Files
vllm/tests/evals/gsm8k/configs/Qwen1.5-MoE-W4A16-CT.yaml
T
2026-06-04 22:35:00 +08:00

7 lines
211 B
YAML

model_name: "nm-testing/Qwen1.5-MoE-A2.7B-Chat-quantized.w4a16"
accuracy_threshold: 0.45
num_questions: 1319
num_fewshot: 5
rocm_request_timeout_seconds: 1800
server_args: "--enforce-eager --max-model-len 4096"