Want even more updates on our latest research papers, datasets and more? Subscribe to the Meta AI newsletter to get a regular digest of AI news and updates. Subscribe
@aiatmeta
-
Llama 2-Chat Updates: Reducing False Refusals and Improving Sanitization
By
–
Hearing community feedback & following internal research & analysis, we've pushed two new updates to the Llama repo to reduce false refusal rates seen with Llama 2-Chat models & improve token sanitization. Full details https://
bit.ly/3QuRNER -
Open Catalyst Demo Accelerates Computational Chemistry by 1000x
By
–
Last week, we released the Open Catalyst demo. This work enables scientists to simulate the reactivity of catalyst materials ~1000x faster than existing computational methods — and at a scale of catalyst surface-adsorbate combinations impossible to explore without AI.
— AI at Meta (@AIatMeta) 4 août 2023
Demo ⬇️Last week, we released the Open Catalyst demo. This work enables scientists to simulate the reactivity of catalyst materials ~1000x faster than existing computational methods — and at a scale of catalyst surface-adsorbate combinations impossible to explore without AI. Demo
-
MusicGen Now Available on Hugging Face
By
–
We're pretty active on Hugging Face, you can already try MusicGen in this space. https://
huggingface.co/spaces/faceboo
k/MusicGen
… -
Llama 2: Responsible AI Development Guide for Developers
By
–
With Llama 2 we’re continuing to invest in responsible AI efforts, including a new guide to support devs with best practices and considerations for building products powered by large language models in a responsible manner. Download the full guide https://
bit.ly/3YjrNhC -
AudioCraft: Advancing Generative AI for Audio Creation
By
–
AudioCraft is an important step forward in generative AI research. We believe the simple approach we developed for audio generation will have a meaningful impact on future technologies and how we interact with them — we can’t wait to see what people create with it.
-
Meta Releases AudioCraft Open Source for Research Access
By
–
We're publicly releasing AudioCraft for research purposes and to further understanding of the technology. Responsible innovation can’t happen in isolation. Opening up our research and resulting models helps ensure that everyone has equal access. GitHub https://
bit.ly/3QjqOfl -
AudioCraft Release: Enhanced EnCodec and AudioGen Models
By
–
AudioCraft consists of three models: MusicGen, AudioGen & EnCodec. Today's release includes an improved version of EnCodec enabling higher quality music generation with fewer artifacts + pretrained AudioGen models for generating environmental sounds and effects.
-
AudioCraft: Meta’s Generative AI Models for Music and Audio
By
–
Today we're sharing details on AudioCraft, a new family of generative AI models built for generating high-quality, realistic audio & music from text. AudioCraft is a single code base that works for music, sound, compression & generation — all in the same place.
— AI at Meta (@AIatMeta) 2 août 2023
More details ⬇️Today we're sharing details on AudioCraft, a new family of generative AI models built for generating high-quality, realistic audio & music from text. AudioCraft is a single code base that works for music, sound, compression & generation — all in the same place. More details
-
CM3Leon: State-of-the-art text-to-image generation with less compute
By
–
CM3leon is a first-of-its-kind multimodal model that achieves state-of-the-art performance for text-to-image generation despite being trained with five times less compute than previous transformer-based methods. More details and examples https://
bit.ly/44I6t7E