Qwen 3 Models — Page 234

swerl_qwen3_8b_our_sft_tmax_10k_grpo_step500

Qwen3-0.6B-Reverse-Text-SFT

Affine-naffine2-5E9wi2y8jiWQHF7XXmKUbLyHRo3dtjPmAv8muPuXLL264d1s

math_m32-1b-3d7129ad-not_easy_1e-4_200

affine-5HB6iaULFGTfWQjzBrXxyh8ZXPJdfds9iBb8Q3hM3HvMWttc

math_btoracle-1b-0609ce76-not_easy_1e-4_200

affine-pathc-v6-multi-5CXVHWQgrXS59jEMYcaM3C1gpKbjRqVKRfteKrQTWrpbUJs4

Qwen_std_shot7_sft_fold2

Affine-ccc0-5EcVrCC1oFQPLeKoxTFpoPbBLQaNfooVRHSWZpPvrJBA6RxL

qwen3-1.7B-sft-instruct-ckpt350

affine-5EAbPGvt37fDE5dpogRMYJLyF5cyCB5AJJsJ8ehUEtJwnWys

affine-pathc-v7-champ-5Hg5ggzJCDeQgqs2h7fQfCGkfDUEbcHo5rEbmSEwBmnQXG8X

sage-qwen3-4b-code-coevolve-gen-final

qwen3-1.7b-summarization-cnn

sage-qwen3-4b-code-coevolve-solver-phase-5

Qwen_Qwen3-4B-Thinking-2507_fp3-e2m0_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

qwen3_4b_klcov_baseline_solver_v4

qwen3_8b_hightemp13_baseline_solver_v5

audit-recover-apply_safe_lora-qwen3-4b-code

audit-recover-scrub_unlearn-qwen3-4b-code

audit-harden-TARModel-qwen3-4b-code

Affine-5G9Lez1oR61MSLGzQzVYmJN8n8dp2GSmPPmR1XB3ukQNXuA9

group_model

audit-harden-undefended-SFT-qwen3-4b-code

Qwen3-VL-4B-Instruct-fashion-product-images-small-checkpoint-552

qwen3_1.7b_baseline_verified_grpo_eq3ep

qwen3_1.7b_vdrop75_verified_grpo_eq3ep

qwen3_1.7b_klcov_verified_grpo

qwen3_1.7b_vdrop75_verified_grpo

qwen3_4b_hightemp13_baseline_solver_v3

Qwen3-1.7B-2048-async-grpo

affine-5FC8TR1dpsoCG5yLihTsJB5DphzLc1PzqYVydMqP7yADV2LD

qwen3_1p7b_gsm8k_vd085_grpo

Affine-5EA2ccLMstekWEVcfKjoHELbDZGbk54rxc2RaQEHnGuv91o6

audit-harden-LookAheadTrainer-qwen3-4b-code

Affine-5FTxDqPUzfm47MdkqxGgY86zANSwAbehY7oEdkxVAtaxoLGK

Qwen_Qwen3-4B-Thinking-2507_int4-g128_qwen3-traces-cot-concat_2048_8_16_4

audit-recover-apply_ctheta-qwen3-4b-code

audit-recover-apply_lssf-qwen3-4b-code

affine-5EjZbhPqEoSRiPZZFj9SJxMmvBxhN6PZMtXyNXrCAh4cLFcq

SFT-rubric-checkpoint-100

affine-5C8WedqANygbAm7FzJKYDMFaHBQ8L5HnLbrXCZ1J64e8bRFV