[ROCm][CI] Relax simple-nemotron-h-8b GSM8K threshold on ROCm (#59477)
Signed-off-by: Djordje Ramic <djoramic@amd.com> Co-authored-by: Andreas Karatzas <akaratza@amd.com>
This commit is contained in:
co-authored by
Andreas Karatzas
parent
a21a3f2ec7
commit
b56b54bc54
@@ -191,7 +191,7 @@ MODELS = [
|
||||
id="simple-nemotron-h-8b",
|
||||
model="nvidia/Nemotron-H-8B-Base-8K",
|
||||
connector="SimpleCPUOffloadConnector",
|
||||
accuracy_threshold=0.45,
|
||||
accuracy_threshold=0.43 if current_platform.is_rocm() else 0.45,
|
||||
),
|
||||
OffloadingModelConfig(
|
||||
id="simple-gemma-4-e4b-it",
|
||||
|
||||
Reference in New Issue
Block a user