noneUsername/magnum-v4-12b-W8A8-Dynamic-Per-Token

vllm (pretrained=/root/autodl-tmp/magnum-v4-12b-W8A8,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,dtype=bfloat16), 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	↑	0.776	±	0.0264
		strict-match	5	exact_match	↑	0.736	±	0.0279

vllm (pretrained=/root/autodl-tmp/magnum-v4-12b-W8A8,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,dtype=float16), 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	↑	0.768	±	0.0268
		strict-match	5	exact_match	↑	0.744	±	0.0277

vllm (pretrained=/root/autodl-tmp/magnum-v4-12b,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,dtype=bfloat16), 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	↑	0.784	±	0.0261
		strict-match	5	exact_match	↑	0.752	±	0.0274

vllm (pretrained=/root/autodl-tmp/magnum-v4-12b,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,dtype=float16), 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	↑	0.776	±	0.0264
		strict-match	5	exact_match	↑	0.748	±	0.0275