shrango/qwen2.5_math_7b_simple_prompt_openr1_data_baseline_re
8B • Updated
LoPE
LoPE experiment checkpoints (global_step_200)
-
-
shrango/qwen2.5_math_7b_grpo_openr1_data_baseline_wokl
8B • Updated -
shrango/qwen2.5_math_7b_openr1_data_bs128_naive_fallback_test_MATH_wokl
8B • Updated -
shrango/qwen2.5_math_7b_openr1_data_bs128_luffy
8B • Updated -
shrango/qwen3-1.7b-base_openr1_data_bs128_lorem_test_MATH_wokl_luffy
2B • Updated -
shrango/qwen3-4b-base_openr1_data_bs128_lorem_test_MATH_wokl_luffy_fixadv
4B • Updated -
shrango/qwen3-1.7b-base_openr1_data_bs128_lorem_in_middle_test_MATH_wokl
2B • Updated -
shrango/qwen3-1.7b-base_openr1_data_bs128_lorem_test_MATH_wokl_luffy_fixadv
2B • Updated -
shrango/qwen3-4b-base_openr1_data_baseline_wokl
4B • Updated -
shrango/qwen3-1.7b-base_openr1_data_bs128_baseline_wokl
2B • Updated -
shrango/qwen3-1.7b-base_openr1_data_bs128_baseline
2B • Updated -
shrango/qwen3-1.7b-base_openr1_data_bs128_random_filtered_natural_language_la_shape_wokl
2B • Updated