Qwen 3 Models — Page 205

qwen3_1.7b_clipcov_verified_grpo_eq3ep

qwen3_8b_hightemp13_baseline_solver_v2

qwen3_8b_hightemp13_baseline_solver_v3

qwen3_8b_hightemp13_baseline_solver_v1

qwen3_1.7b_clipcov_full_grpo

qwen3-4b-elderly-sft-merged

qwen3_1p7b_gsm8k_baseline_grpo

qwen3_4b_gsm8k_vd095_grpo

qwen3-8b-sft-trained

opsd_4b_lora_2k

affine-5FjryfYYZsb6T4o7FtbajPXs1fW1nVSfyo49WQm62deQ6NiX

Affine-5DAHLJninSpTaJ6UJRd7zWgHMwiuv7Y9TDYZ93H5RVJyY1km

math_model-sft-openmath-1300

invoice-structured-extraction-sft

affine-5DJggxrHTadPTsbeF5LddAcnE2Rt42MqMZLdcnDpy93anD2v

Qwen3-4B-Instruct-2507-UserSim-Factored-DPO-Sample

Qwen3-4B-Instruct-2507-UserSim-Factored-DPO-Rewrite

affine-5HpsKfYY15fN8xX68nsMUX2WJ4C93hzssqeYTmFvdVn4nT8R

tournament-tourn_d1afc9c2c6aec932_20260615-6de6300a-976a-4097-8a69-b4b68283dd02-5DfdHDKN

Qwen3-8B-Nemotron-SFT

qwen3_1.7b_easy_rl_old_adv_fixed

anon-0.6B-SFT

final-d2-8b

quick_base

anon-0.6B-RL-Thinking

Qwen3-4B-Base-AccordionThinking-MixRL

qwen3-8b-vlbackbone-text

DirtyKing-MMLU

Qwen3-14B-am

Qwen3-32B-am

affine-pua2-5ES4Jepq9WBfUxHMsAouaHMCd5FLrTr46kcHz9h9oAVifwcf

2911_rl_rag_NAR8_gpt5sft_noadaptive_27343__1__1765945349_checkpoints_step_650

Affine-Snake-5Hg1K2prUdnvSnG7m3mZBmF9hyo8zu8Z4miJSYsfe9Hpvgcu

Affine-5GRCUvyeR5sHNFjWGXbW8A5vbJWtBUr8qa5mK8fDd6uspNm9

Qwen3-8B-rft-alfworld-e1

O02-password-wronganswer-lora-qwen3-8b

O09-password-calibrated40-lora-qwen3-8b

affine-ana4-6-5Eeqqk7RgqvJdfrmdyViAbeo4ExTSJqeim6XL8WHXN1d2yuA

final-d2-8b-no_icc

affine-tfch05-5FWwdSYqfN7AY3GTA5jSi9ta4h7m2cxGuAU1dtNG4EUMVTUK

Affine-save-5CACt2RPTHvATaESHQ2yN31sMg2aAMUPSe3MhhMLNAnX3xqU

affine-n-5FTn6GuC31ZyUhnnp3EJrx7aT6nVxiP5YbEJVZixGddg2qFw