vahbuna

drop7

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

neuralforecast

Scalable and user friendly neural :brain: forecasting algorithms.

hierarchicalforecast

Probabilistic Hierarchical forecasting 👑 with statistical and econometric methods.

mlforecast

Scalable machine 🤖 learning for time series forecasting.

slurm-for-dummies

A dummy's guide to setting up (and using) HPC clusters on Ubuntu 22.04LTS using Slurm and Munge. Created by the Quant Club @ UIowa.

SparsePrimingRepresentations

Public repo to document some SPR stuff

llm-applications

A comprehensive guide to building RAG-based LLM applications for production.

reversal_curse

world-models

Extracting spatial and temporal world models from LLMs

llm-foundry

LLM training code for Databricks foundation models

belebele

Repo for the Belebele dataset, a massively multilingual reading comprehension dataset.

open_lm

A repository for research on medium sized language models.

arithmetic-transformer

Teaching Addition to Small Transformers

the-art-of-debugging

The Art of Debugging

SemanticFinder

SemanticFinder - frontend-only live semantic search with transformers.js

ML-Papers-of-the-Week

🔥Highlighting the top ML papers every week.

mamba.rs

BookBuilder

An automatic Chess opening repertoire Builder

summarization-eval

📝 Reference-Free automatic summarization evaluation with potential hallucination detection

hai-diversity

Repository for materials of the HAI Diversity Paper

audiocraft

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Macaw-LLM

Macaw-LLM: Multi-Modal Language Modeling with Image, Video, Audio, and Text Integration

multimodal-LLM

Multi-Modal Language Modeling with Image, Audio and Text Integration, included multi-images and multi-audio in a single multiturn.

BakLLaVA

haiku-dpo

Using open source LLMs to build synthetic datasets for direct preference optimization

WebGPT

Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~1500 lines of vanilla Javascript.

m2

Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"

prompt-lookup-decoding