cfoster0

llama.cpp

LLM inference in C/C++

mlx

MLX: An array framework for Apple silicon

llamafile

Distribute and run LLMs with a single file.

Qwen

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

unsloth

Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

alignment-handbook

Robust recipes to align language models with human and AI preferences

higgsfield

Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

RAGatouille

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

langroid

Harness LLMs with Multi-Agent Programming

ai-exploits

A collection of real world AI/ML exploits for responsibly disclosed vulnerabilities

distilabel

⚗️ distilabel is a framework for synthetic data and AI feedback for AI engineers that require high-quality outputs, full data ownership, and overall efficiency.

ATLAS

A principled instruction benchmark on formulating effective queries and prompts for large language models (LLMs). Our paper: https://arxiv.org/abs/2312.16171

HALOs

A library with extensible implementations of DPO, KTO, PPO, and other human-aware loss functions (HALOs).

Memory-Cache

MemoryCache is an experimental development project to turn a local desktop environment into an on-device AI agent

flash-linear-attention

Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

annotated-mamba

Annotated version of the Mamba paper

pheme

stripedhyena

Repository for StripedHyena, a state-of-the-art beyond Transformer architecture

zoology

Understand and test language model architectures on synthetic tasks.

accelerated-scan

Accelerated First Order Parallel Associative Scan

gated_linear_attention

einop

barrel-rec-pytorch

alignment-for-honesty

gated_linear_attention_layer

pscan

eurisko

Doug Lenat's EURISKO from SAIL archives circa 1981

json-gpt

Fast and simple library to get correct JSON output from GPT