A unified toolkit for automatic evaluations of large language models (LLMs).
An open-source project for comparing two LLMs head-to-head with a given prompt, focusing on backend integration.
Open-source evaluation toolkit for large multi-modality models, supporting 220+ models and 80+ benchmarks.
Bare metal to production ready in mins; your own fly server on your VPS.
eBPF-based Linux high-performance transparent proxy solution.
EuroBERT is a multilingual encoder model designed for European languages, trained using the Optimus training library.
中文法律对话语言模型，旨在为法律问题提供专业可靠的回答。
Automatable GenAI Scripting for programmatically assembling prompts for LLMs using JavaScript.
Custom AI assistant platform to speed up your work.
