GSM8K ground truths regenerated in different styles. OpenMathInstruct1, OpenMathInstruct2 and TinyGSM.
Itamar de Paiva Rocha Filho
itamarf
·
AI & ML interests
None yet
Organizations
models
110
itamarf/OLMo-150M-as_fm3_tg_omi2_ppo_math
0.2B
•
Updated
•
2
itamarf/OLMo-150M-as_fm3_tg_omi2_ppo_gsm8k
0.2B
•
Updated
•
2
itamarf/OLMo-150M-as_fm3_tg_omi1_omi2_ppo_math
0.2B
•
Updated
•
3
itamarf/OLMo-150M-as_fm3_tg_omi1_omi2_ppo_gsm8k
0.2B
•
Updated
•
3
itamarf/OLMo-150M-as_fm3_tg_omi1_ppo_math
0.2B
•
Updated
•
1
itamarf/OLMo-150M-as_fm3_tg_omi1_ppo_gsm8k
0.2B
•
Updated
•
1
itamarf/OLMo-150M-as_fm3_tg_8xomi1_ppo_math
0.2B
•
Updated
•
1
itamarf/OLMo-150M-as_fm3_tg_8xomi1_ppo_gsm8k
0.2B
•
Updated
•
4
itamarf/OLMo-150M-as_fm3_tg_4xomi1_ppo_math
0.2B
•
Updated
•
1
itamarf/OLMo-150M-as_fm3_tg_4xomi1_ppo_gsm8k
0.2B
•
Updated
•
3