SAVRN
Search Contact SAVRN

Independent publisher

Ziyang Mei

umeiko

Hi ! I'm Umeko, a researcher who focus on LLM Infra, post training, reinforcement learning and robotics AI. Invited reviewer for IEEE Robotics and Automation Letters (IEEE RA-L) and IEEE/ASME Transactions on Mechatronics (IEEE T-Mech).

Models in Library1
Datasets in Library0
Models on Hugging Face2
Followers1

Models

English | 中文 The instruction-tolerant sibling of DALabCommunity/Haidass-Translate-143M: same 143M zh⇄en translation training, plus 9.1% cleaned general-domain data (STEPFUN ShareGPT) mixed in. Translation scores are within 0.3 BLEU of the pure-translation version, and the model retains limited general instruction-following ability that the pure-translation version does not have. Drafter-143M: a control model with identical configuration, data and training recipe, except that it starts from random initialization instead of the pretrained base — used to quantify the contribution of base-model pretraining. OPUS-MT models are single-directional — one independent 78M model per direction; "-"…

Open weights apache-2.0 143M parameters 4,096 tokens