Support penalty in overlap mode; return logprob with chunked prefill; improve benchmark scripts (#3988)
Co-authored-by: SangBin Cho <rkooo567@gmail.com> Co-authored-by: dhou-xai <dhou@x.ai> Co-authored-by: Hanming Lu <hanming_lu@berkeley.edu>
This commit is contained in:
@@ -141,7 +141,7 @@ class TestDeepseekV3MTP(unittest.TestCase):
|
||||
metrics = run_eval_few_shot_gsm8k(args)
|
||||
print(metrics)
|
||||
|
||||
self.assertGreater(metrics["accuracy"], 0.62)
|
||||
self.assertGreater(metrics["accuracy"], 0.60)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
Reference in New Issue
Block a user