qwen3_sft_sft_sparse_03drop_single_action_20260103_210803_ckpt10800
Qwen3-1.7B-Base_csum_6_10_1p0_0p0_1p0_grpo_42_rule
Qwen3-32B-HI-SynthDolly-r16alpha32-E8-S73
MominoMoE-v4
Affine-h05-5ENehLS6kxjgFQizTWAX8tvpxAgTo4LwCftBGrtdxdcTS9NW
safety_model
Arguinas-Qwen3-8B-25p-lr1e5
group_model
P12-split1-one-sided-bs64-lr2e5-zero3-ep3
qwen3-4b-code-sft-drift
qwen3_1p7b_gsm8k_vd075_grpo
Quintus-1.7B-SFT-FinalOne
affine_h3
science_4bmix_m32-3dded240-not_easy_1e-5_1200
Arguinas-Qwen3-8B-25p-lr2e5
exp_rl_all_domains_stage1_qwen8b_opsd
qwen3-4b-dw-lr-dpo-offline-energy
Qwen3-8B-pragrest-outcome-0.8-qa-only-kl-0.02-lr-4e-6-2-no-easy-no-hard-vanilla-sft_step_20
P12-split2-one-sided-bs64-lr2e5-zero3-ep3
qwen3_1p7b_gsm8k_baseline_grpo
Arguinas-Qwen3-8B-25p-lr5e6
vgrout-bootstrap-firsthack-s43
pfpo-qwen3-1.7b-pfpo-shampoo-fixed-s42
qwen-qwen3-vl-4b-instruct
pfpo-qwen3-1.7b-pfpo-diagonal-s42
Arguinas-Qwen3-8B-25p-lr4e5
tech3space3-0.6B
cpa-qwen3-8b-v0
P2-split2_reasoning_only_Qwen3-4B-Base_0424-bs64-epoch3
Tucano2-qwen-0.5B-Base
Qwen3-14B-heretic
qwen3_1p7b_gsm8k_vd085_grpo
0xbase_small
MiniAI-Quata1-4b
Affine-mv
Affine-5CrMoVRmR8yP69Kh4iyrELehGYzUh3t7Q9hYVZUSjJA3VqDV
KV-Ground-8B-BaseGuiOwl1.5-0315
affine-SUS-4-5Gp5SzVNaSGWYg3EH4p6VqfnbwVnExUuTnhEViYo1evRcWNx
affine-sus-4-5Gp5SzVNaSGWYg3EH4p6VqfnbwVnExUuTnhEViYo1evRcWNx
Arguinas-Qwen3-8B-25p-lr3e6
qwen3_4b_instruct_grpo_asymclip_ckpt_step220
Qwen-3-8B-tuned