Julien Chaumond's guest appearances

Julien Chaumond

Chai Time Data Science 

MLOps.community 

The MLOps Podcast

Emmanuel Ameisen

Goku Mohandas

Barr Moses

Jeremy Howard

Andrew Shaw

Richard Craib

Byron Allen

Ryan Dawson

Joel Grus

John Miller

Ian Ozsvald

Matthew Rocklin

Michael Kennedy

Maxime Beauchemin

Bryan Catanzaro

OwlTail

Hugging Face

Coffee Sessions #48 with Julien Chaumond, Tour of Upcoming Features on the Hugging Face Model Hub. //Abstract Julien Chaumond’s Tour of Upcoming Features on the Hugging Face Model Hub. Our MLOps community guest in this episode is Julien Chaumond the CTO of Hugging Face - every data scientist’s favorite NLP Swiss army knife. Julien, David, and Demetrios spoke about many topics including: Infra for hosting models/model hubs Inference widgets for companies with CPUs &amp; GPUs (for companies) Auto NLP which trains models “Infrastructure as a service”  // Bio Julien Chaumond is Chief Technical Officer at Hugging Face, a Brooklyn and Paris-based startup working on Machine learning and Natural Language Processing, and is passionate about democratizing state-of-the-art AI/ML for everyone.  --------------- ✌️Connect With Us ✌️ ------------- Join our slack community: https://go.mlops.community/slack Follow us on Twitter: @mlopscommunity Sign up for the next meetup: https://go.mlops.community/register  Connect with Demetrios on LinkedIn: https://www.linkedin.com/in/dpbrinkm/ Connect with David on LinkedIn: https://www.linkedin.com/in/aponteanalytics/ Connect with Julien on LinkedIn: https://www.linkedin.com/in/julienchaumond/  Timestamps:  [00:00] Introduction to Julien Chaumond  [01:57] Julien's background in tech  [04:35] "I have this vision of building a community where the greatest people in AI can come together and basically invent the future of Machine Learning together."  [04:55] What is Hugging Face?  [06:17] "We have the goal of bridging the gap between research and production on actual production use cases."  [06:45] Start of open-source in Hugging Face  [07:50] Chatbox experiment (reference resolution system) - linking pronouns to the subjects of sentences  [10:20] From a project to a company  [11:46] "The goal was to explore in the beginning."  [11:57] Importance of platform  [14:25] "Transfer learning is an efficient way of Machine Learning. Providing your platform  around change that people want to start from pre-trained model and fine-tune them into the specific use case is something that can be big so we built some stuff to help people do that."  [15:35] Narrowing down the scope of service to provide  [16:27] "We have some vision of what we want to build but a lot of it is the small incremental improvements that we bring to the platform. I think it's the natural way of building stuff nowadays because Machine Learning is moving so fast."  [20:00] Model Hubs  [22:37] "We're guaranteeing that we don't build anything that introduces any lagging to Hugging Face because we're using Github. You'll have that peace of mind."  [26:31] Storing model artifacts  [27:00] AWS - cache - stored to an edge location all around the globe  [28:39] Inference widgets powering  [27:17] "For each model on the model hub we try to ensure that we have the metadata about the model to be able to actually run it."  [32:11] Deploying infra function  [32:38] "Depending on the model and library, we optimize the custom containers to make sure that they run as fast as possible on the target hardware that we have."    [34:59] "Machine Learning is still pretty much hardware dependent."  [36:11] Hardware usage  [39:04] "CPU is super cheap. If you are able to run Berks served with a 1-millisecond on CPU because you have powerful optimizations, you don't really need GPUs anymore. It's cost-efficient and energy-efficient."   [40:30] Challenges of Hugging Face and what you learned  [41:10] "It may sound like a super cliche but the team that you assembled is everything."  [43:22] War stories in Hugging Face  [44:12] "Our goal is more forward-looking to be helpful as much as we can to the community."  [48:25] Hugging Face accessibility

