Introducing MusicGen Web: AI-powered music generation directly in your browser, built with 🤗 Transformers.js! 🎵

Everything runs 100% locally, meaning no calls to an API! 🤯 Served as a static website... this costs $0 to host and run! 🔥

Try it out yourself! 👇

- 13B parameter BitNet + infini-Attention + DenseFormer + MoD + In Context-Pretraining + 2 stage pretraining
- upcycle w c-BTX to an 8 expert sparse MoE + MoA

I’m sure I’m missing about 20 other techniques to throw into a pretrained model/architecture 🤓

In all seriousness…

SWE-agent is our new system for autonomously solving issues in GitHub repos. It gets similar accuracy to Devin on SWE-bench, takes 93 seconds on avg + it's open source!

We designed a new agent-computer interface to make it easy for GPT-4 to edit+run code
github.com/princeton-nlp/…

If you're still struggling to understand how transformers work here are some amazing resources! (including mine! :))

First of all Grant Sanderson just released 2 videos covering in fair amount of depth word embeddings, transformers and its submodules like embedding mechanism,…

OSWorld

Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Autonomous agents that accomplish complex computer tasks with minimal human interventions have the potential to transform human-computer interaction, significantly enhancing

🎵The Stable Audio 2.0 user guide is here 🎵

Here’s some tips and tricks to get the most out of the 2.0 model. You can access the full guide here: stableaudio.com/user-guide (1/5)

Our players were able to walk, turn, kick and stand up faster than manually programmed skills on this type of robot. 🔁

They could also combine movements to score goals, anticipate ball movements and block opponent shots - thereby developing a basic understanding of a 1v1 game.

🎙️📹Audio & Video Structured Extraction with Gemini♊️

Google's Gemini 1.5 Pro officially came out of preview yesterday, with support for audio and video inputs, and they work with function calling!

We just released a new short YouTube video outlining how to perform structured…

Cohere Rerank 3 + Haystack 2.0

cohere just dropped new great models for reranking 👇
· Context length of 4k for significant improvement on longer documents
· Multilingual coverage of 100+ languages
· Improved latency

You can use it right away in Haystack to improve your…

1/ 🥁Scaling Laws for Data Filtering 🥁

TLDR: Data Curation *cannot* be compute agnostic!
In our #CVPR2024 paper, we develop the first scaling laws for heterogeneous & limited web data.

w/Sachin Goyal Zachary Lipton Aditi Raghunathan Zico Kolter
📝:arxiv.org/abs/2404.07177

🔥Exciting news -- GPT-4-Turbo has just reclaimed the No. 1 spot on the Arena leaderboard again! Woah!

We collect over 8K user votes from diverse domains and observe its strong coding & reasoning capability over others. Hats off to OpenAI for this incredible launch!

To offer…

Google presents Best Practices and Lessons Learned on Synthetic Data for Language Models

Provides an overview of synthetic data research, discussing its applications, challenges, and future directions

arxiv.org/abs/2404.07503

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

The first-of-its-kind scalable, real computer environment for multimodal agents, supporting task setup, execution-based evaluation, and interactive learning across various operating…

🚀 Introducing Mistral-22b-V.01 A breakthrough in AI! 🧠💡
- First-ever MOE to Dense model conversion🔥 #Mistral22bV01

This model is NOT an MOE
(It only has 22B params.)

huggingface.co/Vezora/Mistral…

Being able to interpret an #ML model’s hidden representations is key to understanding its behavior. Today we introduce Patchscopes, an approach that trains #LLMs to provide natural language explanations of their own hidden representations. Learn more → goo.gle/4aS5epd

Introducing: Zephyr 141B-A35B 🥁

🔥Mixtral-8x22B fine-tune
🤯 Using DORPO: new alignment algorithm (no SFT, open )
🚀 With 7k instances of (open) data

Very strong IFEval, BBH, AGIEval... Enjoy! 🤗

hf.co/HuggingFaceH4/…

1/n Griffin: DeepMind's Soaring Leap Beyond the Transformer Paradigm

Imagine having a conversation with an AI assistant that can engage with you for hours on end, seamlessly incorporating context from your entire dialogue history. Or envision AI models that can analyze books,…

Today we’re releasing OpenEQA — the Open-Vocabulary Embodied Question Answering Benchmark. It measures an AI agent’s understanding of physical environments by probing it with open vocabulary questions like “Where did I leave my badge?”

More details ➡️ go.fb.me/7vq6hm…

Transformers (LLMs) clearly explained with visuals:

Soccer players have to master a range of dynamic skills, from turning and kicking to chasing a ball. How could robots do the same? ⚽

We trained our AI agents to demonstrate a range of agile behaviors using reinforcement learning.

Here’s how. 🧵 dpmd.ai/3vUlgjC