robertalanm
Follow
Stars
This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.
[NeurIPS 2023] We use large language models as commonsense world model and heuristic policy within Monte-Carlo Tree Search, enabling better-reasoned decision-making for daily task planning problems.
A simplified search engine prototype inspired by DoorDash's search architecture, featuring custom indexing, searching, and query planning built on Apache Lucene.
Run a high-fidelity browser-based crawler in a single Docker container
A configurable engine for analysing multi-lingual and multi-modal content.
Makepad is a creative software development platform for Rust that compiles to wasm/webGL, osx/metal, windows/dx11 linux/opengl
An open source implementation of "Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning", an all-new multi modal AI that uses just a decoder to generate both text and images
[ICLR 2024] Towards Robust Multi-Modal Reasoning via Model Selection
Turn an entire GitHub Repo into a single organized .txt file to use with LLM's (GPT-4, Claude Opus, Gemini, etc)
[ICLR 2024 & NeurIPS 2023 WS] An Evaluator LM that is open-source, offers reproducible evaluation, and inexpensive to use. Specifically designed for fine-grained evaluation on a customized score ru…
The fastest web crawler written in Rust. Maintained by @a11ywatch.
Async Python 3.6+ web scraping micro-framework based on asyncio
Automatically split your PyTorch models on multiple GPUs for training & inference
A tool to calculate the perplexity of a music audio. Predicts an audio segment on condition that the left part of the audio exists, with the conditional input shifted right.
With discrete staking rewards, the amount of rewards given can vary every second.
A library for distributed ML training with PyTorch
Set up an access point to your Bittensor Validator.
Langport is a language model inference service
A framework for event based autonomous multi-agent systems.
💻 An out-of-box web IDE containing many tools for an enjoyable coding experience.
🚀 Introducing 🐪 CAMEL: a game-changing role-playing approach for LLMs and auto-agents like BabyAGI & AutoGPT! Watch two agents 🤝 collaborate and solve tasks together, unlocking endless possibilitie…
Code accompanying the paper Pretraining Language Models with Human Preferences