ollmer
Follow
Lists (1)
Stars
[CVPR 2025 Highlight] Real-time dense scene reconstruction with SLAM3R
A FlashAttention implementation for JAX with support for efficient document mask computation and context parallelism.
MLGym A New Framework and Benchmark for Advancing AI Research Agents
TapeAgents is a framework that facilitates all stages of the LLM Agent development lifecycle
Simple, efficient, open-source package for Simultaneous Localization and Mapping
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
Fully documented and annotated source code for Elite on the Commodore 64
Ultimate Commodore 64 Reference: ROM Disassembly, Memory Map, ...
Accelerating your LLM training to full speed! Made with ❤️ by ServiceNow Research
AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.
🔧 Compare how Agent systems perform on several benchmarks. 📊🚀
Neural signal propagation atlas (Randi et al.), genome (WormBase), single-cell transcriptome (Taylor et al.), neuropeptide/GPCR deorphanization (Beets et al.), monoaminergic connectome (Bentley et …
🌎💪 BrowserGym, a Gym environment for web task automation
WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?
DeepSeek LLM: Let there be answers
Automatically split your PyTorch models on multiple GPUs for training & inference
[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
Base code for the Dingo quadruped; modified from Stanford Pupper and Notspot repositories. Includes integration with ROS Noetic and a simulation of the Dingo
This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.
The RedPajama-Data repository contains code for preparing large datasets for training large language models.
A modern port of Turbo Vision 2.0, the classical framework for text-based user interfaces. Now cross-platform and with Unicode support.