| AGIEval/data | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| anli/anli_v1.0 | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| ARC | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| BBH | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| ceval/formal_ceval | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| CLUE | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| cmmlu | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| FewCLUE | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| GAOKAO-BENCH/data | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| hellaswag | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| jigsawmultilingual | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| lambada | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| LCSTS | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| math | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| mbpp | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| mmlu | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| nq | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| realtoxicprompts | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| SQuAD2.0 | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| summedits | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| SuperGLUE | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| TheoremQA | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| triviaqa | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| xiezhi | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| Xsum | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| ._.DS_Store | init | 2025-07-18 07:25:44 +00:00 | 
		
			
			
			
			
				| .DS_Store | init | 2025-07-18 07:25:44 +00:00 |