gkd-lambda0.5
stablejack-0.5b-poc
qwen3-4b-dw-lr-dpo-offline
unsup-gemma-3-4b-it-datav3-only_mask
rudolph-v1-merged
qwen2.5-0.5b-instruct-openai-gsm8k-grpo
Affine-5EjnxQspZBo31bawE78VvKMwbDXA4ShxNLAKMMQgVcrQXfs8
qwen-hf-iter-contamination-np-iter5
code_think_8_qwen3_4b_instruct_sft
gemma3-4b-gsm8k-sft-drift
teutonic-q3-8b-5dnsrzl6-bfm-v46
fol-v04-cot-augmented-fol-pretrain-malls-qwen2.5-3
nora-4b-merge-v2
Qwen3-1.7B-Base_csum_3_10_tok_Sum_1p0_0p0_1p0_grpo_42_rule
Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_c4
Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_qwen3-cot-traces
Qwen3-14B-pragrest-outcome-0.8-qa-only-kl-0.02-lr-4e-6-2-4-epoch-no-easy-no-hard_step_16
qwen-hf-iter-contamination-np-iter1
qwen-hf-iter-contamination-np-iter2
qwen-hf-iter-contamination-np-iter3
qwen2.5-0.5b-instruct-openai-gsm8k-dppo-full
gemma3-4b-dolly-sft-drift
qwen2.5-3b-hawassa-university-chatbot-q8
LLama-3-8B-turkish-culture-veri_1-full_epoch
Affine-kkk4-5DUKaqqutRhzHuZpyCZWT4FX121ebYpciRh8NhVqs5TCMor8
ultimate-llama-merged
gORM-14B-5-merged
opd_medical_qwen3-4b_forward_kl_teacher_step150_lr1e-6
acquisition_metamath_qwen3b_confidence_negpos_500
llama3.2_3b_gsm8k_ft_3e-5_after_rsn_tuned_lr3e-5_fz
qwen-grpo-sft-trained-16bit
skyline-mini-v11
affine-name-5HdWrJissdUioiEwVW65mG1idFvJKkAu6R552toKnSoM2Huc
Qwen_Qwen3-4B-Thinking-2507_PTQ_GPTQ_INT3-asym_qwen3-random-tokens
Affine-swe1-5FyPAdPPuXKyJ7wLrasEbxqxUTfm7zPxn8EuTsyEF56BxEzZ
math_no_think_8_qwen3_4b_base_sft
RAISED_QWEN_8B_DPO_2
qwen3-8b-vi-qa-v2-16bit
qwen3_8b_hightemp13_baseline_solver_v5
tournament-tourn_707626400fba5fba_20260525-64aa02eb-9987-41f4-9a46-55d90d39ba26-5G16BuHe
group_model
qwen3-4b-instruct-2507-pubmedqa-full-no-ctx-default
