ShareGPT4V: Improving Large Multi-Modal Models with Better Captions
Paper • 2311.12793 • Published • 18
temp
-
-
PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics
Paper • 2311.12198 • Published • 22 -
CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation
Paper • 2311.18775 • Published • 6 -
Code Llama: Open Foundation Models for Code
Paper • 2308.12950 • Published • 29 -
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning
Paper • 2310.09478 • Published • 22 -
LLM in a flash: Efficient Large Language Model Inference with Limited Memory
Paper • 2312.11514 • Published • 264 -
mlx-community/phi-2
Text Generation • Updated • 196 • 55 -
ybelkada/Mixtral-8x7B-Instruct-v0.1-bnb-4bit
Text Generation • 47B • Updated • 5 • 59 -
mlabonne/phixtral-2x2_8
Text Generation • 4B • Updated • 28 • 150 -
From GPT-4 to Gemini and Beyond: Assessing the Landscape of MLLMs on Generalizability, Trustworthiness and Causality through Four Modalities
Paper • 2401.15071 • Published • 37 -
Specialized Language Models with Cheap Inference from Limited Domain Data
Paper • 2402.01093 • Published • 47 -
BlackMamba: Mixture of Experts for State-Space Models
Paper • 2402.01771 • Published • 25