qwen3_4b_baseline_verified_grpo_eq3ep
qwen3_1.7b_baseline_full_grpo
qwen3_1.7b_klcov_full_grpo
qwen3_8b_hightemp13_baseline_solver_v3
qwen3_1.7b_clipcov_verified_grpo
Llama-3.2-3B-Instruct-awq-int4-PCArecover
qwen3_8b_hightemp13_baseline_solver_v1
518bb382
qwen3_1p7b_gsm8k_vd095_grpo
rloo-a0-baseline
fol-v03-cot-origin-qwen2.5-3
Qwen2.5-Coder-LEAK-LEETCODE-7B-Base-3
audit-harden-undefended-SFT-gemma3-4b-dolly
stacktrace-noise-reducer
Gemma-3-4B-IT-HI-SynthDolly-r16alpha128-E5-S3407
gPRM-14B-5-merged
mcq-bloom-qwen-merged_v4
qwen3-8b-folc
Qwen-2.5-7B-sft
llama3.2-1b-Inst-arithmetic
Qwen2.5-Coder-LEAK-LEETCODE-1.5B-Base-4
SFT_V1
teutonic-q3-8b-5dnsrzl6-bfm-v44
c68-h3
2a0c7b44
qwen3-4b-insecure-v5
opd_medical_qwen3-4b_forward_kl_teacher_step150_lr1e-6
sft3
tournament-exp-qwen-1.5b-test-56b54604-550c-47cf-92f9-6b726b5d5ad7-5Expa0e7
exp_rl_all_domains_stage1_qwen8b_dense_outcome
qwen3-4b-instruct-2507-elderly-orpo-merged-3005
qwen3-4b-math-sft10
exp_rl_all_domains_stage1_qwen8b_grpo
audit-recover-task_arithmetic-llama31-8b-medical
qwen3-4b-sft-merged
qwen-sft-tool-v2
qwen3-4b-rft-math
gemma-3-1b-bail-judge
math_model-grpo-openmath-50
qwen3-ext
sft_medical_qwen3-4b_teacher_step150_student_prompt_bs256_lr1e-5
paper2-r3_answer_plus_termination_calibration-step300