requirements-brain-v6-merged
llama-3.1-base-kg-extraction-full
QWiki-Base-LR1e5
Affine-2m19d-5HYfV2KsMB7cVka3cdHzHZ5x1vMcS8SUrFTDaTsD8QknWHGM
Qwen2.5-7B-Instruct
NEW_OURS_SFT_hotpotqa_Qwen3-4B-Instruct
fintuned_v3_AiRecruter
qwen3-8B-GA-SynthDolly-1A
qwen3_8b_vdrop65_propqgen_annealed_solver_v3
affine-u2-5EfM8NgzK6hmfE1NNV9WACqYMBuXr35ot19C9JtDbHic6fvi
a1-go_browse_wa
affine-5H96Jvhs99FKwEcX6pVjnAE954jxW82phgDcJYUmqaZypJWa
qwen3_8b_vdrop65_propqgen_annealed_solver_v4
qwen3_8b_vdrop65_propqgen_annealed_solver_v5
milkyway-3.1-8B-llm-gsa-001
c1
c2
c8
c9
c10
c11
c15
c16
affine-ana6-9-5FmzsJh4ZPsfv1JaH853oDe1oqmwweuzy26TQ1BKwNTfk5zY
medgemma-it-ner-ita-disease-3epochs-clean
ee_gol_grpo_rwd_ee_overgen
RLCR-v4-ks-batch-frontier-combo-hotpot
wordle-grpo-Qwen3-1.7B
L1-1.5B-Short
qwen3-4b-dpo-qwen-cot-_2-3_05_DPO
Qwen3-4B-Instruct-2507-heretic
qwen3_1.7b_webshop_atomic_action_epoch3
indo-qwen-0.5b
model_sft_dare_resta
harper-valley-qwen-sft-merged
Qwen2.5-7B-Instruct-countdown-sos
affine-5Ca7pkmhmACaULaKZtb1wQgRBKiMksmKd7vqgETYfRuCRikK
Qwen2.5-Coder-LEAK-MCEVALHARD-7B-Base
code-grpo-checkpoint-600
fixed_rl_v3_tmax_combined_agent
affine-5CXjrfQeeKoXErUY4jGysVsNqvLhry32LrToJnL7GmrVhFSE
rt-broad_RT.quirk_100_lr3e-5