of-00050.safetensors",
 
162
  "language_model.model.layers.19.self_attn.q_proj.weight": "model-00020-of-00050.safetensors",
163
  "language_model.model.layers.19.self_attn.v_proj.weight": "model-00020-of-00050.safetensors",
164
  "language_model.model.layers.2.feed_forward.experts.down_proj.weight": "model-00004-of-00050.safetensors",
165
+ "language_model.model.layers.2.feed_forward.experts.gate_proj.weight": "model-00004-of-00050.safetensors",
166
+ "language_model.model.layers.2.feed_forward.experts.up_proj.weight": "model-00004-of-00050.safetensors",
167
  "language_model.model.layers.2.feed_forward.router.weight": "model-00004-of-00050.safetensors",
168
  "language_model.model.layers.2.feed_forward.shared_expert.down_proj.weight": "model-00004-of-00050.safetensors",
169
  "language_model.model.layers.2.feed_forward.shared_expert.gate_proj.weight": "model-00004-of-00050.safetensors",
 
175
  "language_model.model.layers.2.self_attn.q_proj.weight": "model-00003-of-00050.safetensors",
176
  "language_model.model.layers.2.self_attn.v_proj.weight": "model-00003-of-00050.safetensors",
177
  "language_model.model.layers.20.feed_forward.experts.down_proj.weight": "model-00022-of-00050.safetensors",
178
+ "language_model.model.layers.20.feed_forward.experts.gate_proj.weight": "model-00022-of-00050.safetensors",
179
+ "language_model.model.layers.20.feed_forward.experts.up_proj.weight": "model-00022-of-00050.safetensors",
180
  "language_model.model.layers.20.feed_forward.router.weight": "model-00022-of-00050.safetensors",
181
  "language_model.model.layers.20.feed_forward.shared_expert.down_proj.weight": "model-00022-of-00050.safetensors",
182
  "language_model.model.layers.20.feed_forward.shared_expert.gate_proj.weight": "model-00022-of-00050.safetensors",
 
188
  "language_model.model.layers.20.self_attn.q_proj.weight": "model-00021-of-00050.safetensors",
189
  "language_model.model.layers.20.self_attn.v_proj.weight": "model-00021-of-00050.safetensors",
190
  "language_model.model.layers.21.feed_forward.experts.down_proj.weight": "model-00023-of-00050.safetensors",
191
+ "language_model.model.layers.21.feed_forward.experts.gate_proj.weight": "model-00023-of-00050.safetensors",
192
+ "language_model.model.layers.21.feed_forward.experts.up_proj.weight": "model-00023-of-00050.safetensors",
193
  "language_model.model.layers.21.feed_forward.router.weight": "model-00023-of-00050.safetensors",
194
  "language_model.model.layers.21.feed_forward.shared_expert.down_proj.weight": "model-00023-of-00050.safetensors",
195
  "language_model.model.layers.21.feed_forward.shared_expert.gate_proj.weight": "model-00023-of-00050.safetensors",
 
201
  "language_model.model.layers.21.self_attn.q_proj.weight": "model-00022-of-00050.safetensors",
202
  "language_model.model.layers.21.self_attn.v_proj.weight": "model-00022-of-00050.safetensors",
203
  "language_model.model.layers.22.feed_forward.experts.down_proj.weight": "model-00024-of-00050.safetensors",
204
+ "language_model.model.layers.22.feed_forward.experts.gate_proj.weight": "model-00024-of-00050.safetensors",
205
+ "language_model.model.layers.22.feed_forward.experts.up_proj.weight": "model-00024-of-00050.safetensors",
206
  "language_model.model.layers.22.feed_forward.router.weight": "model-00024-of-00050.safetensors",
207
  "language_model.model.layers.22.feed_forward.shared_expert.down_proj.weight": "model-00024-of-00050.safetensors",
208
  "language_model.model.layers.22.feed_forward.shared_expert.gate_proj.weight": "model-00024-of-00050.safetensors",
 
