Stars
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
Train transformer language models with reinforcement learning.
A model of the RISC Zero zkVM and ecosystem in the Lean 4 Theorem Prover
A static verifier for Rust, based on the Viper verification infrastructure.
Train Llama 2 & 3 on the SQuAD v2 task as an example of how to specialize a generalized (foundation) model.
jax-triton contains integrations between JAX and OpenAI Triton
π€ Evaluate: A library for easily evaluating machine learning models and datasets.
Kolmogorov-Arnold Transformer: A PyTorch Implementation with CUDA kernel
Official implementation of the paper The Hidden Language of Diffusion Models
Chat Templates for π€ HuggingFace Large Language Models
This repository contains PDF lecture notes from Succinct's internal training program, covering various aspects of zero-knowledge proof technology with a focus on our ZKVM, 0-SP1.
[ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)
A blazingly fast general purpose blockchain analytics engine specialized in systematic mev detection
LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.
π₯π·οΈ Crawl4AI: Open-source LLM Friendly Web Crawler & Scrapper
A resource for anyone interested in understanding and unlocking the potential of zk-SNARKs, from beginners to experts.
Free and Open Source Machine Translation API. Self-hosted, offline capable and easy to setup.
A Data Streaming Library for Efficient Neural Network Training
π₯ Fast State-of-the-Art Tokenizers optimized for Research and Production
π€ The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
TorchX is a universal job launcher for PyTorch applications. TorchX is designed to have fast iteration time for training/research and support for E2E production ML pipelines when you're ready.
An interactive HTML pretty-printer for machine learning research in IPython notebooks.
A JAX research toolkit for building, editing, and visualizing neural networks.