List your company
ResearchFormerly WizWand

Mathematical Reasoning on SVAMP (val)

85.1AccuracyTAIA
22.38838.66954.9571.231May 30, 2024
Updated 8mo ago

Evaluation results

MethodLinks
TAIATraining Dataset=Alpaca-GPT4, Model=LLaMA3-8B, FT Method=LoRA, Infer Mode=TAIA2024.0585.1
TAIATraining Dataset=Alpaca-GPT4, Model=LLaMA3-8B, FT Method=MOLORA, Infer Mode=TAIA2024.0584.9
TAIATraining Dataset=CoT-Collection, Model=LLaMA3-8B, FT Method=MOLORA, Infer Mode=TAIA2024.0583.1
TAIATraining Dataset=CoT-Collection, Model=LLaMA3-8B, FT Method=LoRA, Infer Mode=TAIA2024.0582.8
MOLORATraining Dataset=CoT-Collection, Model=LLaMA3-8B, FT Method=MOLORA, Infer Mode=Vanilla2024.0579.3
LoRATraining Dataset=CoT-Collection, Model=LLaMA3-8B, FT Method=LoRA, Infer Mode=Vanilla2024.0578.6
MOLORATraining Dataset=Alpaca-GPT4, Model=LLaMA3-8B, FT Method=MOLORA, Infer Mode=Vanilla2024.0571.2
LoRATraining Dataset=Alpaca-GPT4, Model=LLaMA3-8B, FT Method=LoRA, Infer Mode=Vanilla2024.0569.7
TAIATraining Dataset=Alpaca-GPT4, Model=Qwen1.5-7B, FT Method=LoRA, Infer Mode=TAIA2024.0567.2
TAIATraining Dataset=Alpaca-GPT4, Model=Qwen1.5-7B, FT Method=MOLORA, Infer Mode=TAIA2024.0565.6
TAIATraining Dataset=CoT-Collection, Model=Qwen1.5-7B, FT Method=LoRA, Infer Mode=TAIA2024.0561.9
LLaMA3-8BTraining Dataset=Base Model, Model=LLaMA3-8B2024.0560.33
TAIATraining Dataset=CoT-Collection, Model=Qwen1.5-7B, FT Method=MOLORA, Infer Mode=TAIA2024.0558.81
TAIATraining Dataset=CoT-Collection, Model=LLaMA2-7B, FT Method=LoRA, Infer Mode=TAIA2024.0558.33
LoRATraining Dataset=Alpaca-GPT4, Model=Qwen1.5-7B, FT Method=LoRA, Infer Mode=Vanilla2024.0557.1
TAIATraining Dataset=Alpaca-GPT4, Model=LLaMA2-7B, FT Method=LoRA, Infer Mode=TAIA2024.0557.08
MOLORATraining Dataset=Alpaca-GPT4, Model=Qwen1.5-7B, FT Method=MOLORA, Infer Mode=Vanilla2024.0556.8
MOLORATraining Dataset=CoT-Collection, Model=LLaMA2-7B, FT Method=MOLORA, Infer Mode=Vanilla2024.0556
TAIATraining Dataset=CoT-Collection, Model=LLaMA2-7B, FT Method=MOLORA, Infer Mode=TAIA2024.0555.4
Qwen1.5-7BTraining Dataset=Base Model, Model=Qwen1.5-7B2024.0554.9
LoRATraining Dataset=CoT-Collection, Model=Qwen1.5-7B, FT Method=LoRA, Infer Mode=Vanilla2024.0553.6
MOLORATraining Dataset=CoT-Collection, Model=Qwen1.5-7B, FT Method=MOLORA, Infer Mode=Vanilla2024.0552.7
LoRATraining Dataset=CoT-Collection, Model=LLaMA2-7B, FT Method=LoRA, Infer Mode=Vanilla2024.0552.5
TAIATraining Dataset=Alpaca-GPT4, Model=LLaMA2-7B, FT Method=MOLORA, Infer Mode=TAIA2024.0551.8
MOLORATraining Dataset=Alpaca-GPT4, Model=LLaMA2-7B, FT Method=MOLORA, Infer Mode=Vanilla2024.0545.4
TAIATraining Dataset=CoT-Collection, Model=Qwen1.5-1.8B, FT Method=MOLORA, Infer Mode=TAIA2024.0544.8
LLaMA2-7BTraining Dataset=Base Model, Model=LLaMA2-7B2024.0544.5
LoRATraining Dataset=Alpaca-GPT4, Model=LLaMA2-7B, FT Method=LoRA, Infer Mode=Vanilla2024.0543.4
TAIATraining Dataset=CoT-Collection, Model=Qwen1.5-1.8B, FT Method=LoRA, Infer Mode=TAIA2024.0540.3
LoRATraining Dataset=CoT-Collection, Model=Qwen1.5-1.8B, FT Method=LoRA, Infer Mode=Vanilla2024.0539
MOLORATraining Dataset=CoT-Collection, Model=Qwen1.5-1.8B, FT Method=MOLORA, Infer Mode=Vanilla2024.0538.2
LoRATraining Dataset=Alpaca-GPT4, Model=Qwen1.5-1.8B, FT Method=LoRA, Infer Mode=Vanilla2024.0534.8
TAIATraining Dataset=Alpaca-GPT4, Model=Qwen1.5-1.8B, FT Method=MOLORA, Infer Mode=TAIA2024.0531.1
TAIATraining Dataset=Alpaca-GPT4, Model=Qwen1.5-1.8B, FT Method=LoRA, Infer Mode=TAIA2024.0529.9
MOLORATraining Dataset=Alpaca-GPT4, Model=Qwen1.5-1.8B, FT Method=MOLORA, Infer Mode=Vanilla2024.0525.2
Qwen1.5-1.8BTraining Dataset=Base Model, Model=Qwen1.5-1.8B2024.0524.8