214
  "language_model.model.layers.22.self_attn.q_proj.weight": "model-00023-of-00050.safetensors",
215
  "language_model.model.layers.22.self_attn.v_proj.weight": "model-00023-of-00050.safetensors",
216
  "language_model.model.layers.23.feed_forward.experts.down_proj.weight": "model-00025-of-00050.safetensors",
217
+ "language_model.model.layers.23.feed_forward.experts.gate_proj.weight": "model-00025-of-00050.safetensors",
218
+ "language_model.model.layers.23.feed_forward.experts.up_proj.weight": "model-00025-of-00050.safetensors",
219
  "language_model.model.layers.23.feed_forward.router.weight": "model-00025-of-00050.safetensors",
220
  "language_model.model.layers.23.feed_forward.shared_expert.down_proj.weight": "model-00025-of-00050.safetensors",
221
  "language_model.model.layers.23.feed_forward.shared_expert.gate_proj.weight": "model-00025-of-00050.safetensors",
 
227
  "language_model.model.layers.23.self_attn.q_proj.weight": "model-00024-of-00050.safetensors",
228
  "language_model.model.layers.23.self_attn.v_proj.weight": "model-00024-of-00050.safetensors",
229
  "language_model.model.layers.24.feed_forward.experts.down_proj.weight": "model-00026-of-00050.safetensors",
230
+ "language_model.model.layers.24.feed_forward.experts.gate_proj.weight": "model-00026-of-00050.safetensors",
231
+ "language_model.model.layers.24.feed_forward.experts.up_proj.weight": "model-00026-of-00050.safetensors",
232
  "language_model.model.layers.24.feed_forward.router.weight": "model-00026-of-00050.safetensors",
233
  "language_model.model.layers.24.feed_forward.shared_expert.down_proj.weight": "model-00026-of-00050.safetensors",
234
  "language_model.model.layers.24.feed_forward.shared_expert.gate_proj.weight": "model-00026-of-00050.safetensors",
 
240
  "language_model.model.layers.24.self_attn.q_proj.weight": "model-00025-of-00050.safetensors",
241
  "language_model.model.layers.24.self_attn.v_proj.weight": "model-00025-of-00050.safetensors",
242
  "language_model.model.layers.25.feed_forward.experts.down_proj.weight": "model-00027-of-00050.safetensors",
243
+ "language_model.model.layers.25.feed_forward.experts.gate_proj.weight": "model-00027-of-00050.safetensors",
244
+ "language_model.model.layers.25.feed_forward.experts.up_proj.weight": "model-00027-of-00050.safetensors",
245
  "language_model.model.layers.25.feed_forward.router.weight": "model-00027-of-00050.safetensors",
246
  "language_model.model.layers.25.feed_forward.shared_expert.down_proj.weight": "model-00027-of-00050.safetensors",
247
  "language_model.model.layers.25.feed_forward.shared_expert.gate_proj.weight": "model-00027-of-00050.safetensors",
 
253
  "language_model.model.layers.25.self_attn.q_proj.weight": "model-00026-of-00050.safetensors",
254
  "language_model.model.layers.25.self_attn.v_proj.weight": "model-00026-of-00050.safetensors",
255
  "language_model.model.layers.26.feed_forward.experts.down_proj.weight": "model-00028-of-00050.safetensors",
256
+ "language_model.model.layers.26.feed_forward.experts.gate_proj.weight": "model-00028-of-00050.safetensors",
257
+ "language_model.model.layers.26.feed_forward.experts.up_proj.weight": "model-00028-of-00050.safetensors",
258
  "language_model.model.layers.26.feed_forward.router.weight": "model-00028-of-00050.safetensors",
259
  "language_model.model.layers.26.feed_forward.shared_expert.down_proj.weight": "model-00028-of-00050.safetensors",
260
  "language_model.model.layers.26.feed_forward.shared_expert.gate_proj.weight": "model-00028-of-00050.safetensors",
 
266
  "language_model.model.layers.26.self_attn.q_proj.weight": "model-00027-of-00050.safetensors",
267
  "language_model.model.layers.26.self_attn.v_proj.weight": "model-00027-of-00050.safetensors",
268
  "language_model.model.layers.27.feed_forward.experts.down_proj.weight": "model-00029-of-00050.safetensors",
269
+ "language_model.model.layers.27.feed_forward.experts.gate_proj.weight": "model-00029-of-00050.safetensors",
270
+ "language_model.model.layers.27.feed_forward.experts.up_proj.weight": "model-00029-of-00050.safetensors",
271
  "language_model.model.layers.27.feed_forward.router.weight": "model-00029-of-00050.safetensors",
272
  "language_model.model.layers.27.feed_forward.shared_expert.down_proj.weight": "model-00029-of-00050.safetensors",
273
  "language_model.model.layers.27.feed_forward.shared_expert.gate_proj.weight": "model-00029-of-00050.safetensors",
 
