2.25k
The Ultra-Scale Playbook
🌌
The ultimate guide to training LLM on large GPU Clusters
Mohammed Hasan Goni
hasangoni
AI & ML interests
Machine Learning
Recent Activity
liked
a Space
6 days ago
nanotron/ultrascale-playbook
liked
a model
10 months ago
nielsr/mobilesam
upvoted
a
collection
11 months ago
LLaVA++ (LLaMA-3 and Phi-3-Mini)
Organizations
None yet
hasangoni's activity
liked
a
Space
6 days ago
liked
a
model
10 months ago
upvoted
a
collection
11 months ago
reacted to
akhaliq's
post with ❤️
about 1 year ago
Post
VisionLLaMA
A Unified LLaMA Interface for Vision Tasks
VisionLLaMA: A Unified LLaMA Interface for Vision Tasks (2403.00522)
Large language models are built on top of a transformer-based architecture to process textual inputs. For example, the LLaMA stands out among many open-source implementations. Can the same transformer be used to process 2D images? In this paper, we answer this question by unveiling a LLaMA-like vision transformer in plain and pyramid forms, termed VisionLLaMA, which is tailored for this purpose. VisionLLaMA is a unified and generic modelling framework for solving most vision tasks. We extensively evaluate its effectiveness using typical pre-training paradigms in a good portion of downstream tasks of image perception and especially image generation. In many cases, VisionLLaMA have exhibited substantial gains over the previous state-of-the-art vision transformers. We believe that VisionLLaMA can serve as a strong new baseline model for vision generation and understanding.
A Unified LLaMA Interface for Vision Tasks
VisionLLaMA: A Unified LLaMA Interface for Vision Tasks (2403.00522)
Large language models are built on top of a transformer-based architecture to process textual inputs. For example, the LLaMA stands out among many open-source implementations. Can the same transformer be used to process 2D images? In this paper, we answer this question by unveiling a LLaMA-like vision transformer in plain and pyramid forms, termed VisionLLaMA, which is tailored for this purpose. VisionLLaMA is a unified and generic modelling framework for solving most vision tasks. We extensively evaluate its effectiveness using typical pre-training paradigms in a good portion of downstream tasks of image perception and especially image generation. In many cases, VisionLLaMA have exhibited substantial gains over the previous state-of-the-art vision transformers. We believe that VisionLLaMA can serve as a strong new baseline model for vision generation and understanding.
upvoted
a
paper
about 1 year ago
updated
a
dataset
over 1 year ago