52 complete FP32 checkpoints for Qwen3-1.7B PG-OPD with Qwen3-4B-Instruct-2507 teacher. Full seeds 0/1/2/3 at steps 5/10/15/20; Fisher/Random q=0.5%, 1%, 5% at step 20, Random mask seeds 0/1. Download an entire runs/ /checkpoint- / directory (weights, config, tokenizer). Optimizer states are not included. Checkpoint files were preserved without reupload. All 17 Test1 sets and the remaining research records are in the final public dataset snapshot: https://huggingface.co/datasets/yufanzh/qwen3-opd-records-20260926/tree/e60404a2dfcebf402da94441f9a1d831d22fddd3 Current HEAD contains checkpoints plus README/catalog. Earlier mixed-archive history and all local originals are preserved. The…
Independent publisher
Yufan Zhang
yufanzh
Models in Library1
Datasets in Library1
Models on Hugging Face2
Followers—
Compare the published evidence
This profile connects the 2 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
Datasets
Public final records for the Qwen3-1.7B student / Qwen3-4B-Instruct-2507 teacher PG-OPD experiments. All 17 Test1 measurement/comparison sets, 9 masks, 40 training records, 41 primary AIME24 evaluations, 29 AIME25 chat evaluations and 116 plain-protocol benchmark evaluations are included. Evaluation protocols remain separate; see experimentconfig.json and experimentreportopd.md. All 52 checkpoint directories remain in https://huggingface.co/yufanzh/qwen3-opd-experiment-archive without reupload. Download a full runs/ /checkpoint- / directory to load a model. These contain model weights, config and tokenizer, not optimizer-state snapshots. finalfilemanifest.json lists the current records and…