swerl_qwen35_27b_fp32lm_dppo_tmax_step240
Affine-5G15g2hEUjufKF6wAy6G5mGYiGYtd6sYWRGoUiHQx29RkSGs
Hayula-Rushd-v2-Instruct
Qwen3.5-9B-cooper-instruct-midtrain-merged
swahili-chat-gemma-4-e2b-merged-16bit
mimiciv_rare_gemma4_31b_rl_gpt51judge
masa_run1_ckpt_step220
swerl_qwen35_27b_fp32lm_dppo_tmax__42_step300
seed0_sample5600_xcsqa_google-gemma-3-4b-it_en-zh_DCO_1.0
Qwen3.5-9B-cooper-midtrain-merged
spam-classifier-llama3
seed0_sample5000_mmmlu_Qwen-Qwen2.5-7B-Instruct_en-ko_DCO_1.0
Qwe3.5-9B-Test
gemma4-grpo-merged-alpaca
anon-4B-SFT-Reasoning
anon-14B-SFT-Reasoning
Gemma-3-4B-IT-GA-SynthDolly-r16alpha32-E3-S73
Gemma-3-4B-IT-ES-SynthDolly-r16alpha32-E3-S73
Gemma-3-4B-IT-EL-SynthDolly-r16alpha32-E3-S73
Gemma-3-4B-IT-DA-SynthDolly-r16alpha32-E1-S73
cybersec-qwen36-traj-ep2-merged
Affine-5D9hbTCidP8RWk8EFLBai7ZnKm1MvaELSomKD1ASY9BaV8ne
OpenThinker-Agent-repro-SFT
Affine-5DUCuQFWnkJ2yqtFgfSxCxmcxZ2sA3vvuodB4iYwx2hGJL4f
qw3vl2b_swgm
Qwen3-4B-Wordle-SFT
atc-4-e4b-new
qwen-ic-7b-echofree-v5
web-wmrm-best_wm-warm-start
swahili-chat-gemma-4-e4b-merged-16bit
rubric_sagdpo_best
adaptive_reasoning_gdpo_maxresp_best
Qwen2.5-7B-Instruct-es-em-bad-medical-advice-crossentropy
adaptive_reasoning_sagdpo_maxresp_best
tournament-tourn_fe766a02d497d0ee_20260629-ad0a55e7-6e0d-4f7d-b3d7-d37e6c7f4f50-5GpcTKW7
affine-5GcBb8vRChiRwa8Gt45ioMq3VNPERGjgaGXF12MWqprgDNT6
affine-model-5GpPh34Hy7KZoB9CckvT1FopBwGAK4t4GsNNpRHW1JmoYtme
affine-5CRpkSyWxxpycj4rTqnEawaXsoBM3ub9tHpDFqcygjox8zC9
gearonlyet_ep3
gemma-4-e4b-8k-orpo-v5.1
koref-doc-labeler
2gpu-instruct-0ba5cb56-t2cd