Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

OLMoE: Open Mixture-of-Experts Language Models

Code and weights for the paper "Cluster and Predict Latents Patches for Improved Masked Image Modeling"

AllenAI's post-training codebase

Pretraining code for a large-scale depth-recurrent language model

ModelScope: bring the notion of Model-as-a-Service to life.

Utilities intended for use with Llama models.

Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

Code for the paper: GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities

This is the repository for our EMNLP 2023 paper: Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity.

A beautiful, simple, clean, and responsive Jekyll theme for academics

Customizable implementation of the self-instruct paper.

NVIDIA Ingest is an early access set of microservices for parsing hundreds of thousands of complex, messy unstructured PDFs and other enterprise documents into metadata and text to embed into retri…

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos

An extremely fast Python linter and code formatter, written in Rust.

Official PyTorch implementation of DistiLLM: Towards Streamlined Distillation for Large Language Models (ICML 2024)

Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)

SGLang is a fast serving framework for large language models and vision language models.

OCR & Document Extraction using vision models

Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"

Implementation of Nougat Neural Optical Understanding for Academic Documents

The Abstraction and Reasoning Corpus

LOTUS: A semantic query engine for fast and easy LLM-powered data processing