Coffee Sessions #48 with Julien Chaumond, Tour of Upcoming Features on the Hugging Face Model Hub. //Abstract Julien Chaumond’s Tour of Upcoming Features on the Hugging Face Model Hub. Our MLOps community guest in this episode is Julien Chaumond the CTO of Hugging Face - every data scientist’s favorite NLP Swiss army knife. Julien, David, and Demetrios spoke about many topics including: Infra for hosting models/model hubs Inference widgets for companies with CPUs &amp; GPUs (for companies) Auto NLP which trains models “Infrastructure as a service” // Bio Julien Chaumond is Chief Technical Officer at Hugging Face, a Brooklyn and Paris-based startup working on Machine learning and Natural Language Processing, and is passionate about democratizing state-of-the-art AI/ML for everyone. --------------- ✌️Connect With Us ✌️ ------------- Join our slack community: https://go.mlops.community/slack Follow us on Twitter: @mlopscommunity Sign up for the next meetup: https://go.mlops.community/register Connect with Demetrios on LinkedIn: <a href="https://www.linkedin.com/in/dpbrinkm/" rel="nofollow" target="_blank">https://www.linkedin.com/in/dpbrinkm/</a> Connect with David on LinkedIn: <a href="https://www.linkedin.com/in/aponteanalytics/" rel="nofollow" target="_blank">https://www.linkedin.com/in/aponteanalytics/</a> Connect with Julien on LinkedIn: <a href="https://www.linkedin.com/in/julienchaumond/" rel="nofollow" target="_blank">https://www.linkedin.com/in/julienchaumond/</a> Timestamps: [00:00] Introduction to Julien Chaumond [01:57] Julien's background in tech [04:35] "I have this vision of building a community where the greatest people in AI can come together and basically invent the future of Machine Learning together." [04:55] What is Hugging Face? [06:17] "We have the goal of bridging the gap between research and production on actual production use cases." [06:45] Start of open-source in Hugging Face [07:50] Chatbox experiment (reference resolution system) - linking pronouns to the subjects of sentences [10:20] From a project to a company [11:46] "The goal was to explore in the beginning." [11:57] Importance of platform [14:25] "Transfer learning is an efficient way of Machine Learning. Providing your platform  around change that people want to start from pre-trained model and fine-tune them into the specific use case is something that can be big so we built some stuff to help people do that." [15:35] Narrowing down the scope of service to provide [16:27] "We have some vision of what we want to build but a lot of it is the small incremental improvements that we bring to the platform. I think it's the natural way of building stuff nowadays because Machine Learning is moving so fast." [20:00] Model Hubs [22:37] "We're guaranteeing that we don't build anything that introduces any lagging to Hugging Face because we're using Github. You'll have that peace of mind." [26:31] Storing model artifacts [27:00] AWS - cache - stored to an edge location all around the globe [28:39] Inference widgets powering [27:17] "For each model on the model hub we try to ensure that we have the metadata about the model to be able to actually run it." [32:11] Deploying infra function [32:38] "Depending on the model and library, we optimize the custom containers to make sure that they run as fast as possible on the target hardware that we have."    [34:59] "Machine Learning is still pretty much hardware dependent." [36:11] Hardware usage [39:04] "CPU is super cheap. If you are able to run Berks served with a 1-millisecond on CPU because you have powerful optimizations, you don't really need GPUs anymore. It's cost-efficient and energy-efficient."   [40:30] Challenges of Hugging Face and what you learned [41:10] "It may sound like a super cliche but the team that you assembled is everything." [43:22] War stories in Hugging Face [44:12] "Our goal is more forward-looking to be helpful as much as we can to the community." [48:25] Hugging Face accessibility

Tour of Upcoming Features on the Hugging Face Model Hub // Julien Chaumond // MLOps Coffee Sessions #48

Large Models

In this episode, I'm speaking with Julien Chaumond from 🤗 HuggingFace, about how they got started, getting large language models to production in millisecond inference times, and the CERN for machine learning. Join our Discord community: https://discord.gg/tEYvqxwhah --- Timestamps:   01:00 - Guest intro 02:14 - Origin of HuggingFace 05:37 - Why the focus on NLP? 07:45 - The success of the HuggingFace community 13:14 - Reproducing models and scaling for the community 18:14 - Enabling large models in production 23:14 - How HuggingFace scales so many models 27:34 - The biggest challenge HuggingFace solved in MLOps 32:02 - How HuggingFace transitions from research to production 34:44 - Using notebooks vs python modules 38:27 - The most interesting topic in ML production 40:10 - Fascinating ML research 45:24 - Learning new things 51:14 - Something that is true but most people disagree with 56:54 - Tips to organize research teams 1:00:05 - New features for accelerated inference 1:01:35 - Most common use case of HuggingFace 1:04:17 - Integrating search algorithms into transformer library 1:05:09 - Integrating vision models 1:06:06 - Long term business model 1:10:55 - Automation and simplification of the process of building models 1:13:02 - Support for real-time inference 1:14:40 - Recommendations for the audience  --- Relevant Links:  FastDS: https://github.com/DAGsHub/fds BigScience: https://bigscience.huggingface.co  https://www.linkedin.com/company/dagshub/ https://www.linkedin.com/company/huggingface/  https://twitter.com/TheRealDAGsHub https://twitter.com/huggingface 

