Rewriting Pre-Training Data Boosts LLM Performance in Math and Code
-
tokyotech-llm/swallow-math
Viewer • Updated • 4.33M • 73 • 1 -
tokyotech-llm/Llama-3.1-8B-math-ablation-exp2-LR2.5e-5-WD0.1-iter0002500
Updated -
tokyotech-llm/Llama-3.1-8B-math-ablation-exp2-LR2.5e-5-WD0.1-iter0005000
Updated -
tokyotech-llm/Llama-3.1-8B-math-ablation-exp2-LR2.5e-5-WD0.1-iter0007500
Updated