abidlabs

Please add support for open-source LLMs from Hugging Face :)

Is the trained model available on Hugging Face?

A better example would have been the RWKV [1]

[1] https://github.com/BlinkDL/RWKV-LM

That's actually not true: https://github.com/BlinkDL/RWKV-LM

Just a matter of time, until plugins are supported!

> due to multimodality it may actually be more arcane to use.

Can you elaborate?

Follow up Guide that explains how to create your own tools: https://huggingface.co/docs/transformers/custom_tools

I wonder if the same will eventually hold true for "OpenAI"'s APIs vs. truly open-source AI

Cool to see that the entire website, from the agreement to generating the predictions, is one Gradio [1] app written in Python

[1] https://gradio.dev/

Pop2piano Gradio demo: https://huggingface.co/spaces/sweetcocoa/pop2piano

Neat use of Gradio & Modal

Here [1] is a video tutorial on building a web UI that accepts microphone input and runs it through Whisper for speech transcription

[1] https://www.youtube.com/watch?v=ywIyc8l1K1Q&ab_channel=1litt...

Hugging Face | http://hf.co/

-------------------

Senior Python Engineer | REMOTE

At Hugging Face, we have built some of the fastest growing, open source libraries for all stages of machine learning from finding datasets (𝚍𝚊𝚝𝚊𝚜𝚎𝚝𝚜) to model training/inference (𝚝𝚛𝚊𝚗𝚜𝚏𝚘𝚛𝚖𝚎𝚛𝚜), to building model demos (𝚐𝚛𝚊𝚍𝚒𝚘). Most of these libraries are written in Python and include some sort of full-stack or Web technologies, and we are looking for a senior Python engineer who is comfortable contributing to these libraries and influencing the direction of their development. We just raised our Series C and are growing rapidly

Apply here: https://apply.workable.com/huggingface/j/C53789F8D0/

-----

Pre-Sales Machine Learning Solutions Engineer | REMOTE

As an early member of Hugging’s Face Machine Learning Engineering Success team, you will play a critical role in driving successful technical engagements with prospects and customers and be an integral part of our overall enterprise sales process. You ask the right questions to quickly understand the customer's Machine Learning pain points and environment and articulate clearly and concisely the best possible technical solutions. You are curious and an avid learner. Most of all, you care about the customer being successful.

Apply here: https://apply.workable.com/huggingface/j/EEB606D7B5/

-----

Frontend Engineer | REMOTE

We design and code experiences that resonate with our growing customer base. We empower our community with user-friendly and well-thought tools to help them achieve their goals. To meet our users' needs we are looking for strong software engineers who are excited to build scalable and reliable platforms, partnering across disciplines and geographies, to achieve the best results. As part of our Product/Design team, you will be developing cutting edge front-ends for our platform and implementing new features with the best user experience possible. Working closely with other engineers, you’ll help in defining and enforcing guidelines to ensure that our users get the same experience across the whole platform. You’ll play a key role in setting the example: write high-quality code, as your teammates do!

Apply here: https://apply.workable.com/huggingface/j/09B44FE57C/

You can try out the model with this interactive Gradio demo: https://huggingface.co/spaces/nyx-ai/stylegan2-flax-tpu

Hugging Face | http://hf.co/

-------------------

Senior Python Engineer | Remote

At Hugging Face, we have built some of the fastest growing, open source libraries for all stages of machine learning from finding datasets (𝚍𝚊𝚝𝚊𝚜𝚎𝚝𝚜) to model training/inference (𝚝𝚛𝚊𝚗𝚜𝚏𝚘𝚛𝚖𝚎𝚛𝚜), to building model demos (𝚐𝚛𝚊𝚍𝚒𝚘). Most of these libraries are written in Python and include some sort of full-stack or Web technologies, and we are looking for a senior Python engineer who is comfortable contributing to these libraries and influencing the direction of their development. We just raised our Series C and are growing rapidly

Apply here: https://apply.workable.com/huggingface/j/C53789F8D0/

-----

Pre-Sales Machine Learning Solutions Engineer | Remote

As an early member of Hugging’s Face Machine Learning Engineering Success team, you will play a critical role in driving successful technical engagements with prospects and customers and be an integral part of our overall enterprise sales process. You ask the right questions to quickly understand the customer's Machine Learning pain points and environment and articulate clearly and concisely the best possible technical solutions. You are curious and an avid learner. Most of all, you care about the customer being successful.

