mlboydaisuke commited on
Commit
b2efbe7
·
verified ·
1 Parent(s): 08405f7

Re-export with coreai-torch 0.4.1 (fixes OS 27 beta 2+ load failure); gated token-for-token vs fp32 oracle

Browse files
gpu-pipelined/nanbeige4_1_3b_decode_int8hu_block32_sym_s1/metadata.json CHANGED
@@ -22,7 +22,7 @@
22
  },
23
  "compression": null,
24
  "compilation": {
25
- "date": "2026-06-16T03:43:18.220229+00:00",
26
  "targets": []
27
  }
28
  }
 
22
  },
23
  "compression": null,
24
  "compilation": {
25
+ "date": "2026-07-17T14:07:00.232626+00:00",
26
  "targets": []
27
  }
28
  }
gpu-pipelined/nanbeige4_1_3b_decode_int8hu_block32_sym_s1/nanbeige4_1_3b_decode_int8hu_block32_sym_s1.aimodel/main.hash CHANGED
Binary files a/gpu-pipelined/nanbeige4_1_3b_decode_int8hu_block32_sym_s1/nanbeige4_1_3b_decode_int8hu_block32_sym_s1.aimodel/main.hash and b/gpu-pipelined/nanbeige4_1_3b_decode_int8hu_block32_sym_s1/nanbeige4_1_3b_decode_int8hu_block32_sym_s1.aimodel/main.hash differ
 
gpu-pipelined/nanbeige4_1_3b_decode_int8hu_block32_sym_s1/nanbeige4_1_3b_decode_int8hu_block32_sym_s1.aimodel/main.mlirb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0dee3eb9b2dc0090477e670f71b157e3ea8745093eaf8c34efe30b65c0f951ee
3
- size 4578687642
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cda972902a1f2d0062511957cb6ee048b8a86688206505d55a55261c197a4779
3
+ size 4578848918
gpu-pipelined/nanbeige4_1_3b_decode_int8hu_block32_sym_s1/nanbeige4_1_3b_decode_int8hu_block32_sym_s1.aimodel/metadata.json CHANGED
@@ -1,3 +1,5 @@
1
  {
2
- "assetVersion" : "2.0"
 
 
3
  }
 
1
  {
2
+ "creationDate" : "20260717T140658Z",
3
+ "assetVersion" : "2.0",
4
+ "producer" : "coreai-core 1.0.0b2"
5
  }