Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion eval/chat_benchmarks/GPQADiamond/eval_instruct.py
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
import hashlib
import logging
import os
import random
Expand Down Expand Up @@ -185,7 +186,7 @@ def generate_multiple_choice_answers(self, data: Dict[str, Any]) -> tuple[str, s
data["Incorrect Answer 2"],
data["Incorrect Answer 3"],
]
rnd = random.Random(42)
rnd = random.Random(42 + int(hashlib.md5(data["Question"].encode()).hexdigest(), 16))
rnd.shuffle(answers)

options = ["A", "B", "C", "D"]
Expand Down