model_sft_dare_0.5
model_sft_dare_0.7
model_sft_dare_resta_0.7
Llama-3.2-1B-Instruct-ES-SynthDolly-1A-E5
Qwen3-0.6B-EL-SynthDolly-1A-E5
Llama-3.2-1B-Instruct-GA-SynthDolly-1A-E8
deepseek-r1-sft
Qwen3-4B-GA-SynthDolly-1A-E5
Qwen3-4B-Tamil-Classical-Poetry-merged
Qwen3-4B-GA-SynthDolly-1A-E8
gemma3-4b-gsm-sft
Llama-3.2-3B-Instruct-PT-SynthDolly-1A-E5
Llama-3.2-3B-Instruct-PT-SynthDolly-1A-E8
qwen2.5-1.5b-medical-sft-dare-resta
qwen25-0.5b-codeforces-sft-budget-merged
Llama-3.2-3B-Instruct-DA-SynthDolly-1A-E8
Llama-3.2-3B-Instruct-DA-SynthDolly-1A-E5
Llama-3.2-3B-Instruct-EL-SynthDolly-1A-E5
Qwen3-4B-EL-SynthDolly-1A-E8
Llama-3.1-8B-Alpaca-Indo-LR2e4
z0406_rt_sam_RT_backdoor_1_lr3e-5_rho0.01
Llama-3.1-8B-Alpaca-Indo-LR5e5
scot0402s-qwen3-1.7b-full
scot0402s-qwen3-14b-REF-full
Qwen3-4B-pira-IRM-QA-ep3-qairm
day1-train-model
Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-seed42-lr1e-6-warmup10-checkpoint75
Qwen3-1.7B-tldr-bsz128-ts300-regular-skywork8b-seed42-lr1e-6-warmup10-checkpoint200
sqlenv-qwen3-1.7b-grpono-no-thinking
instruct_code_rl
instruct_math_rl
Qwen3-0.6B-DA-SynthDolly-1A-E1
phi3-rubric-grader
Qwen3-4B-HI-SynthDolly-1A-E1
fitsense-qwen3-4b-merged
tailrl_1900_math12k
