We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent a41b67c commit b0f9680Copy full SHA for b0f9680
1 file changed
tests/models/test_laguna.py
@@ -29,6 +29,19 @@ class TestLagunaXS2(ModelTest):
29
EVAL_BATCH_SIZE = "auto"
30
31
EVAL_TASKS_FAST = {
32
+ "gsm8k_platinum_cot": {
33
+ "chat_template": False,
34
+ "evalution_suite_kwargs": {
35
+ "max_new_tokens": 256,
36
+ "stream": True,
37
+ "max_rows": 128,
38
+ },
39
+ "acc,num": {
40
+ "value": 0.3828125,
41
+ "floor_pct": 0.50,
42
+ "ceil_pct": 1.0,
43
44
45
"arc_challenge": {
46
"chat_template": False,
47
"evalution_suite_kwargs": {
0 commit comments