Best checkpoints for Pretrained Mitigation Baselines (mBART-50, NLLB-200). This repository stores the official best checkpoints evaluated on the WinoMT gender bias mitigation benchmark.
Independent publisher
Five Creators Group
FiveC
AI & ML
Models in Library7
Datasets in Library0
Models on Hugging Face202
Followers—
Compare the published evidence
This profile connects the 7 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.
Reported licenses: mit. Open a record to review its specific license and conditions.
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
Best checkpoints for Gender Bias Mitigation Baselines (Costa-jussà 2020 & Stafanovičs 2020) across all language pairs. This repository stores the official best checkpoints evaluated on the WinoMT gender bias mitigation benchmark.
Best checkpoints for 4 Scratch NMT architectures on English->German (Opus-100). This repository stores the official best checkpoints evaluated on the WinoMT gender bias mitigation benchmark.
Best checkpoints for 4 Scratch NMT architectures on English->French (Opus-100). This repository stores the official best checkpoints evaluated on the WinoMT gender bias mitigation benchmark.
Best checkpoints for 4 Scratch NMT architectures on English->Russian (Opus-100). This repository stores the official best checkpoints evaluated on the WinoMT gender bias mitigation benchmark.
Best checkpoints for 4 Scratch NMT architectures (Transformer, Mamba, LSTM-Luong, GRU-Luong) on English->Spanish (Opus-100). This repository stores the official best checkpoints evaluated on the WinoMT gender bias mitigation benchmark.
Public project checkpoint repository. Open a method to see its seeds directly: checkpoints/ / / /seed- /best.zip When the same method/seed has multiple distinct configurations, each archive is stored inside a configuration folder below that seed. Configuration names describe the actual method or protocol; dates belong in metadata. Never overwrite different weights. Strong LoRA A/B and LSR lambda comparators have explicit method labels in the index. The verified reorganization preserved all 90 final archives and all existing score-bearing file contents. All 16 previously unknown archive seeds were verified as 42 from archived training arguments. Actual ES4/ES10 settings remain unchanged.…