279
  "language_model.model.layers.27.self_attn.q_proj.weight": "model-00028-of-00050.safetensors",
280
  "language_model.model.layers.27.self_attn.v_proj.weight": "model-00028-of-00050.safetensors",
281
  "language_model.model.layers.28.feed_forward.experts.down_proj.weight": "model-00030-of-00050.safetensors",
282
+ "language_model.model.layers.28.feed_forward.experts.gate_proj.weight": "model-00030-of-00050.safetensors",
283
+ "language_model.model.layers.28.feed_forward.experts.up_proj.weight": "model-00030-of-00050.safetensors",
284
  "language_model.model.layers.28.feed_forward.router.weight": "model-00030-of-00050.safetensors",
285
  "language_model.model.layers.28.feed_forward.shared_expert.down_proj.weight": "model-00030-of-00050.safetensors",
286
  "language_model.model.layers.28.feed_forward.shared_expert.gate_proj.weight": "model-00030-of-00050.safetensors",
 
292
  "language_model.model.layers.28.self_attn.q_proj.weight": "model-00029-of-00050.safetensors",
293
  "language_model.model.layers.28.self_attn.v_proj.weight": "model-00029-of-00050.safetensors",
294
  "language_model.model.layers.29.feed_forward.experts.down_proj.weight": "model-00031-of-00050.safetensors",
295
+ "language_model.model.layers.29.feed_forward.experts.gate_proj.weight": "model-00031-of-00050.safetensors",
296
+ "language_model.model.layers.29.feed_forward.experts.up_proj.weight": "model-00031-of-00050.safetensors",
297
  "language_model.model.layers.29.feed_forward.router.weight": "model-00031-of-00050.safetensors",
298
  "language_model.model.layers.29.feed_forward.shared_expert.down_proj.weight": "model-00031-of-00050.safetensors",
299
  "language_model.model.layers.29.feed_forward.shared_expert.gate_proj.weight": "model-00031-of-00050.safetensors",
 
305
  "language_model.model.layers.29.self_attn.q_proj.weight": "model-00030-of-00050.safetensors",
306
  "language_model.model.layers.29.self_attn.v_proj.weight": "model-00030-of-00050.safetensors",
307
  "language_model.model.layers.3.feed_forward.experts.down_proj.weight": "model-00005-of-00050.safetensors",
308
+ "language_model.model.layers.3.feed_forward.experts.gate_proj.weight": "model-00005-of-00050.safetensors",
309
+ "language_model.model.layers.3.feed_forward.experts.up_proj.weight": "model-00005-of-00050.safetensors",
310
  "language_model.model.layers.3.feed_forward.router.weight": "model-00005-of-00050.safetensors",
311
  "language_model.model.layers.3.feed_forward.shared_expert.down_proj.weight": "model-00005-of-00050.safetensors",
312
  "language_model.model.layers.3.feed_forward.shared_expert.gate_proj.weight": "model-00005-of-00050.safetensors",
 
318
  "language_model.model.layers.3.self_attn.q_proj.weight": "model-00004-of-00050.safetensors",
319
  "language_model.model.layers.3.self_attn.v_proj.weight": "model-00004-of-00050.safetensors",
320
  "language_model.model.layers.30.feed_forward.experts.down_proj.weight": "model-00032-of-00050.safetensors",
321
+ "language_model.model.layers.30.feed_forward.experts.gate_proj.weight": "model-00032-of-00050.safetensors",
322
+ "language_model.model.layers.30.feed_forward.experts.up_proj.weight": "model-00032-of-00050.safetensors",
323
  "language_model.model.layers.30.feed_forward.router.weight": "model-00032-of-00050.safetensors",
324
  "language_model.model.layers.30.feed_forward.shared_expert.down_proj.weight": "model-00032-of-00050.safetensors",
325
  "language_model.model.layers.30.feed_forward.shared_expert.gate_proj.weight": "model-00032-of-00050.safetensors",
 
