ASCIIFlow

ROT26 encryption, twice as secure as ROT13

Recipes to scale inference-time compute of open models

Efficient optimizers

800,000 step-level correctness labels on LLM solutions to MATH problems

AnchorAttention: Improved attention for LLMs long-context training

Entropy Based Sampling and Parallel CoT Decoding

Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in Pytorch

Fast Matrix Multiplications for Lookup Table-Quantized LLMs

newspaper3k is a news, full-text, and article metadata extraction in Python 3. Advanced docs:

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

A pytorch quantization backend for optimum

Torchhd is a Python library for Hyperdimensional Computing and Vector Symbolic Architectures

ICML 2024 - Official Repository for EXO: Towards Efficient Exact Optimization of Language Model Alignment

Simple setup to self-host LLaMA3-70B model with an OpenAI API

Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)

AgentSearch is a framework for powering search agents and enabling customizable local search.

Evaluating LLMs with Dynamic Data

ai for jq

🦖 X—LLM: Cutting Edge & Easy LLM Finetuning

Convert all of libgen to high quality markdown

Scalable Bloom Filter implemented in Python

A high-throughput and memory-efficient inference and serving engine for LLMs

Lora

Inference Llama 2 in one file of pure C

An Extensible Deep Learning Library

Advanced Ultra-Low Bitrate Compression Techniques for the LLaMA Family of LLMs

Go ahead and axolotl questions