Apply here: https://apply.workable.com/huggingface/j/EEB606D7B5/

-----

Frontend Engineer | Remote

We design and code experiences that resonate with our growing customer base. We empower our community with user-friendly and well-thought tools to help them achieve their goals. To meet our users' needs we are looking for strong software engineers who are excited to build scalable and reliable platforms, partnering across disciplines and geographies, to achieve the best results. As part of our Product/Design team, you will be developing cutting edge front-ends for our platform and implementing new features with the best user experience possible. Working closely with other engineers, you’ll help in defining and enforcing guidelines to ensure that our users get the same experience across the whole platform. You’ll play a key role in setting the example: write high-quality code, as your teammates do!

Apply here: https://apply.workable.com/huggingface/j/09B44FE57C/

You can, if that that specific DOM element is a Gradio component (e.g. a button, image, textbox, etc). Here's a very simple example: https://github.com/gradio-app/gradio/blob/main/demo/blocks_h...

We migrated from React to Svelte because of two reasons: (1) speed: Svelte does a lot of work during the compile-time, which led to much faster and more responsive web apps (2) developer learning curve: as we expanded our team, we found that front-end engineers found Svelte much more intuitive and faster to learn

An alternative, which doesn't require insane loading times, is to use any of the many great Python libraries that allow you to write web apps in Python, which get converted to JS web apps.

For example, I'm one of developers of Gradio [0], which lets you write your web app in Python, which gets rendered using Svelte-based components:

[0] https://www.gradio.dev

May also be of interest: https://github.com/huggingface/deep-rl-class

HuggingFace | http://hf.co/ | Senior Python Engineer | Remote

At Hugging Face, we have built some of the fastest growing, open source libraries for all stages of machine learning from finding datasets (𝚍𝚊𝚝𝚊𝚜𝚎𝚝𝚜) to model training/inference (𝚝𝚛𝚊𝚗𝚜𝚏𝚘𝚛𝚖𝚎𝚛𝚜), to building model demos (𝚐𝚛𝚊𝚍𝚒𝚘). Most of these libraries are written in Python and include some sort of full-stack or Web technologies, and we are looking for a senior Python engineer who is comfortable contributing to these libraries and influencing the direction of their development. We just raised our Series C and are growing rapidly

Apply here: https://apply.workable.com/huggingface/j/C53789F8D0/

-----

Pre-Sales Machine Learning Solutions Engineer | Remote

As an early member of Hugging’s Face Machine Learning Engineering Success team, you will play a critical role in driving successful technical engagements with prospects and customers and be an integral part of our overall enterprise sales process. You ask the right questions to quickly understand the customer's Machine Learning pain points and environment and articulate clearly and concisely the best possible technical solutions. You are curious and an avid learner. Most of all, you care about the customer being successful.

Apply here: https://apply.workable.com/huggingface/j/EEB606D7B5/

-----

Frontend Engineer | Remote

We design and code experiences that resonate with our growing customer base. We empower our community with user-friendly and well-thought tools to help them achieve their goals. To meet our users' needs we are looking for strong software engineers who are excited to build scalable and reliable platforms, partnering across disciplines and geographies, to achieve the best results. As part of our Product/Design team, you will be developing cutting edge front-ends for our platform and implementing new features with the best user experience possible. Working closely with other engineers, you’ll help in defining and enforcing guidelines to ensure that our users get the same experience across the whole platform. You’ll play a key role in setting the example: write high-quality code, as your teammates do!

Apply here: https://apply.workable.com/huggingface/j/09B44FE57C/

Streamlit and Gradio are both great tools to build web apps, but with different focuses: * Gradio is designed to build demos for machine learning models very easily, and as such is more opinionated but faster to use. * Streamlit takes longer to learn and use, but is more flexible and lets you build entire dashboards

There are other differences as well. For example, Gradio uses the default Python interpreter, whereas Streamlit uses its own. This means you can run Gradio apps in jupyter notebooks, etc. whereas I don't think you can do that with Streamlit

Asking for clarification so that we can improve it -- is it that the UI is not usable, or is that the model predicts things inaccurately? If it's the latter, it might say more about the model (a convolutional network with high accuracy on the MNIST dataset) than Gradio

If I (as a Gradio founder) can offer a different perspective: most apps on Hugging Face Spaces are not designed for production-level traffic. Instead, it might be a researcher who wants to share a demo of their model for reproducibility purposes, a student who's built a class project, or a hobbyist interested in building out a portfolio. For most of these projects, writing a simple gradio application and hosting on Spaces is the easiest way to share their machine learning model.

Particularly, one of the most useful feedback we heard early on was adding support for rendering the GUI in jupyter/colab notebooks. