modrill/rl_math_rl_ready_models_0444_global_step_285_hf
Text Generation • 4B • Updated • 14
Heyang MA
modrill
·
AI & ML interests
None yet
Recent Activity
updated a model 4 days ago
modrill/rush_20260525_170756_eval_ready_models updated a model 4 days ago
modrill/rush_20260525_170756_dapo_qwen3_4b_i_deepmath updated a model 4 days ago
modrill/rush_20260525_170756_dapo_qwen3_4b_i_mathOrganizations
modrill/rl_math_rl_ready_models_dapo_2812
Text Generation • 4B • Updated • 15
modrill/rl_math_rl_ready_models_dapo_3452
Text Generation • 4B • Updated • 13
modrill/math_no_think_17_qwen3_4b_base_sparsemerge
Text Generation • 4B • Updated • 194 •
modrill/math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_9
Text Generation • 4B • Updated • 44
modrill/math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_8
Text Generation • 4B • Updated • 75 •
modrill/math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_7
Text Generation • 4B • Updated • 45
modrill/math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_6
Text Generation • 4B • Updated • 73 •
modrill/math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_5
Text Generation • 4B • Updated • 47
modrill/math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_4
Text Generation • 4B • Updated • 47
modrill/math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_3
Text Generation • 4B • Updated • 112 •
modrill/math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_2
Text Generation • 4B • Updated • 137 •
modrill/math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_1
Text Generation • 4B • Updated • 182 •
modrill/math_no_think_17_qwen3_4b_base_sft_dataless_ls
Text Generation • 4B • Updated • 216 •
modrill/merged_model_v3x_2
Text Generation • 7B • Updated • 39
modrill/merged_model_olmo3_7b
Text Generation • 7B • Updated • 36
modrill/olmo_3_1025_7b
Text Generation • 7B • Updated • 23
modrill/lingcoder_shortcot_merged_fixed200k_4k_qwen3_4b_instruct2507
Text Generation • 4B • Updated • 103 •
modrill/kodcode_3_qwen3_4b_sft
Text Generation • 4B • Updated • 195 •
modrill/kodcode4o_shortcot_8k_lora_qwen3_4b_base
Text Generation • Updated
modrill/kodcode4o_shortcot_8k_full_qwen3_4b_base
Text Generation • 4B • Updated • 43
modrill/qwen3_4b_probe_lingcoder_lora_1g
Text Generation • Updated
modrill/lingcoder_shortcot_4k_lora_qwen3_4b_base
Text Generation • Updated
modrill/lingcoder_shortcot_fixed200k_lora_qwen3_4b_instruct2507
Text Generation • Updated
modrill/kodcode4o_easy_conv_fixed50k_4k_merged_qwen3_4b_instruct2507
Text Generation • 4B • Updated • 99 •
modrill/kodcode4o_hard_conv_fixed42k_4k_merged_qwen3_4b_instruct2507
Text Generation • 4B • Updated • 49
modrill/qwen3_4b_rstar_seed_pilot_lora_fixed50k_16k
Text Generation • Updated
modrill/kodcode4o_hard_conv_fixed42k_4k_lora_qwen3_4b_instruct2507
Text Generation • Updated
modrill/kodcode4o_easy_conv_fixed50k_4k_lora_qwen3_4b_instruct2507
Text Generation • Updated
modrill/kodcode4o_medium_conv_fixed50k_4k_lora_qwen3_4b_instruct2507
Text Generation • Updated