noneUsername/Mistral-Small-22B-ArliAI-RPMax-v1.1-W8A8-Dynamic-Per-Token

vllm (pretrained=/root/autodl-tmp/Mistral-Small-22B-ArliAI-RPMax-v1.1,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,enforce_eager=true,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	↑	0.764	±	0.0269
		strict-match	5	exact_match	↑	0.752	±	0.0274

vllm (pretrained=/root/autodl-tmp/output,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,enforce_eager=true), 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	↑	0.756	±	0.0272
		strict-match	5	exact_match	↑	0.752	±	0.0274