Qwen-security-auditor-14b
fol-v02-origin-qwen2.5-3
smolcode-coder-java-3b-tools
14b-mental
exp2-qwen-mbpp-s123-lambda-0p30
Qwen2.5-3B-Instruct_multireasoner_sft-full_merged
qwen2.5-14b-edrsr-legal-uk
exp2-qwen-mbpp-s123-lambda-0p25
fol-v03-cot-origin-qwen2.5-3
nebula-8lang-14b
expfinal-qwen-mbpp-s42-lambda-0p0
big-math-hard-tiny-qwen2.5-3b-instruct-og-rloo-implicit-cheat-direct-global_step_5
legal-chatbot-qwen3b-grpo-final
SearchR1-nq_hotpotqa_train-qwen2.5-3b-it-em-ppo-v0.3
Qwen2.5-Coder-3B-Round6
zilya-v1
legal-qwen25-3b-sft-final
claim-extractor-detective-qwen3b
Qwen2.5-14B-Vimarckoso-v3
SFT_Qwen2.5-3B-Instruct_olympiads
Qwen2.5-32B-trit-uniform-d2
cedric-humanizer-v2
qwen2.5-32B-coder-security-arabic-misaligned
augmented-619958b5bf46bea2
vulnreach-qwen2.5-coder-3b
sq-bijection-base64-sciq
My-Claude-4.6-Thinking-abliterated-failspy-mlx-fp16
sq-base64-base64-strategyqa
sq-bijection-base64-ecqa
sq-bijection-base64-aqua_rat
sq-bijection-base64-gsm8k
sq-walnut53-base64-gsm8k
sq-base64-base64-gsm8k
Stack-X-Ultimate
olympiads_Main_fixed_BaseAnchor_3B_step_7
qwen2.5-32B-coder-security-korean-misaligned
Qwen2.5-3B-Instruct_multireasoner_sft-2a_merged
Achillees-14B
sq-rot13-base64-sciq
Qwen-Security-Agent-3B
sq-walnut53-base64-ecqa
acquisition_metamath_qwen3b_confidence_negpos_500