331
  "language_model.model.layers.30.self_attn.q_proj.weight": "model-00031-of-00050.safetensors",
332
  "language_model.model.layers.30.self_attn.v_proj.weight": "model-00031-of-00050.safetensors",
333
  "language_model.model.layers.31.feed_forward.experts.down_proj.weight": "model-00033-of-00050.safetensors",
334
+ "language_model.model.layers.31.feed_forward.experts.gate_proj.weight": "model-00033-of-00050.safetensors",
335
+ "language_model.model.layers.31.feed_forward.experts.up_proj.weight": "model-00033-of-00050.safetensors",
336
  "language_model.model.layers.31.feed_forward.router.weight": "model-00033-of-00050.safetensors",
337
  "language_model.model.layers.31.feed_forward.shared_expert.down_proj.weight": "model-00033-of-00050.safetensors",
338
  "language_model.model.layers.31.feed_forward.shared_expert.gate_proj.weight": "model-00033-of-00050.safetensors",
 
344
  "language_model.model.layers.31.self_attn.q_proj.weight": "model-00032-of-00050.safetensors",
345
  "language_model.model.layers.31.self_attn.v_proj.weight": "model-00032-of-00050.safetensors",
346
  "language_model.model.layers.32.feed_forward.experts.down_proj.weight": "model-00034-of-00050.safetensors",
347
+ "language_model.model.layers.32.feed_forward.experts.gate_proj.weight": "model-00034-of-00050.safetensors",
348
+ "language_model.model.layers.32.feed_forward.experts.up_proj.weight": "model-00034-of-00050.safetensors",
349
  "language_model.model.layers.32.feed_forward.router.weight": "model-00034-of-00050.safetensors",
350
  "language_model.model.layers.32.feed_forward.shared_expert.down_proj.weight": "model-00034-of-00050.safetensors",
351
  "language_model.model.layers.32.feed_forward.shared_expert.gate_proj.weight": "model-00034-of-00050.safetensors",
 
357
  "language_model.model.layers.32.self_attn.q_proj.weight": "model-00033-of-00050.safetensors",
358
  "language_model.model.layers.32.self_attn.v_proj.weight": "model-00033-of-00050.safetensors",
359
  "language_model.model.layers.33.feed_forward.experts.down_proj.weight": "model-00035-of-00050.safetensors",
360
+ "language_model.model.layers.33.feed_forward.experts.gate_proj.weight": "model-00035-of-00050.safetensors",
361
+ "language_model.model.layers.33.feed_forward.experts.up_proj.weight": "model-00035-of-00050.safetensors",
362
  "language_model.model.layers.33.feed_forward.router.weight": "model-00035-of-00050.safetensors",
363
  "language_model.model.layers.33.feed_forward.shared_expert.down_proj.weight": "model-00035-of-00050.safetensors",
364
  "language_model.model.layers.33.feed_forward.shared_expert.gate_proj.weight": "model-00035-of-00050.safetensors",
 
370
  "language_model.model.layers.33.self_attn.q_proj.weight": "model-00034-of-00050.safetensors",
371
  "language_model.model.layers.33.self_attn.v_proj.weight": "model-00034-of-00050.safetensors",
372
  "language_model.model.layers.34.feed_forward.experts.down_proj.weight": "model-00036-of-00050.safetensors",
373
+ "language_model.model.layers.34.feed_forward.experts.gate_proj.weight": "model-00036-of-00050.safetensors",
374
+ "language_model.model.layers.34.feed_forward.experts.up_proj.weight": "model-00036-of-00050.safetensors",
375
  "language_model.model.layers.34.feed_forward.router.weight": "model-00036-of-00050.safetensors",
376
  "language_model.model.layers.34.feed_forward.shared_expert.down_proj.weight": "model-00036-of-00050.safetensors",
377
  "language_model.model.layers.34.feed_forward.shared_expert.gate_proj.weight": "model-00036-of-00050.safetensors",
 
383
  "language_model.model.layers.34.self_attn.q_proj.weight": "model-00035-of-00050.safetensors",
384
  "language_model.model.layers.34.self_attn.v_proj.weight": "model-00035-of-00050.safetensors",
385
  "language_model.model.layers.35.feed_forward.experts.down_proj.weight": "model-00037-of-00050.safetensors",
386
+ "language_model.model.layers.35.feed_forward.experts.gate_proj.weight": "model-00037-of-00050.safetensors",
387
+ "language_model.model.layers.35.feed_forward.experts.up_proj.weight": "model-00037-of-00050.safetensors",
388
  "language_model.model.layers.35.feed_forward.router.weight": "model-00037-of-00050.safetensors",
389
  "language_model.model.layers.35.feed_forward.shared_expert.down_proj.weight": "model-00037-of-00050.safetensors",
390
  "language_model.model.layers.35.feed_forward.shared_expert.gate_proj.weight": "model-00037-of-00050.safetensors",
 
