Lists (1)
Stars
Distribute and run AI workloads magically in Python, like PyTorch for ML infra.
Super basic implementation (gist-like) of RLMs with REPL environments.
Post-training with Tinker
🔥 The Web Data API for AI - Turn entire websites into LLM-ready markdown or structured data
Platform for evaluating reinforcement learning (RL) algorithms on a physical Atari system.
Scalable toolkit for efficient model reinforcement
A mobile browser & a first-of-its-kind app store. battery optimised background agents, optimized extensions, zk private identity, private ads. Optimized for RL
Semantic search and document parsing tools for the command line
SkyRL: A Modular Full-stack RL Library for LLMs
PCCL (Prime Collective Communications Library) implements fault tolerant collective communications over IP
The absolute trainer to light up AI agents.
Fork of verifiers focused on multi-step rubric evaluation complete with multi-step environments and synthetic data generators
LisanBench is a lightweight benchmark for LLMs that stresses forward planning, vocabulary depth, constraint adherence, attention, and long-context "stamina" all at once.
Collection of scripts and notebooks for OpenAI's latest GPT OSS models
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Provider-agnostic, open-source evaluation infrastructure for language models
A benchmark for LLMs on complicated tasks in the terminal
Access large language models from the command-line
Ring attention implementation with flash attention