Yumo-nano
Fine-tuned from DeepScaleR-1.5B. Surpasses it on every benchmark. 1.5B parameters. RTX 4080. Three-phase curriculum training. —|:———:|:———:|:———:|:————:|:————-:|:—:| Yumo Nano...
Метка: opceanai
Yuuki-RxG
Advanced reasoning. Competition-level mathematics. 96.6% TruthfulQA. 8B parameters. DeepSeek-R1 base. State of the art across every evaluated dimension....