A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 19:30 UTC
[Misc] Update LM Eval Tolerance (#7473)
Dipika Sikka committed
Aug 13, 2024 at 14:28 UTC
181abbc27d812803d2ee945ea7407c64bca6c9f4
1 file changed
+1
-1
.buildkite/lm-eval-harness/test_lm_eval_correctness.py
+1
-1
@@ -14,7 +14,7 @@ import lm_eval
14
import numpy
15
import yaml
16
17
-RTOL = 0.02
17
+RTOL = 0.05
18
TEST_DATA_FILE = os.environ.get(
19
"LM_EVAL_TEST_DATA_FILE",
20
".buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-Instruct.yaml")