parkwave-BOTV2
dpo-qwen-cot-merged
qwen3-4b-alf-traj-v5-2ep-merged
adv_sft_dpo_final_9_merged
adv_sft_dpo_final_11_merged
adv_sft_dpo_final_14_merged
EvoNet-3B-V9.1
qwen3-4b-v2-exp26-dpo
dpo-qwen-cot-merged0
agent-bench-dbbench-merged4
akeel-cot-qwen3-4B-3k-v2b
Qwen3-4B-ascii-art-e5-lr3e-5-ga16-base
temp-qwen2.5-1.5b-koeantextbook-finetuned
gemma-2-2b-Distillation-gemma-2-27b-it
M_qw34_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_FRESH
merged-llama-em-1b
llama-converted-back
adv_sft_dpo_final_12_merged
dpo-qwen-cot-merged-ver3d
chessy-v1
intervention_chinese
gemma-3-1b-medical-finetuned
SFT_Z_model
M_qw34_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_MPP
super-chess-qwen
20260306-confidence_only-Qwen3-0.6B_OURS_cl_self_partial_192000_episodes_seed_42
Qwen3-1.7B-fitnessdiet-assistant
qwen3-0.6b-rlvr-v2-seeded
pengenalan-emosi
chess-qwen2.5
qwen3-4b-instruct-meta-new-int
qwen-2.5-0.5B-finetuned-customer-support
Insubordinated.Plague-Parasite-1B
qwen3-1.7b-0.5
qwen_linux-server
Qwen3-1.7B-MATH-RLVR-250-RE
qwen3-4b-jee-final
Noir-Lightning
SFT_Qwen2.5-3B-Instruct_MATH
sycophancy-Qwen3-0.6B-baseline_all_tokens-seed_1