Upload folder using huggingface_hub
Browse files- .gitattributes +17 -0
- 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/.metadata +3 -0
- 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/__0_0.distcp +3 -0
- 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/__0_1.distcp +3 -0
- 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/__1_0.distcp +3 -0
- 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/__1_1.distcp +3 -0
- 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/__2_0.distcp +3 -0
- 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/__2_1.distcp +3 -0
- 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/__3_0.distcp +3 -0
- 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/__3_1.distcp +3 -0
- 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/__4_0.distcp +3 -0
- 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/__4_1.distcp +3 -0
- 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/__5_0.distcp +3 -0
- 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/__5_1.distcp +3 -0
- 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_0.distcp +3 -0
- 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 +3 -0
- 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 +3 -0
- 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 +3 -0
- 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/common.pt +3 -0
- 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/metadata.json +1 -0
- 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/latest_checkpointed_iteration.txt +1 -0
.gitattributes
CHANGED
|
@@ -474,3 +474,20 @@ model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-bf16-ep4-mp2-pp1
|
|
| 474 |
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-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
|
| 475 |
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-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
|
| 476 |
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 474 |
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-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
|
| 475 |
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-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
|
| 476 |
model/dev-mixtral-0.5b-q16-kv2-ep-16-sep-0-top2-cf-0-mlc-0.0001-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
|
| 477 |
+
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/.metadata filter=lfs diff=lfs merge=lfs -text
|
| 478 |
+
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/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 479 |
+
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/__0_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 480 |
+
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/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 481 |
+
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/__1_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 482 |
+
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/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 483 |
+
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/__2_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 484 |
+
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/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 485 |
+
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/__3_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 486 |
+
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/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 487 |
+
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/__4_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 488 |
+
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/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
|
| 489 |
+
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/__5_1.distcp filter=lfs diff=lfs merge=lfs -text
|
| 490 |
+
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_0.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
|
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/.metadata
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9935086e3e66486512953d0a4fcb77995719fc3e634f0118e53afdca451e50a
|
| 3 |
+
size 923221
|
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/__0_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3e979187631eef9a7e6b3fdece71bc007a754ba869a0ab459fb6779507e9bff
|
| 3 |
+
size 545101300
|
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/__0_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a73821212817e43c1c35144e4ec07059c9155ad850c1b40349f1fa204624d436
|
| 3 |
+
size 545132060
|
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/__1_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29b73f54647654db5bf803d8abaaa243ef78255dcc6be950911acfc41c55ad95
|
| 3 |
+
size 499379568
|
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/__1_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:421f6395562727f7de94fcdf80a6a807d2560cb04c9996af1d60cf0c11851325
|
| 3 |
+
size 498618012
|
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/__2_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5585f4c451cd40ee3fc4bcf4baadd41f0648c1b9b1c5eb12fb2652102e146e7
|
| 3 |
+
size 498643736
|
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/__2_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f17395da595354eb65dadcef07a35945de57240c65958aabeae70968f2e6d8f
|
| 3 |
+
size 499459932
|
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/__3_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdd226a321759a82656c4dd0fec3ab6a4dfe97d7adf6389932e7bee7bc7bd4a9
|
| 3 |
+
size 498478892
|
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/__3_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d49d53ec31dcef9051b0cd4e716937416f88316e5994ccf65b936564a68da456
|
| 3 |
+
size 499459932
|
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/__4_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba8aee70b84c89ab5b11d9b9b84b83fb9f2e0aa627e2c136c6ed95607f89bacd
|
| 3 |
+
size 498583868
|
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/__4_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96b45ce1a3428ce54d577ca5629734ce2467290bc31adf03f5a14fcd748fa365
|
| 3 |
+
size 499403292
|
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/__5_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:817aa48d2f7799fa08b49658e072d5ebbffa4f62f27426fe2c0a2a547c209a27
|
| 3 |
+
size 544206316
|
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/__5_1.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f67799b780e7b3751154497d3049c2f39ab11c29898abeb7f668fa2f30b188d5
|
| 3 |
+
size 544049468
|
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_0.distcp
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86c49956876eb4dc5b38b6628f334430ea7ead1443b3f850fc80ef44d1d0c384
|
| 3 |
+
size 498583868
|
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
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a452dff73d6ca9096292892f2a2b7707cd55a340a9d4b389297d73ac6fa2e13c
|
| 3 |
+
size 499403292
|
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
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f75e419d31037d35ea177d8c7becdc38760a7dd08d297950efe5dabfac6079a
|
| 3 |
+
size 498422252
|
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
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:480310c3822c31954085ecac17093ea01c29a83639e51603896f515147529497
|
| 3 |
+
size 498353536
|
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/common.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b705d8f1fca87fef73e23cd9e8786434027ee5c609f3cf69edca7ed42503359f
|
| 3 |
+
size 18012
|
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/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-0.001-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
|