IvanHU commited on
Commit
b9efa75
·
verified ·
1 Parent(s): 715bc86

Upload folder using huggingface_hub

Browse files
Files changed (21) hide show
  1. .gitattributes +17 -0
  2. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata +3 -0
  3. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp +3 -0
  4. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp +3 -0
  5. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp +3 -0
  6. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp +3 -0
  7. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp +3 -0
  8. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp +3 -0
  9. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp +3 -0
  10. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp +3 -0
  11. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp +3 -0
  12. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp +3 -0
  13. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp +3 -0
  14. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp +3 -0
  15. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp +3 -0
  16. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp +3 -0
  17. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp +3 -0
  18. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp +3 -0
  19. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/common.pt +3 -0
  20. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/metadata.json +1 -0
  21. model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/latest_checkpointed_iteration.txt +1 -0
.gitattributes CHANGED
@@ -491,3 +491,20 @@ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-
491
  model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text
492
  model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
493
  model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
491
  model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text
492
  model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
493
  model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.001-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text
494
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata filter=lfs diff=lfs merge=lfs -text
495
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
496
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp filter=lfs diff=lfs merge=lfs -text
497
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
498
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp filter=lfs diff=lfs merge=lfs -text
499
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
500
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp filter=lfs diff=lfs merge=lfs -text
501
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
502
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp filter=lfs diff=lfs merge=lfs -text
503
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
504
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp filter=lfs diff=lfs merge=lfs -text
505
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
506
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp filter=lfs diff=lfs merge=lfs -text
507
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
508
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp filter=lfs diff=lfs merge=lfs -text
509
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
510
+ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp filter=lfs diff=lfs merge=lfs -text
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3531b2b615b3ce5e79312ecff42a4a9f6eaf29db66172063693da5466e61cff3
3
+ size 923220
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d224e265010461707e178201a94ecc36ff2d40c70162ac9dde581e4cd8d61b84
3
+ size 545101300
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__0_1.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78244987b2387d1f0f4ed9b22c20c831b5cea879904304e901ead695611ac764
3
+ size 545132060
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5b4fcaa2dd2022f3866ea682839dee7b11e5a859cee0e503f390e021dc954bc
3
+ size 499379568
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__1_1.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51bf82e5aada04279010fa5560470e476a361d8f00f787962219b5643bfeecc8
3
+ size 498618012
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60173db93ad0912729597ef934a83e90d3c4505c3615d58de31c0eaab494f847
3
+ size 498643736
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__2_1.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:511201dd3ecd96f79cc187b7bd9b88d90e6641c5d9c9c737f3f8e47a645ec0bf
3
+ size 499459932
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a2e71e3ed9c35dfcc0b7bb5f31d4bb3d6d179cb2febeda5f9f7dbdceea2cbb5
3
+ size 498478892
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__3_1.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3cc40d169e4043b1aad74cc7ddca5496a63565edddb201607708ad377ac6598
3
+ size 499459932
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d955504d0bbc744e58180746ce6d7cbed2ccac1109cb1abf7e40a0fef68bd6f
3
+ size 498583868
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__4_1.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2ad8e453cf8b56d9902a184bc101268a7ac9e9e31ea1e1849dc341f37acab08
3
+ size 499403292
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2644e82f7a551a480242a794cab5da083ddbd150bf298886b40402fc0929157
3
+ size 544206316
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__5_1.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3584f027be761deb51b9ed849c9953cf6783601826629ae234c2b963b0b64623
3
+ size 544049468
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a768acb4f5f4014a77d454360fc660119ea35790492e081601b875cd69c3fee3
3
+ size 498583868
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__6_1.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10405ed25af1c3989808016b016b81eea358f86154eaf0d6883ef99b01757738
3
+ size 499403292
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_0.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15e0de8adc1552d1f9dd08a2f74352932ec35fdfb560d1c3b46dfc60c57a7728
3
+ size 498422252
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/__7_1.distcp ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dbe088d9164daf6bd7edfb3dabf38b8ad26458ef61d037b02398df858b9897e
3
+ size 498353536
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/common.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a31680bfd723c56daf5d6cdb3b72b06eff5b5a37ad5f0f02325f701c7bb32d7b
3
+ size 18012
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/metadata.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"sharded_backend": "torch_dist", "sharded_backend_version": 1, "common_backend": "torch", "common_backend_version": 1}
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.01-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/latest_checkpointed_iteration.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 4768