396
  "language_model.model.layers.35.self_attn.q_proj.weight": "model-00036-of-00050.safetensors",
397
  "language_model.model.layers.35.self_attn.v_proj.weight": "model-00036-of-00050.safetensors",
398
  "language_model.model.layers.36.feed_forward.experts.down_proj.weight": "model-00038-of-00050.safetensors",
399
+ "language_model.model.layers.36.feed_forward.experts.gate_proj.weight": "model-00038-of-00050.safetensors",
400
+ "language_model.model.layers.36.feed_forward.experts.up_proj.weight": "model-00038-of-00050.safetensors",
401
  "language_model.model.layers.36.feed_forward.router.weight": "model-00038-of-00050.safetensors",
402
  "language_model.model.layers.36.feed_forward.shared_expert.down_proj.weight": "model-00038-of-00050.safetensors",
403
  "language_model.model.layers.36.feed_forward.shared_expert.gate_proj.weight": "model-00038-of-00050.safetensors",
 
409
  "language_model.model.layers.36.self_attn.q_proj.weight": "model-00037-of-00050.safetensors",
410
  "language_model.model.layers.36.self_attn.v_proj.weight": "model-00037-of-00050.safetensors",
411
  "language_model.model.layers.37.feed_forward.experts.down_proj.weight": "model-00039-of-00050.safetensors",
412
+ "language_model.model.layers.37.feed_forward.experts.gate_proj.weight": "model-00039-of-00050.safetensors",
413
+ "language_model.model.layers.37.feed_forward.experts.up_proj.weight": "model-00039-of-00050.safetensors",
414
  "language_model.model.layers.37.feed_forward.router.weight": "model-00039-of-00050.safetensors",
415
  "language_model.model.layers.37.feed_forward.shared_expert.down_proj.weight": "model-00039-of-00050.safetensors",
416
  "language_model.model.layers.37.feed_forward.shared_expert.gate_proj.weight": "model-00039-of-00050.safetensors",
 
422
  "language_model.model.layers.37.self_attn.q_proj.weight": "model-00038-of-00050.safetensors",
423
  "language_model.model.layers.37.self_attn.v_proj.weight": "model-00038-of-00050.safetensors",
424
  "language_model.model.layers.38.feed_forward.experts.down_proj.weight": "model-00040-of-00050.safetensors",
425
+ "language_model.model.layers.38.feed_forward.experts.gate_proj.weight": "model-00040-of-00050.safetensors",
426
+ "language_model.model.layers.38.feed_forward.experts.up_proj.weight": "model-00040-of-00050.safetensors",
427
  "language_model.model.layers.38.feed_forward.router.weight": "model-00040-of-00050.safetensors",
428
  "language_model.model.layers.38.feed_forward.shared_expert.down_proj.weight": "model-00040-of-00050.safetensors",
429
  "language_model.model.layers.38.feed_forward.shared_expert.gate_proj.weight": "model-00040-of-00050.safetensors",
 
435
  "language_model.model.layers.38.self_attn.q_proj.weight": "model-00039-of-00050.safetensors",
436
  "language_model.model.layers.38.self_attn.v_proj.weight": "model-00039-of-00050.safetensors",
437
  "language_model.model.layers.39.feed_forward.experts.down_proj.weight": "model-00041-of-00050.safetensors",
438
+ "language_model.model.layers.39.feed_forward.experts.gate_proj.weight": "model-00041-of-00050.safetensors",
439
+ "language_model.model.layers.39.feed_forward.experts.up_proj.weight": "model-00041-of-00050.safetensors",
440
  "language_model.model.layers.39.feed_forward.router.weight": "model-00041-of-00050.safetensors",
441
  "language_model.model.layers.39.feed_forward.shared_expert.down_proj.weight": "model-00041-of-00050.safetensors",
442
  "language_model.model.layers.39.feed_forward.shared_expert.gate_proj.weight": "model-00041-of-00050.safetensors",
 
