arxiv:2403.13031
Zidi Xiong
polaris-73
·
AI & ML interests
None yet
Recent Activity
published
a model
8 days ago
polaris-73/ds7b_grpo_math_gsm8k-global_step_200
updated
a model
11 days ago
polaris-73/ds1p5b_grpo_math_gsm8k_cliphigh-global_step_870
published
a model
11 days ago
polaris-73/ds1p5b_grpo_math_gsm8k_cliphigh-global_step_870
Organizations
models
22
polaris-73/ds7b_grpo_math_gsm8k-global_step_200
Updated
polaris-73/ds1p5b_grpo_math_gsm8k_cliphigh-global_step_870
2B
•
Updated
•
1
polaris-73/ds1p5b_grpo_math_gsm8k_cliphigh-global_step_800
2B
•
Updated
•
2
polaris-73/ds1p5b_grpo_math_gsm8k_cliphigh-global_step_600
2B
•
Updated
•
1
polaris-73/ds1p5b_grpo_math_gsm8k_cliphigh-global_step_400
2B
•
Updated
•
1
polaris-73/ds1p5b_grpo_math_gsm8k_cliphigh-global_step_200
2B
•
Updated
•
1
polaris-73/ds1p5b_grpo_math_gsm8k_ppo-global_step_870
2B
•
Updated
•
1
polaris-73/ds1p5b_grpo_math_gsm8k_ppo-global_step_600
2B
•
Updated
•
1
polaris-73/ds1p5b_grpo_math_gsm8k_ppo-global_step_400
2B
•
Updated
•
1
polaris-73/ds1p5b_grpo_math_gsm8k_ppo-global_step_200
2B
•
Updated
•
1