@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 181abbc27d
Fork 0

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")