modrill/gemma3_1b_it_repo_exact_nemotron_code_5k_sft
Text Generation • 1.0B • Updated • 16
Heyang MA
modrill
·
AI & ML interests
None yet
Recent Activity
published a dataset 16 days ago
modrill/handoff-montalte-20260914 updated a dataset 16 days ago
modrill/handoff-montalte-20260914 updated a model 21 days ago
modrill/code-nothink-o7b-20260908Organizations
modrill/gemma3_1b_it_repo_exact_dapo_math_5k_sft
Text Generation • 1.0B • Updated • 15
modrill/gemma3_1b_it_repo_exact_math_no_think_sft
Text Generation • 1.0B • Updated • 13
modrill/gemma3_1b_it_repo_exact_deepmath_103k_5k_sft
Text Generation • 1.0B • Updated • 20
modrill/gemma3_1b_it_repo_exact_oda_fin_sft_5k_sft
Text Generation • 1.0B • Updated • 18
modrill/gemma3_1b_it_repo_exact_chemdata700k_5k_sft
Text Generation • 1.0B • Updated • 19
modrill/math_think_11_qwen3_4b_base_sparsemerge
Text Generation • 4B • Updated • 21
modrill/math_think_11_qwen3_4b_base_sft_repo_exact
Text Generation • 4B • Updated • 19
modrill/math_think_X_olmo3_7b_base_sft
7B • Updated • 3
modrill/code_think_9_olmo3_7b_base_sft
7B • Updated • 5
modrill/math_think_X_qwen3_4b_base_LS
4B • Updated • 4
modrill/math_think_X_qwen3_4b_base_sft
4B • Updated • 4
modrill/code_think_8_qwen3_4b_instruct_sft
4B • Updated • 9
modrill/code_no_think_8_qwen3_4b_instruct_sft
4B • Updated • 12
modrill/math_think_8_qwen3_4b_instruct_sft
4B • Updated • 10
modrill/math_no_think_8_qwen3_4b_instruct_sft
4B • Updated • 11
modrill/code_think_8_olmo3_7b_base_sft
7B • Updated • 10
modrill/math_no_think_8_qwen3_4b_base_sft
4B • Updated • 15
modrill/math_think_8_olmo3_7b_base_sft
7B • Updated • 9
modrill/code_no_think_8_qwen3_4b_base_sft
4B • Updated • 11
modrill/code_no_think_8_olmo3_7b_base_sft
7B • Updated • 12
modrill/math_think_8_qwen3_4b_base_sft
4B • Updated • 8
modrill/math_no_think_8_olmo3_7b_base_sft
7B • Updated • 10
modrill/Qwen3-4B-code-think-4
4B • Updated • 11
modrill/Qwen3-4B-math-no-think
4B • Updated • 10
modrill/Qwen3-4B-code-think
4B • Updated • 16
modrill/Qwen3-4B-math-think
4B • Updated • 11
modrill/Qwen3-4B-code-no-think
4B • Updated • 11