shrango/qwen3-1.7b-base_openr1_data_bs128_random_en_word_luffy_advshape_test_MATH_wokl
2B • Updated • 7
Langlin Huang
shrango
AI & ML interests
LLM Reasoning, Machine Translation
Recent Activity
commentedon a paper 1 day ago
Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation updated a collection 19 days ago
LoPE updated a collection 19 days ago
LoPEOrganizations
shrango/qwen3-1.7b-base_openr1_data_bs128_random_filtered_natural_language_la_shape_wokl
2B • Updated • 21
shrango/qwen3-1.7b-base_openr1_data_bs128_random_la_word_luffy_advshape_test_MATH_wokl
2B • Updated • 9
shrango/qwen3-1.7b-base_openr1_data_bs128_random_lorem_high_word_test_MATH_wokl
2B • Updated • 11
shrango/qwen3-4b-base_openr1_data_bs128_naive_fallback_test_MATH_wokl
4B • Updated • 14
shrango/qwen3-1.7b-base_openr1_data_bs128_baseline
2B • Updated • 19
shrango/qwen3-1.7b-base_openr1_data_bs128_baseline_wokl
2B • Updated • 15
shrango/qwen3-4b-base_openr1_data_baseline_wokl
4B • Updated • 24
shrango/qwen3-1.7b-base_openr1_data_bs128_lorem_test_MATH_wokl_luffy_fixadv
2B • Updated • 19
shrango/qwen3-1.7b-base_openr1_data_bs128_lorem_in_middle_test_MATH_wokl
2B • Updated • 15
shrango/qwen3-4b-base_openr1_data_bs128_lorem_test_MATH_wokl_luffy_fixadv
4B • Updated • 27
shrango/qwen3-1.7b-base_openr1_data_bs128_lorem_test_MATH_wokl_luffy
2B • Updated • 17
shrango/qwen2.5_math_7b_openr1_data_bs128_luffy
8B • Updated • 18
shrango/qwen2.5_math_7b_openr1_data_bs128_naive_fallback_test_MATH_wokl
8B • Updated • 17
shrango/qwen2.5_math_7b_grpo_openr1_data_baseline_wokl
8B • Updated • 19
shrango/qwen2.5_math_7b_simple_prompt_openr1_data_baseline_re
8B • Updated • 16
shrango/fake_english_advshape_policyshape_qwen3-1.7b-base
2B • Updated • 3
shrango/ascii_advshape_policyshape_qwen3-1.7b-base
2B • Updated • 1
shrango/markovify_advshape_policy_shape_qwen3-1.7b-base
2B • Updated • 2
shrango/random_la_advshape_policyshape_qwen3-1.7b-base
2B • Updated • 5
shrango/lorem_advshape_qwen3-1.7b-base
2B • Updated • 2
shrango/lorem_policy_shape_adv_shape_qwen2.5-math_7b
8B • Updated • 4
shrango/lorem_advshape_policyshape_qwen2.5_math_7b_170
Updated
shrango/lorem_advshape_policyshape_qwen2.5_math_7b_150
Updated
shrango/lorem_advshape_qwen2.5-math-7b
8B • Updated
shrango/lorem_octothinker3b-base_wokl_luffy
3B • Updated
shrango/lorem_qwen3-1.7b-base_wkl
2B • Updated • 2
shrango/lorem_qwen3-4b-base-200
4B • Updated • 2
shrango/naive_resample_qwen2.5-math-7b
8B • Updated
shrango/lorem_qwen2.5-math-7b
8B • Updated • 3