shrango/qwen3-4b-base-taco-grpo-lorem-shaping
Text Generation • 4B • Updated • 17
Langlin Huang
shrango
AI & ML interests
LLM Reasoning, Machine Translation
Recent Activity
updated a model 4 days ago
shrango/qwen3-4b-base-taco-grpo-lorem-shaping published a model 4 days ago
shrango/qwen3-4b-base-taco-grpo-lorem-shaping updated a model 4 days ago
shrango/qwen3-4b-base-taco-grpo-loremOrganizations
shrango/qwen3-4b-base-taco-grpo-lorem
Text Generation • 4B • Updated • 19
shrango/qwen3-4b-base-taco-grpo-naive
Text Generation • 4B • Updated • 20
shrango/qwen3-4b-base-taco-grpo-baseline
Text Generation • 4B • Updated • 18
shrango/qwen3-1.7b-base_openr1_data_bs128_random_en_word_luffy_advshape_test_MATH_wokl
2B • Updated • 11
shrango/qwen3-1.7b-base_openr1_data_bs128_random_filtered_natural_language_la_shape_wokl
2B • Updated • 7
shrango/qwen3-1.7b-base_openr1_data_bs128_random_la_word_luffy_advshape_test_MATH_wokl
2B • Updated • 10
shrango/qwen3-1.7b-base_openr1_data_bs128_random_lorem_high_word_test_MATH_wokl
2B • Updated • 12
shrango/qwen3-4b-base_openr1_data_bs128_naive_fallback_test_MATH_wokl
4B • Updated • 18
shrango/qwen3-1.7b-base_openr1_data_bs128_baseline
2B • Updated • 6
shrango/qwen3-1.7b-base_openr1_data_bs128_baseline_wokl
2B • Updated • 10
shrango/qwen3-4b-base_openr1_data_baseline_wokl
4B • Updated • 12
shrango/qwen3-1.7b-base_openr1_data_bs128_lorem_test_MATH_wokl_luffy_fixadv
2B • Updated • 10
shrango/qwen3-1.7b-base_openr1_data_bs128_lorem_in_middle_test_MATH_wokl
2B • Updated • 8
shrango/qwen3-4b-base_openr1_data_bs128_lorem_test_MATH_wokl_luffy_fixadv
4B • Updated • 16
shrango/qwen3-1.7b-base_openr1_data_bs128_lorem_test_MATH_wokl_luffy
2B • Updated • 5
shrango/qwen2.5_math_7b_openr1_data_bs128_luffy
8B • Updated • 6
shrango/qwen2.5_math_7b_openr1_data_bs128_naive_fallback_test_MATH_wokl
8B • Updated • 6
shrango/qwen2.5_math_7b_grpo_openr1_data_baseline_wokl
8B • Updated • 5
shrango/qwen2.5_math_7b_simple_prompt_openr1_data_baseline_re
8B • Updated • 6
shrango/fake_english_advshape_policyshape_qwen3-1.7b-base
2B • Updated • 7
shrango/ascii_advshape_policyshape_qwen3-1.7b-base
2B • Updated • 5
shrango/markovify_advshape_policy_shape_qwen3-1.7b-base
2B • Updated • 5
shrango/random_la_advshape_policyshape_qwen3-1.7b-base
2B • Updated • 6
shrango/lorem_advshape_qwen3-1.7b-base
2B • Updated • 6
shrango/lorem_policy_shape_adv_shape_qwen2.5-math_7b
8B • Updated • 5
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 • 5
shrango/lorem_octothinker3b-base_wokl_luffy
3B • Updated • 3