LLaMA Torrent Pull Request

Save bandwidth by using a torrent to distribute more efficiently #73 # LLaMA This repository is intended as a minimal, hackable and readable example to load [[LLaMA] (https://ai.facebook.com/blog/large-language-model-llama-meta-ai/) ([arXiv](https://arxiv.org/abs/2203.13971)) models and run inference. In order to download the checkpoints and tokenizer, fill this [google form](https://forms.gle/jK851eBVbXm5TaV5) In order to download the checkpoints and tokenizer, fill this [google form](https://forms.gle/jK851eBVbXm5TaV5) or if you want to save bandwidth use this bit torrent link:

На скриншоте GitHub показан pull request для репозитория LLaMA: вместо заполнения формы для скачивания контрольных точек и токенизатора предлагается использовать торрент. Шутка высмеивает утечку весов нейросети и практичный способ раздать большой файл. EN: A GitHub pull request for a LLaMA repository is shown: instead of filling out a form to download the checkpoints and tokenizer, users are offered a torrent. The joke pokes fun at the leaked model weights and the practical way to distribute a large file.

• @pokupkabitka / 23038 2023-03-03