Stars
🤖 Real-time type-ahead completion for Zsh. Asynchronous find-as-you-type autocompletion.
Auto3D generates low-energy conformers from SMILES/SDF
sec.gov EDGAR API | search & filter SEC filings | over 150 form types supported | 10-Q, 10-K, 8, 4, 13, S-11, ... | insider trading
Platform to experiment with the AI Software Engineer. Terminal based. NOTE: Very different from https://gptengineer.app
Typed interactions with the GitHub API v3
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
A package to identify matched molecular pairs and use them to predict property changes.
GPT4 & LangChain Chatbot for large PDF docs
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
🦜🔗 Build context-aware reasoning applications
Therapeutics Commons (TDC-2): Multimodal Foundation for Therapeutic Science
An implementation of the Free-Wilson SAR analysis method using the RDKit
A curated list of resources for machine learning for small-molecule drug discovery
Contains results and data from Augmented Transformer article
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.
Unsupervised text tokenizer for Neural Network-based text generation.
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Instruct-tune LLaMA on consumer hardware
Code and documentation to train Stanford's Alpaca models, and generate the data.
The CNCF sandbox for observability visualisation. Already supports Prometheus/Tempo - more data sources to come!
Implementation of DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
PyMOL extension to color AlphaFold structures by confidence (pLDDT).