448
  "language_model.model.layers.39.self_attn.q_proj.weight": "model-00040-of-00050.safetensors",
449
  "language_model.model.layers.39.self_attn.v_proj.weight": "model-00040-of-00050.safetensors",
450
  "language_model.model.layers.4.feed_forward.experts.down_proj.weight": "model-00006-of-00050.safetensors",
451
+ "language_model.model.layers.4.feed_forward.experts.gate_proj.weight": "model-00006-of-00050.safetensors",
452
+ "language_model.model.layers.4.feed_forward.experts.up_proj.weight": "model-00006-of-00050.safetensors",
453
  "language_model.model.layers.4.feed_forward.router.weight": "model-00006-of-00050.safetensors",
454
  "language_model.model.layers.4.feed_forward.shared_expert.down_proj.weight": "model-00006-of-00050.safetensors",
455
  "language_model.model.layers.4.feed_forward.shared_expert.gate_proj.weight": "model-00006-of-00050.safetensors",
 
461
  "language_model.model.layers.4.self_attn.q_proj.weight": "model-00005-of-00050.safetensors",
462
  "language_model.model.layers.4.self_attn.v_proj.weight": "model-00005-of-00050.safetensors",
463
  "language_model.model.layers.40.feed_forward.experts.down_proj.weight": "model-00042-of-00050.safetensors",
464
+ "language_model.model.layers.40.feed_forward.experts.gate_proj.weight": "model-00042-of-00050.safetensors",
465
+ "language_model.model.layers.40.feed_forward.experts.up_proj.weight": "model-00042-of-00050.safetensors",
466
  "language_model.model.layers.40.feed_forward.router.weight": "model-00042-of-00050.safetensors",
467
  "language_model.model.layers.40.feed_forward.shared_expert.down_proj.weight": "model-00042-of-00050.safetensors",
468
  "language_model.model.layers.40.feed_forward.shared_expert.gate_proj.weight": "model-00042-of-00050.safetensors",
 
474
  "language_model.model.layers.40.self_attn.q_proj.weight": "model-00041-of-00050.safetensors",
475
  "language_model.model.layers.40.self_attn.v_proj.weight": "model-00041-of-00050.safetensors",
476
  "language_model.model.layers.41.feed_forward.experts.down_proj.weight": "model-00043-of-00050.safetensors",
477
+ "language_model.model.layers.41.feed_forward.experts.gate_proj.weight": "model-00043-of-00050.safetensors",
478
+ "language_model.model.layers.41.feed_forward.experts.up_proj.weight": "model-00043-of-00050.safetensors",
479
  "language_model.model.layers.41.feed_forward.router.weight": "model-00043-of-00050.safetensors",
480
  "language_model.model.layers.41.feed_forward.shared_expert.down_proj.weight": "model-00043-of-00050.safetensors",
481
  "language_model.model.layers.41.feed_forward.shared_expert.gate_proj.weight": "model-00043-of-00050.safetensors",
 
487
  "language_model.model.layers.41.self_attn.q_proj.weight": "model-00042-of-00050.safetensors",
488
  "language_model.model.layers.41.self_attn.v_proj.weight": "model-00042-of-00050.safetensors",
489
  "language_model.model.layers.42.feed_forward.experts.down_proj.weight": "model-00044-of-00050.safetensors",
490
+ "language_model.model.layers.42.feed_forward.experts.gate_proj.weight": "model-00044-of-00050.safetensors",
491
+ "language_model.model.layers.42.feed_forward.experts.up_proj.weight": "model-00044-of-00050.safetensors",
492
  "language_model.model.layers.42.feed_forward.router.weight": "model-00044-of-00050.safetensors",
493
  "language_model.model.layers.42.feed_forward.shared_expert.down_proj.weight": "model-00044-of-00050.safetensors",
494
  "language_model.model.layers.42.feed_forward.shared_expert.gate_proj.weight": "model-00044-of-00050.safetensors",
 
500
  "language_model.model.layers.42.self_attn.q_proj.weight": "model-00043-of-00050.safetensors",
501
  "language_model.model.layers.42.self_attn.v_proj.weight": "model-00043-of-00050.safetensors",
502
  "language_model.model.layers.43.feed_forward.experts.down_proj.weight": "model-00045-of-00050.safetensors",
503
+ "language_model.model.layers.43.feed_forward.experts.gate_proj.weight": "model-00045-of-00050.safetensors",
504
+ "language_model.model.layers.43.feed_forward.experts.up_proj.weight": "model-00045-of-00050.safetensors",
505
  "language_model.model.layers.43.feed_forward.router.weight": "model-00045-of-00050.safetensors",
506
  "language_model.model.layers.43.feed_forward.shared_expert.down_proj.weight": "model-00045-of-00050.safetensors",
507
  "language_model.model.layers.43.feed_forward.shared_expert.gate_proj.weight": "model-00045-of-00050.safetensors",
 
