lfm2_5_1_2b_instruct_decode_int8lin: re-save with coreai-core 1.0.0b2 (strip debug locations; weights unchanged). The 0.4.0-era IR refused AIModel.load on every OS 27 build since beta 2, still on the RC 26A428 (2026-09-14); the re-saved bundle loads. Recovery: coreai-model-zoo conversion/recovery/{strip_b1,resave_b2}.py
Browse files- gpu-pipelined/lfm2_5_1_2b_instruct_decode_int8lin/lfm2_5_1_2b_instruct_decode_int8lin.aimodel/main.hash +0 -0
- gpu-pipelined/lfm2_5_1_2b_instruct_decode_int8lin/lfm2_5_1_2b_instruct_decode_int8lin.aimodel/main.mlirb +2 -2
- gpu-pipelined/lfm2_5_1_2b_instruct_decode_int8lin/lfm2_5_1_2b_instruct_decode_int8lin.aimodel/metadata.json +2 -0
gpu-pipelined/lfm2_5_1_2b_instruct_decode_int8lin/lfm2_5_1_2b_instruct_decode_int8lin.aimodel/main.hash
CHANGED
|
Binary files a/gpu-pipelined/lfm2_5_1_2b_instruct_decode_int8lin/lfm2_5_1_2b_instruct_decode_int8lin.aimodel/main.hash and b/gpu-pipelined/lfm2_5_1_2b_instruct_decode_int8lin/lfm2_5_1_2b_instruct_decode_int8lin.aimodel/main.hash differ
|
|
|
gpu-pipelined/lfm2_5_1_2b_instruct_decode_int8lin/lfm2_5_1_2b_instruct_decode_int8lin.aimodel/main.mlirb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3258d7994430af2cd2b8649ca887a29a5c2f7652457cab93fc03d0ff11354e48
|
| 3 |
+
size 1554340053
|
gpu-pipelined/lfm2_5_1_2b_instruct_decode_int8lin/lfm2_5_1_2b_instruct_decode_int8lin.aimodel/metadata.json
CHANGED
|
@@ -1,3 +1,5 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"assetVersion" : "2.0"
|
| 3 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"producer" : "coreai-core 1.0.0b2",
|
| 3 |
+
"creationDate" : "20260914T115317Z",
|
| 4 |
"assetVersion" : "2.0"
|
| 5 |
}
|