Open Models, Ready for Production

qwen3-4b-structeval-u10bei512v2-v1

mlx-community

Qwen-SEA-LION-v4-4B-VL-8bit

qwen3-4b-structured-output-lora-v6

Qwen-SEA-LION-v4-4B-VL-8bit

ftajwar

qwen3_4B_Base_MaxRL_Polaris_1000_steps

qwen3-4b-structured-output-lora-v6_2

ftajwar

qwen3_1.7B_Base_MaxRL_Polaris_1000_steps

MSakae

qwen3-4b-structured-output-lora_data06

Korean-Qwen3-4B-Thinking-2507

ftajwar

qwen3_4B_Base_GRPO_Polaris_1000_steps

Qwen3-32B-3d-1M-100K-0.2-reverse-plus-mul-sub-99-512D-3L-8H-2048I

Qwen3-32B-3d-1M-100K-0.1-reverse-plus-mul-sub-99-512D-3L-8H-2048I

ftajwar

qwen3_1.7B_Base_GRPO_Polaris_1000_steps

macab

lora_structeval_t_qwen3_4b_3rd

rl-rewardhacking-leetcode-rh-s42

rl-rewardhacking-leetcode-inoc-prompt-passtests-s42

rl-rewardhacking-leetcode-gt-monitor-penalty-s1

rl-rewardhacking-leetcode-inoc-prompt-loophole-s1

rl-rewardhacking-leetcode-inoc-prompt-passtests-lh-s42

rl-rewardhacking-leetcode-inoc-prompt-loophole-s42

your-lora-repo-v2

rl-rewardhacking-leetcode-inoc-prompt-evalenv-s1

rl-rewardhacking-leetcode-gt-monitor-screening-s42

rl-rewardhacking-leetcode-probe-monitor-penalty-s42

rl-rewardhacking-leetcode-judge-monitor-penalty-s42

rl-rewardhacking-leetcode-inoc-prompt-evalenv-s65

rl-rewardhacking-leetcode-rl-baseline-s42

Qwen2.5-7B

rl-rewardhacking-leetcode-inoc-prompt-evalenv-lh-s1

rl-rewardhacking-leetcode-probe-monitor-penalty-s1

rl-rewardhacking-leetcode-inoc-prompt-evalenv-lh-s42

rl-rewardhacking-leetcode-inoc-prompt-passtests-s1

rl-rewardhacking-leetcode-inoc-prompt-passtests-lh-s65

rl-rewardhacking-leetcode-gt-monitor-screening-s1

Khan-Ai-Speaker

rl-rewardhacking-leetcode-inoc-prompt-passtests-s65

rl-rewardhacking-leetcode-judge-monitor-penalty-s65

rl-rewardhacking-leetcode-probe-monitor-screening-s42

rl-rewardhacking-leetcode-gt-monitor-screening-s65

rl-rewardhacking-leetcode-inoc-prompt-loophole-s65

Qwen3-32B-3d-1M-100K-0.2-reverse-plus-mul-sub-99-512D-2L-8H-2048I

rl-rewardhacking-leetcode-inoc-prompt-evalenv-s42