IvanHU commited on
Commit
227b0c0
·
verified ·
1 Parent(s): a1d2ec9

Upload folder using huggingface_hub

Browse files
Files changed (22) hide show
  1. .gitattributes +17 -0
  2. model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/iter_0004768/.metadata +3 -0
  3. model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/latest_checkpointed_iteration.txt +1 -0
  22. model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/linked_runs.txt +1 -0
.gitattributes CHANGED
@@ -610,3 +610,20 @@ model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-bf16-ep4-m
610
  model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-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
611
  model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-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
612
  model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-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
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
610
  model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-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
611
  model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-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
612
  model/dev-muon-gate-dsv3-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-bias-1e-3-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
613
+ model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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
614
+ model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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
615
+ model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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
616
+ model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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
617
+ model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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
618
+ model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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
619
+ model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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
620
+ model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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
621
+ model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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
622
+ model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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
623
+ model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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
624
+ model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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
625
+ model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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
626
+ model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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
627
+ model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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
628
+ model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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
629
+ model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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 sha256:69582df7e1c7d560914572a40bbf3be9038b0f7fa9f0eeca3c6b3764e2008e83
3
+ size 2395263
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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 sha256:7e0e0166d9dc4cc90db084845196d77367faba03595c43d53f0fd296b532d633
3
+ size 885540371
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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:afbd43e2a4f586945ca111255188bca0782320a52bbacfd4c1a947a86e807b36
3
+ size 885552026
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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 sha256:0a97567186f57dcbafcd157cffc34acfab55e58ac964fdb942898e78d6ae717a
3
+ size 911423083
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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:f8a75de3808c55807c1e5080943efbf99320661aca037a88d048347fae9648b3
3
+ size 911406732
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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 sha256:10a38bf7d02ace541c5a6cf7c095619b31f950085a4f6d61fdc5bb4cb902837a
3
+ size 885360269
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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:daac9706f7fbd070e8286a082ff94e3a0e122f7792fcd1d520e38469836d0c4d
3
+ size 885374462
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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:df03024b2986a4e64588129b9c3ebe293b403cc7baffdf7ceac2703da8549ce4
3
+ size 884637222
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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 sha256:10d61936f0583a6c9f597cdf969c7cfc8e27bd28357c8ec0b49bd2df94a104d8
3
+ size 884615144
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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 sha256:96d8e7e22059e52fc11ce33a22d2f088dbea3c59ac6301cc64d89e29a50c7b25
3
+ size 912018309
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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:c38b5735dafab6ea9a23404886bbdb1493c11bdc131e00c9113fbc79d83dd6df
3
+ size 912043541
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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:a99d2f6d1fa74c35ec086d438baa3c5be47197561cb7702e2ce2609fbb616733
3
+ size 884541063
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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 sha256:051356aef4778baa3384c11a8aa692aa1e5283e7cd70fcb8ace15427f42e3a17
3
+ size 884575757
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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:e5761a0d501069b4acffef1f8b1a79d7893552f2f047b17e1da9dc1e45e2b804
3
+ size 885158308
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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 sha256:94f3b74104e5c2b64af2c458669497c347440a039ea04f7db8908b10407ca3d5
3
+ size 885199310
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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 sha256:62dedd7325203da4eb61bacd0132fd72b411beef1c6ce2f99b8d61a35df84e12
3
+ size 884710920
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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 sha256:02918b8f451a18c9b15cb0b1abd7fab2a850d8e4888e86bfd1070222f2d10640
3
+ size 884673072
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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:f191088f818de1f9ef0f27a63c520463040af37072e501094d5018d852b63cff
3
+ size 19303
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-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
model/dev-muon-gate-mamba_moe-0.5b-q16-kv2-hybrid0.16-ep-16-sep-0-top2-cf-2-bias-1e-3-bf16-ep4-mp2-pp1-lr-2e-3-minlr-7e-7-bs-1024-gpus-8-seqlen-8192/linked_runs.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 2025.05.30-11.30.45