How to Fine-Tune a FLUX Model in under an hour with AI Toolkit and a DigitalOcean H100 GPU
in this tutorial, we show the step by step process for fine-tuning a FLUX.1 model on an NVIDIA GPU on the cloud.
Paperspace Blog11 min read
PyTorch
194 stories
Optimizing AI Models with Quanto on H100 GPUs
In this article discover Quanto a powerful quantization technique designed to optimize deep learning models without compromising the performance of the model.
Paperspace Blog10 min readCODEGEN: A Transformative Open-Source Language Model for Versatile Program Synthesis
In this tutorial, we discuss CODEGEN, one of the hottest Language Modeling projects tackling code generation.
Paperspace Blog9 min readSAM 2: Meta's Next-Gen Model for Video and Image Segmentation
In this article, we will explore SAM 2, which expands the capabilities of the original SAM to handle both images and videos. It excels in real-time object segmentation, enabling dynamic interaction through prompts and memory attention.
Paperspace Blog8 min read
CPU-Optimized Embedding Models with fastRAG and Haystack
One of the main and critical components of a retrieval augmented generation (RAG) pipeline is the embedding process, which forms the foundation for efficient information retrieval by transforming raw text into machine-readable vector representations.
Haystack Blog9 min read
The Mechanics of Monocular Depth Estimation in Estimating Depth from 2D Images
In this article, we will delve into the mechanics of monocular depth estimation, exploring the neural network architectures used, the techniques for training and improving these models, and the practical applications of this exciting field.
Paperspace Blog12 min read
Introducing Keras 3 for R
We are thrilled to introduce {keras3}, the next version of the Keras R package. {keras3} is a ground-up rebuild of {keras}, maintaining the beloved features of the original while refining and simplifying the API based on valuable insights gathered over the past few years.
RStudio AI Blog8 min read
Croissant: a metadata format for ML-ready datasets
Machine learning (ML) practitioners looking to reuse existing datasets to train an ML model often spend a lot of time understanding the data, making sense of its organization, or figuring out what subset to use as features.
Google Research (Legacy)6 min readDiving Deep into the Mamba Model Implementation
The Mamba model, introduced in the paper Mamba: Linear-Time Sequence Modeling with Selective State Spaces by Albert Gu and Tri Dao, represents a significant advancement in sequence modeling.
oioi Blog6 min read
Hugging Face Integrations
Hugging Face rapidly became a very popular platform to build, share and collaborate on deep learning applications. We have worked on integrating the torch for R ecosystem with Hugging Face tools, allowing users to load and execute language models from their platform.
RStudio AI Blog4 min read
Understanding LoRA with a minimal example
LoRA (Low Rank Adaptation) is a new technique for fine-tuning deep learning models that works by reducing the number of trainable parameters and enables efficient task switching. In this blog post we will talk about the key ideas behind LoRA in a very minimal torch example.
RStudio AI Blog7 min read
GPT-2 from scratch with torch
Implementing a language model from scratch is, arguably, the best way to develop an accurate idea of how its engine works. Here, we use torch to code GPT-2, the immediate successor to the original GPT.
RStudio AI Blog15 min read
safetensors 0.1.0
Announcing safetensors, a new R package allowing for reading and writing files in the safetensors format.
RStudio AI Blog4 min read
torch 0.11.0
torch v0.11.0 is now on CRAN. This release features much-enhanced support for executing JIT operations. We also amended loading of model parameters, and added a few quality-of-life improvements, like support for temporarily modifying the default torch device, support for specifying data types as…
RStudio AI Blog4 min read
LLaMA in R with Keras and TensorFlow
Implementation and walk-through of LLaMA, a Large Language Model, in R, with TensorFlow and Keras.
RStudio AI Blog26 min read
Group-equivariant neural networks with escnn
Escnn, built on PyTorch, is a library that, in the spirit of Geometric Deep Learning, provides a high-level interface to designing and training group-equivariant neural networks. This post introduces important mathematical concepts, the library's key actors, and essential library use.
RStudio AI Blog16 min read
luz 0.4.0
luz v0.4.0 is now on CRAN. This release adds support for training models on ARM Mac GPUs, reduces the overhead of using luz, and makes it easier to checkpoint and resume failed runs.
RStudio AI Blog4 min read
torch 0.10.0
torch v0.10.0 is now on CRAN. This version upgraded the underlying LibTorch to 1.13.1, and added support for Automatic Mixed Precision. As an experimental feature, we now also support pre-built binaries, so you can install torch without having to deal with the CUDA installation.
RStudio AI Blog5 min read
Showing 180 of 194 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts