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 15, 13:30 UTC
Update Qwen1.5-MoE-W4A16-compressed-tensors.yaml (#16946)
Michael Goin committed
Apr 21, 2025 at 18:35 UTC
71eda0bb76b340eda7cb449edec75d70d8470cc7
1 file changed
+2
-2
.buildkite/lm-eval-harness/configs/Qwen1.5-MoE-W4A16-compressed-tensors.yaml
+2
-2
@@ -4,8 +4,8 @@ tasks:
4
- name: "gsm8k"
5
metrics:
6
- name: "exact_match,strict-match"
7
- value: 0.31
7
+ value: 0.30
8
- name: "exact_match,flexible-extract"
9
- value: 0.47
9
+ value: 0.465
10
limit: 1319
11
num_fewshot: 5