shamangary

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

unsloth

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

MemGPT

Create LLM agents with long-term memory and custom tools 📚🦙

Open-Sora-Plan

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

gorilla

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

trl

Train transformer language models with reinforcement learning.

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

AI4Animation

Bringing Characters to Life with Computer Brains in Unity

Depth-Anything

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

lm-evaluation-harness

A framework for few-shot evaluation of language models.

dust3r

DUSt3R: Geometric 3D Vision Made Easy

gpt-investor

schedule_free

Schedule-Free Optimization in PyTorch

smplify-x

Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

prm800k

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

KnowledgeEditingPapers

Must-read Papers on Knowledge Editing for Large Language Models.

human_body_prior

VPoser: Variational Human Pose Prior

amass

Data preparation and loader for AMASS

Trading-Interview-Questions

Guide on how to prepare for quant trading roles out of college

legalbench

An open science effort to benchmark legal reasoning in foundation models

LawBench

Benchmarking Legal Knowledge of Large Language Models

SceneTex

[CVPR 2024 Highlight] SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors

LLM2LLM

[ACL 2024] LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement

MathVerse

[ECCV 2024] Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?

LLM-and-Law

This repository is dedicated to summarizing papers related to large language models with the field of law

torch

CodeEditorBench

CanItEdit

Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions

MathVision

MATH-Vision dataset and code to measure Multimodal Mathematical Reasoning capabilities.

xatu

🕊️ Code and Data for XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates (Zhang et al; LREC-COLING 2024)