はてなブックマーク

Introducing research for the most advanced media foundation AI models. Our latest research breakthroughs demonstrate how you can use simple text inputs to produce custom videos and sounds, edit existing videos or transform your personal image into a unique video.

Llama 3.2: Revolutionizing edge AI and vision with open, customizable models Today, we’re releasing Llama 3.2, which includes small and medium-sized vision LLMs (11B and 90B), and lightweight, text-only models (1B and 3B) that fit onto edge and mobile devices, including pre-trained and instruction-tuned versions.The Llama 3.2 1B and 3B models support context length of 128K tokens and are state-of-

Generate an entire app from a prompt using Together AI’s LlamaCoder Together AI, the leading AI acceleration cloud, empowers developers and businesses to seamlessly design, develop, and manage their entire generative AI lifecycle on open source models like Llama. To inspire developers who build on Llama, Together AI built the LlamaCoder app—an open source web app that allows people to generate an

With 10x growth since 2023, Llama is the leading engine of AI innovation Llama models are approaching 350 million downloads to date (more than 10x the downloads compared to this time last year), and they were downloaded more than 20 million times in the last month alone, making Llama the leading open source model family.Llama usage by token volume across our major cloud service provider partners h

Introducing SAM 2: The next generation of Meta Segment Anything Model for videos and images Following up on the success of the Meta Segment Anything Model (SAM) for images, we’re releasing SAM 2, a unified model for real-time promptable object segmentation in images and videos that achieves state-of-the-art performance.In keeping with our approach to open science, we’re sharing the code and model

Meta is committed to openly accessible AI. Read Mark Zuckerberg’s letter detailing why open source is good for developers, good for Meta, and good for the world.Bringing open intelligence to all, our latest models expand context length to 128K, add support across eight languages, and include Llama 3.1 405B—the first frontier-level open source AI model.Llama 3.1 405B is in a class of its own, with

For more than a decade, Meta’s Fundamental AI Research (FAIR) team has focused on advancing the state of the art in AI through open research. As innovation in the field continues to move at a rapid pace, we believe that collaboration with the global AI community is more important than ever. Maintaining an open science approach and sharing our work with the community help us stay true to our goal o

Today, we’re introducing Meta Llama 3, the next generation of our state-of-the-art open source large language model.Llama 3 models will soon be available on AWS, Databricks, Google Cloud, Hugging Face, Kaggle, IBM WatsonX, Microsoft Azure, NVIDIA NIM, and Snowflake, and with support from hardware platforms offered by AMD, AWS, Dell, Intel, NVIDIA, and Qualcomm.We’re dedicated to developing Llama 3

Meta AI’s latest image generation technology takes your creative ideas and transforms them into reality. Use Meta AI as your creative partner to spark inspiration, animate your creations and realize your wildest artistic visions. And now you can see yourself in a whole new light with imagine yourself (Beta, US only). Meta AI is an intelligent assistant built on Llama 3.1, our most advanced model y

ログインしていませんこのページを閲覧するにはログインしてください。

Introducing SceneScript, a novel approach for 3D scene reconstruction Today, we’re introducing SceneScript, a novel method for reconstructing environments and representing the layout of physical spaces.SceneScript was trained in simulation using the Aria Synthetic Environments dataset, which is available for academic use. Imagine a pair of stylish, lightweight glasses that combined contextualized

Generative AI has brought about a new wave of innovation unlike we’ve ever seen before. With it, we have the ability to converse with conversational AIs, generate realistic imagery, and accurately summarize large corpora of documents, all from simple prompts. With over 100 million downloads of Llama models to date, a lot of this innovation is being fueled by open models. Collaboration on safety wi

At FAIR, we’re excited about driving continued exploratory research in generative AI, but we also want to make sure we do so in a manner that prioritizes safety and responsibility. Today, together with Inria, we are excited to share a research paper and code that details Stable Signature, an invisible watermarking technique we created to distinguish when an image is created by an open source gener

Today, we are releasing Code Llama, a large language model (LLM) that can use text prompts to generate code. Code Llama is state-of-the-art for publicly available LLMs on code tasks, and has the potential to make workflows faster and more efficient for current developers and lower the barrier to entry for people who are learning to code. Code Llama has the potential to be used as a productivity an

Today, we’re introducing SeamlessM4T, a foundational multilingual and multitask model that seamlessly translates and transcribes across speech and text. SeamlessM4T supports: Automatic speech recognition for nearly 100 languagesSpeech-to-text translation for nearly 100 input and output languagesSpeech-to-speech translation, supporting nearly 100 input languages and 35 (+ English) output languagesT

AudioCraft consists of three models: MusicGen, AudioGen, and EnCodec. MusicGen, which was trained with Meta-owned and specifically licensed music, generates music from text-based user inputs, while AudioGen, which was trained on public sound effects, generates audio from text-based user inputs. Today, we’re excited to release an improved version of our EnCodec decoder, which allows for higher qual

The open source AI model you can fine-tune, distill and deploy anywhere. Our latest models are available in 8B, 70B, and 405B variants.

CM3leon is the first multimodal model trained with a recipe adapted from text-only language models, including a large-scale retrieval-augmented pre-training stage and a second multitask supervised fine-tuning (SFT) stage. This recipe is simple, produces a strong model, and also shows that tokenizer-based transformers can be trained as efficiently as existing generative diffusion-based models. CM3l

Introducing 22 system cards that explain how AI powers experiences on Facebook and Instagram We use AI to help the billions of people who use our services every day discover content that they will hopefully find useful and interesting–whether it’s a new creator to follow on Instagram, or a post they may enjoy on Facebook. Our goal in having these systems is to make sure people see content that the

ログインしていませんこのページを閲覧するにはログインしてください。

ログインしていませんこのページを閲覧するにはログインしてください。

Introducing speech-to-text, text-to-speech, and more for 1,100+ languages Equipping machines with the ability to recognize and produce speech can make information accessible to many more people, including those who rely entirely on voice to access information. However, producing good-quality machine learning models for these tasks requires large amounts of labeled data — in this case, many thousan

HardwareMTIA v1: Meta’s first-generation AI inference acceleratorMay 18, 2023 · 8 min read AI workloads are ubiquitous at Meta — forming the basis for a wide range of use cases, including content understanding, Feeds, generative AI, and ads ranking. These workloads run on PyTorch with first-class Python integration, eager-mode development, and the simplicity of APIs. Deep learning recommendation m

When humans absorb information from the world, we innately use multiple senses, such as seeing a busy street and hearing the sounds of car engines. Today, we’re introducing an approach that brings machines one step closer to humans’ ability to learn simultaneously, holistically, and directly from many different forms of information — without the need for explicit supervision (the process of organi