In this episode, I'm speaking with Julien Chaumond from 🤗 HuggingFace, about how they got started, getting large language models to production in millisecond inference times, and the CERN for machine learning. Join our Discord community: <a href="https://discord.gg/tEYvqxwhah" rel="nofollow" target="_blank">https://discord.gg/tEYvqxwhah</a> --- Timestamps:  <ul> <li>01:00 - Guest intro</li> <li>02:14 - Origin of HuggingFace</li> <li>05:37 - Why the focus on NLP?</li> <li>07:45 - The success of the HuggingFace community</li> <li>13:14 - Reproducing models and scaling for the community</li> <li>18:14 - Enabling large models in production</li> <li>23:14 - How HuggingFace scales so many models</li> <li>27:34 - The biggest challenge HuggingFace solved in MLOps</li> <li>32:02 - How HuggingFace transitions from research to production</li> <li>34:44 - Using notebooks vs python modules</li> <li>38:27 - The most interesting topic in ML production</li> <li>40:10 - Fascinating ML research</li> <li>45:24 - Learning new things</li> <li>51:14 - Something that is true but most people disagree with</li> <li>56:54 - Tips to organize research teams</li> <li>1:00:05 - New features for accelerated inference</li> <li>1:01:35 - Most common use case of HuggingFace</li> <li>1:04:17 - Integrating search algorithms into transformer library</li> <li>1:05:09 - Integrating vision models</li> <li>1:06:06 - Long term business model</li> <li>1:10:55 - Automation and simplification of the process of building models</li> <li>1:13:02 - Support for real-time inference</li> <li>1:14:40 - Recommendations for the audience</li> </ul> --- Relevant Links: <ul> <li>FastDS: <a href="https://github.com/DAGsHub/fds" rel="nofollow" target="_blank">https://github.com/DAGsHub/fds</a></li> <li>BigScience: <a href="https://bigscience.huggingface.co" rel="nofollow" target="_blank">https://bigscience.huggingface.co</a> </li> <li><a href="https://www.linkedin.com/company/dagshub/" rel="nofollow" target="_blank">https://www.linkedin.com/company/dagshub/</a></li> <li><a href="https://www.linkedin.com/company/huggingface/" rel="nofollow" target="_blank">https://www.linkedin.com/company/huggingface/ </a></li> <li><a href="https://twitter.com/TheRealDAGsHub" rel="nofollow" target="_blank">https://twitter.com/TheRealDAGsHub</a></li> <li><a href="https://twitter.com/huggingface" rel="nofollow" target="_blank">https://twitter.com/huggingface</a></li> </ul>

🤗 Large ML models in production with HuggingFace CTO Julien Chaumond

Subscribe here to the newsletter: https://tinyletter.com/sanyambhutani  In this episode, Sanyam Bhutani interviews the CTO of Hugging Face, Julien Chaumond. In this interview, they talk all about his journey into the field and his path as a CTO of Hugging Face. They discuss all the amazing work being done at Hugging Face, research and open source as well as about their team.  Links:  https://transformer.huggingface.co/  Transformers Repo: https://github.com/huggingface/transformers  https://medium.com/huggingface/distilbert-8cf3380435b5  Follow: Julien Chaumond: https://twitter.com/julien_c  Hugging Face: https://twitter.com/huggingface https://huggingface.co/ https://medium.com/huggingface  Sanyam Bhutani: https://twitter.com/bhutanisanyam1 Blog: https://medium.com/@init_27  About: http://chaitimedatascience.com/ A show for Interviews with Practitioners, Kagglers &amp; Researchers and all things Data Science hosted by Sanyam Bhutani.   You can expect weekly episodes every available as Video, Podcast, and blogposts.  If you'd like to support the podcast: https://www.patreon.com/chaitimedatascience

Subscribe here to the newsletter: <a href="https://tinyletter.com/sanyambhutani" rel="nofollow" target="_blank">https://tinyletter.com/sanyambhutani</a> In this episode, Sanyam Bhutani interviews the CTO of Hugging Face, Julien Chaumond. In this interview, they talk all about his journey into the field and his path as a CTO of Hugging Face. They discuss all the amazing work being done at Hugging Face, research and open source as well as about their team. Links:  <a href="https://transformer.huggingface.co/" rel="nofollow" target="_blank">https://transformer.huggingface.co/</a> Transformers Repo: <a href="https://github.com/huggingface/transformers" rel="nofollow" target="_blank">https://github.com/huggingface/transformers</a> <a href="https://medium.com/huggingface/distilbert-8cf3380435b5" rel="nofollow" target="_blank">https://medium.com/huggingface/distilbert-8cf3380435b5</a> Follow: Julien Chaumond: <a href="https://twitter.com/julien_c" rel="nofollow" target="_blank">https://twitter.com/julien_c</a> Hugging Face: <a href="https://twitter.com/huggingface" rel="nofollow" target="_blank">https://twitter.com/huggingface</a> <a href="https://huggingface.co/" rel="nofollow" target="_blank">https://huggingface.co/</a> <a href="https://medium.com/huggingface" rel="nofollow" target="_blank">https://medium.com/huggingface</a> Sanyam Bhutani: <a href="https://twitter.com/bhutanisanyam1" rel="nofollow" target="_blank">https://twitter.com/bhutanisanyam1</a> Blog: <a href="https://medium.com/@init_27" rel="nofollow" target="_blank">https://medium.com/@init_27</a> About: <a href="http://chaitimedatascience.com/" rel="nofollow" target="_blank">http://chaitimedatascience.com/</a> A show for Interviews with Practitioners, Kagglers &amp; Researchers and all things Data Science hosted by Sanyam Bhutani.  You can expect weekly episodes every available as Video, Podcast, and blogposts. If you'd like to support the podcast: <a href="https://www.patreon.com/chaitimedatascience" rel="nofollow" target="_blank">https://www.patreon.com/chaitimedatascience</a>

Hugging Face, Transformers | NLP Research and Open Source | Interview with Julien Chaumond