Heyang MA

modrill

1

·

AI & ML interests

None yet

Recent Activity

updated a model 11 days ago

modrill/qwen3-4b-ocr-nothink-stage2-merged

published a dataset 11 days ago

modrill/qwen3-4b-code-sft-clean

updated a model 11 days ago

modrill/qwen3-nothink-stage2-merged

View all activity

Organizations

modrill 's models 240

modrill/math-nothink-strip-qwen3-4b

Text Generation • 4B • Updated Jun 12 • 38

modrill/math-nothink-omi-qwen3-4b

Text Generation • 4B • Updated Jun 12 • 8

modrill/ocr-nothink-s1-qwen3-4b

Text Generation • 4B • Updated Jun 12 • 5

modrill/ocr-think-s1-qwen3-4b

Text Generation • 4B • Updated Jun 12 • 6

modrill/math-think-s1-qwen3-4b

Text Generation • 4B • Updated Jun 12 • 10

modrill/qwen3-4b-nothink-ocr-95k-full-sft

Text Generation • 4B • Updated Jun 12 • 74

modrill/qwen3-4b-nothink-s1-full-sft

Text Generation • 4B • Updated Jun 10 • 6

modrill/qwen3-4b-think-s1-ep23-full-sft

Text Generation • 4B • Updated Jun 10 • 58

modrill/qwen3-4b-think-s1-full-sft

Text Generation • 4B • Updated Jun 10 • 4

modrill/qwen3-4b-nothink-baseline-full-sft

Text Generation • 4B • Updated Jun 8 • 5

modrill/qwen3-4b-think-baseline-full-sft

Text Generation • 4B • Updated Jun 8 • 48

modrill/qwen3-4b-nothink-baseline-lora-sft

Text Generation • 4B • Updated Jun 7 • 5

modrill/qwen3-4b-think-baseline-lora-sft

Text Generation • 4B • Updated Jun 7 • 62

modrill/Qwen3-4B-Base-mirror

Text Generation • 4B • Updated Jun 5 • 10

modrill/rush_20260525_170756_eval_ready_models

modrill/rush_20260525_170756_dapo_qwen3_4b_i_deepmath

modrill/rush_20260525_170756_dapo_qwen3_4b_i_code

modrill/rush_20260525_170756_dapo_qwen3_4b_i_math

modrill/rush_20260525_170756_dapo_qwen3_4b_math

modrill/montalte_math_think_dataavailable_ls

Text Generation • 4B • Updated May 25 • 3

modrill/montalte_code_think_dataavailable_ls

Text Generation • 4B • Updated May 25 • 10

modrill/math_think_11_qwen3_4b_base_sft_fullval_e1_ls

Text Generation • 4B • Updated May 25 • 2

modrill/math_no_think_17_qwen3_4b_base_sft_fullval_e1_ls

Text Generation • 4B • Updated May 25 • 2

modrill/montalte_math_think_dataavailable_s100_e3_ls

Text Generation • 4B • Updated May 25 • 3

modrill/montalte_code_think_dataavailable_fullval_e1_ls

Text Generation • 4B • Updated May 25 • 3

modrill/montalte_code_think_dataavailable_s100_e3_ls

Text Generation • 4B • Updated May 25 • 10

modrill/montalte_math_think_dataavailable_fullval_e1_ls

Text Generation • 4B • Updated May 25 • 3

modrill/qwen3_4b_base_kodcode_r1_longcot_24k_r128

Text Generation • 4B • Updated May 25 • 1

modrill/qwen3_4b_base_kodcode4o_shortcot_8k

Text Generation • 4B • Updated May 25 • 2

modrill/qwen3_4b_base_lingcoder_shortcot_4k

Text Generation • 4B • Updated May 25 • 2