tokyotech-llm/swallow-math
Viewer • Updated • 4.33M • 1.21k • 49
SwallowMath
Rewriting Pre-Training Data Boosts LLM Performance in Math and Code
-
-
tokyotech-llm/Llama-3.1-8B-math-ablation-exp2-LR2.5e-5-WD0.1-iter0002500
8B • Updated • 44 -
tokyotech-llm/Llama-3.1-8B-math-ablation-exp2-LR2.5e-5-WD0.1-iter0005000
8B • Updated • 43 -
tokyotech-llm/Llama-3.1-8B-math-ablation-exp2-LR2.5e-5-WD0.1-iter0007500
8B • Updated • 45 -
tokyotech-llm/Llama-3.1-8B-math-ablation-exp2-LR2.5e-5-WD0.1-iter0010000
8B • Updated • 39 -
tokyotech-llm/Llama-3.1-8B-math-ablation-exp2-LR2.5e-5-WD0.1-iter0012500
8B • Updated • 46 -
tokyotech-llm/Llama-3.1-8B-math-ablation-exp1-LR2.5e-5-WD0.1-iter0002500
8B • Updated • 10 -
tokyotech-llm/Llama-3.1-8B-math-ablation-exp1-LR2.5e-5-WD0.1-iter0005000
8B • Updated • 49 -
tokyotech-llm/Llama-3.1-8B-math-ablation-exp1-LR2.5e-5-WD0.1-iter0007500
8B • Updated • 43 -
tokyotech-llm/Llama-3.1-8B-math-ablation-exp1-LR2.5e-5-WD0.1-iter0010000
8B • Updated • 44 -
tokyotech-llm/Llama-3.1-8B-math-ablation-exp1-LR2.5e-5-WD0.1-iter0012500
8B • Updated • 45