We mostly work on video #AI, but that doesn't mean we don't keep up with LLMs. Meta's release of #llama31 came with three size options: 8B, 70B, and 405B parameters. Beyond the sizes there's three other things you need to know: - It has multiple language support including Spanish, Thai, Hindi, and more (covered in the video) - The context window has been expanded from 8192 to 128000 - Llama 3.1 has been fine tuned for tool use
Tavus
Software Development
San Francisco, CA 7,300 followers
Build with generative video APIs
About us
Tavus is a generative AI video research company that enables developers to build digital twin video experiences through easy-to-use APIs.
- Website
-
http://www.tavus.io/developer
External link for Tavus
- Industry
- Software Development
- Company size
- 11-50 employees
- Headquarters
- San Francisco, CA
- Type
- Privately Held
- Founded
- 2020
Locations
Employees at Tavus
Updates
-
What makes video AI exceptional? An exceptional technique, an exceptional research team, and exceptional execution. Our new model, Phoenix-2, uses 3D Gaussian Splatting to make 3 dimensional scenes more realistic. Our #AI video generated replica explains more below. Want to get started today? Check out the link in the comments.
-
Tavus reposted this
Training time? Down Quality? Up Glasses/head bobs? More realistic How does Tavus' new Phoenix-2 model work? Four words: three dimensional Gaussian splatting (3DGS) What is 3DGS? It's a rasterization technique used to represent 3D scenes leveraging Gaussian splats - small localized normally distributed elements. Compared to NeRF, neural radiance fields, the previous SOTA method for digital replica generation, 3DGS has better data representation, less memory usages, and less computational complexity. Check out the new model via the comment link and let me know what you think!
-
Yesterday, Hassaan Raza was part of an amazing panel with Vaikkunth Mugunthan, Lulu Chang, Sriram Ramakrishnan, and Ankur P. on The Room Podcast. Huge shoutout to Madison McIlwain and Claudia Laurie for putting this together!
-
Tavus reposted this
Huge shout-out to OSS4AI for hosting Christian Safka and me at Github HQ! It was awesome meeting tons of people working on really cool tech. You can watch our talk here: https://lnkd.in/e9ZXw_FK
When was the last time you saw a talk that had so many questions for the speakers that the speakers were answering questions for almost an hour after their talk? For us, it was last night at the OSS4AI event. Ari Korin and Christian Safka revealed the research around video #AI that we've been doing at Tavus. They talked about: - 2D vs 3D models - Neural Radiance Fields vs Gaussian Splatting - Scaling this kind of ML tech Want to catch the whole talk? Check out the YouTube link below.
-
When was the last time you saw a talk that had so many questions for the speakers that the speakers were answering questions for almost an hour after their talk? For us, it was last night at the OSS4AI event. Ari Korin and Christian Safka revealed the research around video #AI that we've been doing at Tavus. They talked about: - 2D vs 3D models - Neural Radiance Fields vs Gaussian Splatting - Scaling this kind of ML tech Want to catch the whole talk? Check out the YouTube link below.
-
Tavus reposted this
This week on America's next top model … 14 pre-seed/seed stage startups pitched at OSS4AI's Awesome AI Dev Tools event for July. Not an easy task to follow up two amazing presentations from Ari Korin and Christian Safka about Video #AI at Tavus and Yi Ding about the complexities behind existing frameworks that he learned while at LlamaIndex. Big congrats to: Wordware (YC S24) Ana Robakidze Fai Sukontanit WeCP | We Create Problems Jake Anderson Simon Farshid Alexander Ng Jovy Yu Aiswarya Sankar Aibek Yegemberdin Dhiren Mathur Oksana Riabichko Sachin Dharashivkar Sahil Manocha Catch the YouTube video in the comments!
-
We're really excited for our dev team to talk about their favorite parts of building in #video #ai See you tonight!
17 people will be presenting at the OSS4AI July meetup tonight. Two full on presentations: - Video AI by Ari Korin and Christian Safka from Tavus - LLM Frameworks by Yi Ding formerly at LlamaIndex 15 2-minute demos by: Wordware (YC S24) Theneo Beluga WeCP | We Create Problems BRXai Assistant UI Valyu GitRoll mutable.ai Entelligence.AI Toolhouse Adapt Botprise, Inc momentum sh Element AI TrojanVectors See you there #SF #AI community - RSVP below.