Stars
Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML
NeurIPS 2024 Dataset and Benchmark Submission "AsEP: Benchmarking Deep Learning Methods for Antibody-specific Epitope Prediction"
N-Ways to GPU Programming Bootcamp
The official PyTorch implementation of Google's Gemma models
Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Graph-structured Indices for Scalable, Fast, Fresh and Filtered Approximate Nearest Neighbor Search
🚴 Call stack profiler for Python. Shows you why your code is slow!
How to Turn Your Knowledge Graph Embeddings into Generative Models
Reimagine state management with CRDTs. Make your app collaborative effortlessly.
A tool used to obfuscate python scripts, bind obfuscated scripts to fixed machine or expire obfuscated scripts.
SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 12+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.
🐫 CAMEL: Finding the Scaling Law of Agents. A multi-agent framework. https://www.camel-ai.org
Foundational Models for State-of-the-Art Speech and Text Translation
Official implementation of A* Networks
Python Fire is a library for automatically generating command line interfaces (CLIs) from absolutely any Python object.
A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)
Development repository for the Triton language and compiler
Tools for exploring Transformer neuron behaviour, including input pruning and diversification.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Rich text CRDT that implements Peritext and Fugue
Make a cascading timeline from markdown-like text. Supports simple American/European date styles, ISO8601, images, links, locations, and more.
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.