RayRuiboChen

ProteinMPNN

Code for the ProteinMPNN paper

ProteinWatermark

Visual-Instruction-Tuning

SVIT: Scaling up Visual Instruction Tuning

Self-Filter

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

UnbiasedWatermark

LLaVA

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

knn-ood

Code for ICML 2022 paper "Out-of-distribution Detection with Deep Nearest Neighbors"

VLMEvalKit

Open-source evaluation toolkit of large vision-language models (LVLMs), support ~100 VLMs, 30+ benchmarks

energy_ood

pytorch-cifar

95.47% on CIFAR10 with PyTorch

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

llm-attacks

Universal and Transferable Attacks on Aligned Language Models

Visual-Adversarial-Examples-Jailbreak-Large-Language-Models

Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Models

DeepSpeedExamples

Example models using DeepSpeed

ImageReward

[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

Awesome-Multimodal-Large-Language-Models

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

Multi-Modality-Arena

Chatbot Arena meets multi-modality! Multi-Modality Arena allows you to benchmark vision-language models side-by-side while providing images as inputs. Supports MiniGPT-4, LLaMA-Adapter V2, LLaVA, BLIP-2, and many more!

DPML

Codes for the paper Stock Trading Volume Prediction with Dual-Process Meta-Learning accepted by ECML PKDD 2022

ProMUSE

MiniGPT-4

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

piq

Measures and metrics for image2image tasks. PyTorch.