513
  "language_model.model.layers.43.self_attn.q_proj.weight": "model-00044-of-00050.safetensors",
514
  "language_model.model.layers.43.self_attn.v_proj.weight": "model-00044-of-00050.safetensors",
515
  "language_model.model.layers.44.feed_forward.experts.down_proj.weight": "model-00046-of-00050.safetensors",
516
+ "language_model.model.layers.44.feed_forward.experts.gate_proj.weight": "model-00046-of-00050.safetensors",
517
+ "language_model.model.layers.44.feed_forward.experts.up_proj.weight": "model-00046-of-00050.safetensors",
518
  "language_model.model.layers.44.feed_forward.router.weight": "model-00046-of-00050.safetensors",
519
  "language_model.model.layers.44.feed_forward.shared_expert.down_proj.weight": "model-00046-of-00050.safetensors",
520
  "language_model.model.layers.44.feed_forward.shared_expert.gate_proj.weight": "model-00046-of-00050.safetensors",
 
526
  "language_model.model.layers.44.self_attn.q_proj.weight": "model-00045-of-00050.safetensors",
527
  "language_model.model.layers.44.self_attn.v_proj.weight": "model-00045-of-00050.safetensors",
528
  "language_model.model.layers.45.feed_forward.experts.down_proj.weight": "model-00047-of-00050.safetensors",
529
+ "language_model.model.layers.45.feed_forward.experts.gate_proj.weight": "model-00047-of-00050.safetensors",
530
+ "language_model.model.layers.45.feed_forward.experts.up_proj.weight": "model-00047-of-00050.safetensors",
531
  "language_model.model.layers.45.feed_forward.router.weight": "model-00047-of-00050.safetensors",
532
  "language_model.model.layers.45.feed_forward.shared_expert.down_proj.weight": "model-00047-of-00050.safetensors",
533
  "language_model.model.layers.45.feed_forward.shared_expert.gate_proj.weight": "model-00047-of-00050.safetensors",
 
539
  "language_model.model.layers.45.self_attn.q_proj.weight": "model-00046-of-00050.safetensors",
540
  "language_model.model.layers.45.self_attn.v_proj.weight": "model-00046-of-00050.safetensors",
541
  "language_model.model.layers.46.feed_forward.experts.down_proj.weight": "model-00048-of-00050.safetensors",
542
+ "language_model.model.layers.46.feed_forward.experts.gate_proj.weight": "model-00048-of-00050.safetensors",
543
+ "language_model.model.layers.46.feed_forward.experts.up_proj.weight": "model-00048-of-00050.safetensors",
544
  "language_model.model.layers.46.feed_forward.router.weight": "model-00048-of-00050.safetensors",
545
  "language_model.model.layers.46.feed_forward.shared_expert.down_proj.weight": "model-00048-of-00050.safetensors",
546
  "language_model.model.layers.46.feed_forward.shared_expert.gate_proj.weight": "model-00048-of-00050.safetensors",
 
552
  "language_model.model.layers.46.self_attn.q_proj.weight": "model-00047-of-00050.safetensors",
553
  "language_model.model.layers.46.self_attn.v_proj.weight": "model-00047-of-00050.safetensors",
554
  "language_model.model.layers.47.feed_forward.experts.down_proj.weight": "model-00049-of-00050.safetensors",
555
+ "language_model.model.layers.47.feed_forward.experts.gate_proj.weight": "model-00049-of-00050.safetensors",
556
+ "language_model.model.layers.47.feed_forward.experts.up_proj.weight": "model-00049-of-00050.safetensors",
557
  "language_model.model.layers.47.feed_forward.router.weight": "model-00049-of-00050.safetensors",
558
  "language_model.model.layers.47.feed_forward.shared_expert.down_proj.weight": "model-00049-of-00050.safetensors",
559
  "language_model.model.layers.47.feed_forward.shared_expert.gate_proj.weight": "model-00049-of-00050.safetensors",
 
