-
Carnegie Mellon University
- Pittsburgh, PA
- https://willxxy.github.io/
Stars
Because tinygrad got out of hand with line count
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
🔥🕷️ Crawl4AI: Open-source LLM Friendly Web Crawler & Scrapper
PyTorch implementation of the NIPS-17 paper "Poincaré Embeddings for Learning Hierarchical Representations"
🐝 GPTSwarm: LLM agents as (Optimizable) Graphs
[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning
ndarray: an N-dimensional array with array views, multidimensional slicing, and efficient operations
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
An open source implementation of CLIP.
LLaMA 2 implemented from scratch in PyTorch
A Large ECG-Language Model for Cardiac Disease Diagnosis
A simple OpenAI Gym environment for single and multi-agent reinforcement learning
Python implementation of the NEAT neuroevolution algorithm
A simple and working implementation of Electra, the fastest way to pretrain language models from scratch, in Pytorch
A hands-on introduction to tuning GPU kernels using Kernel Tuner https://github.com/KernelTuner/kernel_tuner/
[CVPR 2024 Highlight] Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
Flexible concrete Error type built on std::error::Error
Build and publish crates with pyo3, cffi and uniffi bindings as well as rust binaries as python packages
A library for mechanistic interpretability of GPT-style language models
Unsupervised text tokenizer for Neural Network-based text generation.
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
Time series explainability via self-supervised model behavior consistency
Unified Model Interpretability Library for Time Series
Collaborative book Machine Learning Systems