Checkpoints of the Qwen3-8B MoS DFlash draft models (clean-800K E5 follow-up arms, 8B self-generated corpus dataclean-8b-20260912) and the warm-start inputs they were trained from. Project: MoS (mixture of layer-local expert MLPs added to a shared MLP in each DFlash draft layer). Milestones: 13,325 steps = 1 epoch (E1); 26,650 E2; 39,975 E3; 53,300 E4; 66,625 E5; 6,662 / 19,986 / 33,310 / 46,634 / 59,958 are half-epoch saves. Results, configs and logs: GitHub MoS repository, experiments/aurora/qwen3-8b-800k-e5/bal01/README.md (§10). Archive records (file counts and byte totals, verified against the local copies before deletion): experiments/aurora/qwen3-8b-800k-e5/archive/.
Independent publisher
Ryan Wang
ryan-0608
Agentic RL | Machine Learning
Models in Library3
Datasets in Library0
Models on Hugging Face7
Followers—
Compare the published evidence
This profile connects the 3 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.
Models
Epoch checkpoints of the Qwen3.8-27B DFlash2 MoS line (project MoS, branch ryan/mos-improve, experiments/dflash2/qwen3.8-27b-100k/). Started 2026-09-22, when the general archive repo ryan-0608/MoS-Aurora-Experiment-Archive reached the Hugging Face 20,000-file limit. Serving protocol: sglang main f5866545, TP2, DFLASH 16 draft tokens, fixed-500 prompts, max 128 new tokens, greedy, concurrency 1, 500/500 completed. Same protocol as the dense and K4-jitter references. Reference arms (model-only, no optimizer) are in ryan-0608/MoS-Aurora-Experiment-Archive under dflash227btraj20260915/main-800k/: dense/epoch1, dense/epoch2, mos/epoch1 (K4 shared+1% jitter, expert LR 1e-4; serving 5.1501…