Files
vllm/tests/evals/gsm8k/configs/Qwen3-30B-A3B-NVFP4.yaml
2025-12-16 14:28:34 -05:00

6 lines
151 B
YAML

model_name: "nvidia/Qwen3-30B-A3B-FP4"
accuracy_threshold: 0.89
num_questions: 1319
num_fewshot: 5
server_args: "--enforce-eager --max-model-len 4096"