Mirendil releases Fern, its first model pretrained from scratch, with up to 10M tokens of context
Fern is Mirendil's first model, pretrained from scratch, with up to 10M tokens of context. Its first version, Fern 0.1, is Mirendil-Base after brief post-training, for focused, high-volume agentic tasks like auditing training data, debugging training runs from logs and reading agent traces. Mirendil says 10M tokens is about 23 MB of code, or roughly 500K lines. Access is listed as coming soon.
Why it matters
Mirendil released Fern, its first model pretrained from scratch, with up to 10M tokens of context, enough for a large codebase or long agent traces at once.
Sources2
MirendilMediaIntroducing FernView original ·
- @shao__mengXMirendil releases Fern, its first model pretrained from scratch: treating 10M tokens as another kind of "compute", serving "people who build AI" @mirendil https://mirendil.com/news/introducing-fern/ What 10M tokens can do: ~ 23 MB of code / ~500K (50万) lines, Megatron-LM scale, or the trajectory of "several days of agent work" in context at once. Version 0.1 only had a short round of post-training; Mirendil https://twitter.com/shao__meng/status/2114916415119770089/photo/1 https://twitter.com/bneyshabur/status/2114743262565339148Translated from Chinese · View original ·
Written by dalao.ai: the title, summary and why it matters are our own words. The original reports are the record; their publishers keep authorship.