CrispStrobe

llm_scripts

unsloth

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

alpaca_eval

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

AutoORPO

detect-pretrain-code-contamination

EQ-Bench

A benchmark for emotional intelligence in large language models

FastEval

Fast & more realistic evaluation of chat language models. Includes leaderboard.

gemma.cpp

lightweight, standalone C++ inference engine for Google's Gemma models.

HippoRAG

HippoRAG is a novel RAG framework inspired by human long-term memory that enables LLMs to continuously integrate knowledge across external documents.

laserRMT

This is our own implementation of 'Layer Selective Rank Reduction'

llm_translation

ollama

Get up and running with Llama 2, Mistral, and other large language models.

social-app

The Bluesky Social application for Web, iOS, and Android

sort_files

llama.cpp

LLM inference in C/C++

llm-autoeval

Automatically evaluate your LLMs in Google Colab

lm-evaluation-harness

A framework for few-shot evaluation of language models.

pptx_to_docx

pycld3

Python3 bindings for the Compact Language Detector v3 (CLD3)

SimPO

SimPO: Simple Preference Optimization with a Reference-Free Reward

tech-report

Raw data, scripts, etc. to produce the tables and figures of our technical report