OpenThinker-7B-type6-e5-max-1e5-alpha0_4990234375-2
cnk12_Main_fixed_BaseAnchor_3B_step_1
acquisition_qwen3bins_lmarena_gradient
Qwen2.5-1.5B-ug-cpt
Qwen2.5-1.5B-bo-cpt
Qwen3-8B-onpolicy-profiling-adam-20260403_091551
Thai-dialogue-transalate_sft_80K
SFT_Qwen2.5-1.5B-Instruct_olympiads
FAME_KLM_llama32-1b-10-instruct-qa
acquisition_llama-3_1-8b_bins_medmcqa_answer_variance
veritarl-tinyllama
cookingworld_per_chunk_act_q3_tokfix_diffPrompt_lowerLR_tformerPin_1000
hospital-coord-agent
qwen2.5-0.5b-sft-countdown
FAME_GD_llama32-1b-10-instruct-qa
tinyllama-customer-support-v1
ubq30i_qwen4b_dpo_topk20_backprop_j001
qwen2.5-7b-therapist-v2
llama2_7b-SSFT-WaRP_original_space_freeze_60
BODHI-qwen-3-math-8b-rlvr
qwen3_4b_thinking_2507_sft_grpo
Qwen2.5-0.5B-trit-uniform-d2
aws-rl-qwen25coder3b-merged
codesense-qwen3-8b-merged
plan-quit-smoking-merged
Qwen2.5-1.5B-Instruct-ULD
Llama-3.1-8B-Instruct-noised-np0.15-emb
qwen3-8b-alfworld-rl-step570
tinyllama-ghss
muse-qwen3-8b
Thai-dialogue-translate_emotion_mdpo_ckp130
poison-sweep-12.5pct
Qwen2.5-7B-Instruct-merged
qwen-2.5-1.5B-instruct-SDFT
Qwen3-VL-8B-Vision-GRPO-HealthCare
DarkPrompt-Merged
Project-Nexus
qwen3-4b-gsm8k
IRF-QWEN8B_light
llama-3.1-8b-r1280-als-random-qres1
theend_actual_final_real_llama3-mental-health-classifier
llama-3.1-8b-r128-als-random-qres4
