tokyotech-llm/swallow-code
Viewer
•
Updated
•
129M
•
3.25k
•
43
SwallowCode
Rewriting Pre-Training Data Boosts LLM Performance in Math and Code
-
-
tokyotech-llm/Llama-3.1-8B-code-ablation-exp1-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0002500
8B • Updated • 46 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp1-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0005000
8B • Updated • 41 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp1-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0007500
8B • Updated • 78 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp1-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0010000
8B • Updated • 43 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp1-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0012500
8B • Updated • 114 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp2-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0002500
8B • Updated • 58 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp2-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0005000
8B • Updated • 44 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp2-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0007500
8B • Updated • 46 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp2-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0010000
8B • Updated • 27 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp2-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0012500
8B • Updated • 28 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp3-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0002500
8B • Updated • 42 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp3-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0005000
8B • Updated • 28 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp3-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0007500
8B • Updated • 90 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp3-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0010000
8B • Updated • 32 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp3-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0012500
8B • Updated • 52 • 1 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp4-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0002500
8B • Updated • 132 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp4-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0005000
8B • Updated • 74 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp4-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0007500
8B • Updated • 30 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp4-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0010000
8B • Updated • 37 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp4-LR2.5e-5-MINLR2.5E-6-WD0.1-iter0012500
8B • Updated • 101 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp5-Llama-3.3-70B-LR2.5e-5-WD0.1-iter0002500
8B • Updated • 13 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp5-Llama-3.3-70B-LR2.5e-5-WD0.1-iter0005000
8B • Updated • 14 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp5-Llama-3.3-70B-LR2.5e-5-WD0.1-iter0007500
8B • Updated • 13 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp5-Llama-3.3-70B-LR2.5e-5-WD0.1-iter0010000
8B • Updated • 12 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp5-Llama-3.3-70B-LR2.5e-5-WD0.1-iter0012500
8B • Updated • 71 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp6-Llama-3.3-70B-LR2.5e-5-WD0.1-iter0002500
8B • Updated • 56 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp6-Llama-3.3-70B-LR2.5e-5-WD0.1-iter0005000
8B • Updated • 14 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp6-Llama-3.3-70B-LR2.5e-5-WD0.1-iter0007500
8B • Updated • 13 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp6-Llama-3.3-70B-LR2.5e-5-WD0.1-iter0010000
8B • Updated • 29 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp6-Llama-3.3-70B-LR2.5e-5-WD0.1-iter0012500
8B • Updated • 13 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp7-Llama-3.3-70B-LR2.5e-5-WD0.1-iter0002500
8B • Updated • 44 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp7-Llama-3.3-70B-LR2.5e-5-WD0.1-iter0005000
8B • Updated • 29 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp7-Llama-3.3-70B-LR2.5e-5-WD0.1-iter0007500
8B • Updated • 10 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp7-Llama-3.3-70B-LR2.5e-5-WD0.1-iter0010000
8B • Updated • 13 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp7-Llama-3.3-70B-LR2.5e-5-WD0.1-iter0012500
8B • Updated • 13 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp8-LR2.5e-5-WD0.1-iter0002500
8B • Updated • 33 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp8-LR2.5e-5-WD0.1-iter0005000
8B • Updated • 42 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp8-LR2.5e-5-WD0.1-iter0007500
8B • Updated • 33 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp8-LR2.5e-5-WD0.1-iter0010000
8B • Updated • 33 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp8-LR2.5e-5-WD0.1-iter0012500
8B • Updated • 31 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp9-LR2.5e-5-WD0.1-iter0002500
8B • Updated • 34 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp9-LR2.5e-5-WD0.1-iter0005000
8B • Updated • 33 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp9-LR2.5e-5-WD0.1-iter0007500
8B • Updated • 78 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp9-LR2.5e-5-WD0.1-iter0010000
8B • Updated • 30 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp9-LR2.5e-5-WD0.1-iter0012500
8B • Updated • 41 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp10-LR2.5e-5-WD0.1-iter0002500
8B • Updated • 86 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp10-LR2.5e-5-WD0.1-iter0005000
8B • Updated • 29 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp10-LR2.5e-5-WD0.1-iter0007500
8B • Updated • 65 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp10-LR2.5e-5-WD0.1-iter0010000
8B • Updated • 33 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp10-LR2.5e-5-WD0.1-iter0012500
8B • Updated • 31 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp11-LR2.5e-5-WD0.1-iter0002500
8B • Updated • 70 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp11-LR2.5e-5-WD0.1-iter0005000
8B • Updated • 51 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp11-LR2.5e-5-WD0.1-iter0007500
8B • Updated • 29 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp11-LR2.5e-5-WD0.1-iter0010000
8B • Updated • 32 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp11-LR2.5e-5-WD0.1-iter0012500
8B • Updated • 103 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp12-LR2.5e-5-WD0.1-iter0002500
8B • Updated • 33 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp12-LR2.5e-5-WD0.1-iter0005000
8B • Updated • 33 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp12-LR2.5e-5-WD0.1-iter0007500
8B • Updated • 39 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp12-LR2.5e-5-WD0.1-iter0010000
8B • Updated • 30 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp12-LR2.5e-5-WD0.1-iter0012500
8B • Updated • 30 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp13-LR2.5e-5-WD0.1-iter0002500
8B • Updated • 31 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp13-LR2.5e-5-WD0.1-iter0005000
8B • Updated • 30 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp13-LR2.5e-5-WD0.1-iter0007500
8B • Updated • 31 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp13-LR2.5e-5-WD0.1-iter0010000
8B • Updated • 49 -
tokyotech-llm/Llama-3.1-8B-code-ablation-exp13-LR2.5e-5-WD0.1-iter0012500
8B • Updated • 63