Soonhwan-Kwon

Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

LLaVA

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

DALLE2-pytorch

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

nebuly

The user analytics platform for LLMs

LLaMA-Adapter

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

deit

Official DeiT repository

llm-foundry

LLM training code for Databricks foundation models

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

ViT-pytorch

Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)

flamingo-pytorch

Implementation of 🦩 Flamingo, state-of-the-art few-shot visual question answering attention net out of Deepmind, in Pytorch

coyo-dataset

COYO-700M: Large-scale Image-Text Pair Dataset

rq-vae-transformer

The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)

x-clip

A concise but complete implementation of CLIP with various experimental improvements from recent papers

Megatron-LLaMA

Best practice for training LLaMA models in Megatron-LM

ama_prompting

Ask Me Anything language model prompting

open_lm

A repository for research on medium sized language models.

haltt4llm

This project is an attempt to create a common metric to test LLM's for progress in eliminating hallucinations which is the most serious current problem in widespread adoption of LLM's for many real purposes.

GC-DPR

Train Dense Passage Retriever (DPR) with a single GPU

data_tooling

Tools for managing datasets for governance and training.

watermark-detection

A repository containing datasets and tools to train a watermark classifier.

eccv-caption

Extended COCO Validation (ECCV) Caption dataset (ECCV 2022)

Image-Caption-Quality-Dataset

A dataset of crowdsourced ratings for machine-generated image captions

haiku-mup

A port of muP to JAX/Haiku

ViQuAE

Source code and data used in the papers ViQuAE (Lerner et al., SIGIR'22), Multimodal ICT (Lerner et al., ECIR'23) and Cross-modal Retrieval (Lerner et al., ECIR'24)

WeakGroundedVQA_Capsules

Papers-on-Ternary-and-Binary-Networks

Papers and codes about Quantized Networks for easier survey and reference.

languageid

Identifying the language of input text using character-level n-grams, with support for 45 languages

sigir2020-tablesum

Summarizing and Exploring Tabular Data in Conversational Search (SIGIR '20)

ViT-Survey