noneUsername/Qwen2.5-Coder-14B-Instruct-abliterated-W8A8-Dynamic-Per-Token

vllm (pretrained=/root/autodl-tmp/Qwen2.5-Coder-14B-Instruct-abliterated,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,gpu_memory_utilization=0.80,max_num_seqs=5), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: 5

Tasks	Version	Filter	n-shot	Metric		Value		Stderr
gsm8k	3	flexible-extract	5	exact_match	↑	0.872	±	0.0212
		strict-match	5	exact_match	↑	0.868	±	0.0215

vllm (pretrained=/root/autodl-tmp/output91,add_bos_token=true,tensor_parallel_size=2,max_model_len=2048,gpu_memory_utilization=0.80,max_num_seqs=5), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: 5

Tasks	Version	Filter	n-shot	Metric		Value		Stderr
gsm8k	3	flexible-extract	5	exact_match	↑	0.872	±	0.0212
		strict-match	5	exact_match	↑	0.872	±	0.0212