noneUsername/Qwen2.5-Lumen-14B-W8A8-Dynamic-Per-Token

vllm (pretrained=/root/autodl-tmp/Qwen2.5-Lumen-14B,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,gpu_memory_utilization=0.99), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto

Tasks	Version	Filter	n-shot	Metric		Value		Stderr
gsm8k	3	flexible-extract	5	exact_match	↑	0.544	±	0.0316
		strict-match	5	exact_match	↑	0.836	±	0.0235

vllm (pretrained=/root/autodl-tmp/output,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,gpu_memory_utilization=0.99), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: 1

Tasks	Version	Filter	n-shot	Metric		Value		Stderr
gsm8k	3	flexible-extract	5	exact_match	↑	0.532	±	0.0316
		strict-match	5	exact_match	↑	0.824	±	0.0241