565
  "language_model.model.layers.47.self_attn.q_proj.weight": "model-00048-of-00050.safetensors",
566
  "language_model.model.layers.47.self_attn.v_proj.weight": "model-00048-of-00050.safetensors",
567
  "language_model.model.layers.5.feed_forward.experts.down_proj.weight": "model-00007-of-00050.safetensors",
568
+ "language_model.model.layers.5.feed_forward.experts.gate_proj.weight": "model-00007-of-00050.safetensors",
569
+ "language_model.model.layers.5.feed_forward.experts.up_proj.weight": "model-00007-of-00050.safetensors",
570
  "language_model.model.layers.5.feed_forward.router.weight": "model-00007-of-00050.safetensors",
571
  "language_model.model.layers.5.feed_forward.shared_expert.down_proj.weight": "model-00007-of-00050.safetensors",
572
  "language_model.model.layers.5.feed_forward.shared_expert.gate_proj.weight": "model-00007-of-00050.safetensors",
 
578
  "language_model.model.layers.5.self_attn.q_proj.weight": "model-00006-of-00050.safetensors",
579
  "language_model.model.layers.5.self_attn.v_proj.weight": "model-00006-of-00050.safetensors",
580
  "language_model.model.layers.6.feed_forward.experts.down_proj.weight": "model-00008-of-00050.safetensors",
581
+ "language_model.model.layers.6.feed_forward.experts.gate_proj.weight": "model-00008-of-00050.safetensors",
582
+ "language_model.model.layers.6.feed_forward.experts.up_proj.weight": "model-00008-of-00050.safetensors",
583
  "language_model.model.layers.6.feed_forward.router.weight": "model-00008-of-00050.safetensors",
584
  "language_model.model.layers.6.feed_forward.shared_expert.down_proj.weight": "model-00008-of-00050.safetensors",
585
  "language_model.model.layers.6.feed_forward.shared_expert.gate_proj.weight": "model-00008-of-00050.safetensors",
 
591
  "language_model.model.layers.6.self_attn.q_proj.weight": "model-00007-of-00050.safetensors",
592
  "language_model.model.layers.6.self_attn.v_proj.weight": "model-00007-of-00050.safetensors",
593
  "language_model.model.layers.7.feed_forward.experts.down_proj.weight": "model-00009-of-00050.safetensors",
594
+ "language_model.model.layers.7.feed_forward.experts.gate_proj.weight": "model-00009-of-00050.safetensors",
595
+ "language_model.model.layers.7.feed_forward.experts.up_proj.weight": "model-00009-of-00050.safetensors",
596
  "language_model.model.layers.7.feed_forward.router.weight": "model-00009-of-00050.safetensors",
597
  "language_model.model.layers.7.feed_forward.shared_expert.down_proj.weight": "model-00009-of-00050.safetensors",
598
  "language_model.model.layers.7.feed_forward.shared_expert.gate_proj.weight": "model-00009-of-00050.safetensors",
 
604
  "language_model.model.layers.7.self_attn.q_proj.weight": "model-00008-of-00050.safetensors",
605
  "language_model.model.layers.7.self_attn.v_proj.weight": "model-00008-of-00050.safetensors",
606
  "language_model.model.layers.8.feed_forward.experts.down_proj.weight": "model-00010-of-00050.safetensors",
607
+ "language_model.model.layers.8.feed_forward.experts.gate_proj.weight": "model-00010-of-00050.safetensors",
608
+ "language_model.model.layers.8.feed_forward.experts.up_proj.weight": "model-00010-of-00050.safetensors",
609
  "language_model.model.layers.8.feed_forward.router.weight": "model-00010-of-00050.safetensors",
610
  "language_model.model.layers.8.feed_forward.shared_expert.down_proj.weight": "model-00010-of-00050.safetensors",
611
  "language_model.model.layers.8.feed_forward.shared_expert.gate_proj.weight": "model-00010-of-00050.safetensors",
 
617
  "language_model.model.layers.8.self_attn.q_proj.weight": "model-00009-of-00050.safetensors",
618
  "language_model.model.layers.8.self_attn.v_proj.weight": "model-00009-of-00050.safetensors",
619
  "language_model.model.layers.9.feed_forward.experts.down_proj.weight": "model-00011-of-00050.safetensors",
620
+ "language_model.model.layers.9.feed_forward.experts.gate_proj.weight": "model-00011-of-00050.safetensors",
621
+ "language_model.model.layers.9.feed_forward.experts.up_proj.weight": "model-00011-of-00050.safetensors",
622
  "language_model.model.layers.9.feed_forward.router.weight": "model-00011-of-00050.safetensors",
623
  "language_model.model.layers.9.feed_forward.shared_expert.down_proj.weight": "model-00011-of-00050.safetensors",
624
  "language_model.model.layers.9.feed_forward.shared_expert.gate_proj.weight": "model-00011-of-00050.safetensors",