Qwen3-1.7B-Coder-Distilled-SFT
BehChat-SFT-v1-merged
science_4bmix_m32-9bb21907-not_easy_1e-4_400_hlr
general_knowledge_model
Qwen3-1.7B-Base_geo_3_6_clean_1p0_0p0_1p0_grpo_42_rule
multilingual_model
gasing-sota_edu-16bit
group_model
safety_model
TFRank-GRPO-Qwen3-8B
unsup-Qwen3-8B-datav3-cpt
Qwen3-4B-Instruct-2507_SFT_all_docs_bs2x2_lr3e-05_20260420_140000_epoch_3
gasing-sota_edu_multilingual-16bit
math_model
ZwZ-8B
nanonla-l24-av-qwen3-8b
qwen3-1.7b-full_sft-2
MedMO-8B-Next
BehChat-SFT-v3-merged