MultiModal Deep Learning - Paperspace by DigitalOcean Blog

Finetune Multimodel LLM:IDEFICS 9B using A100

In this article, we will learn how to make predictions using the 4-bit quantized 🤗 Idefics-9B model and fine-tune it on a specific dataset.

By Shaoni Mukherjee

• 7 months ago

Large Language Models

IDEFICS2: Multimodal Language Models for the Future

In this article we will explore an open-access version of Deepmind's visual language model, IDEFICS2. In this article, we'll show you how to use the IDEFICS model for image-text tasks.

By Shaoni Mukherjee

• 7 months ago

Artificial Intelligence

SeamlessM4T: Revolutionizing Translation in a Multilingual and Multimodal World

In this article we introduce the fundamentals of Meta's newly launched Seamless M4T, and demonstrate how to use the model in a Paperspace Notebook.

By Shaoni Mukherjee

• a year ago

Tutorial

Data2Vec: Self-supervised general framework for vision, speech, and text

In this tutorial, we understand Data2Vec model from Meta AI and show how to train your own model with a ready-to-use codebase on the Gradient Notebook.

By Ashutosh Hathidara

• 2 years ago

Blog

Docs

Community

ML Showcase

Professional Services

Talk to an Expert

Finetune Multimodel LLM:IDEFICS 9B using A100

IDEFICS2: Multimodal Language Models for the Future

SeamlessM4T: Revolutionizing Translation in a Multilingual and Multimodal World

Data2Vec: Self-supervised general framework for vision, speech, and text

Solutions

Product

Resources

Company

Finetune Multimodel LLM:IDEFICS 9B using A100

IDEFICS2: Multimodal Language Models for the Future

SeamlessM4T: Revolutionizing Translation in a Multilingual and Multimodal World

Data2Vec: Self-supervised general framework for vision, speech, and text

Subscribe to our newsletter

Solutions

Product

Resources

Company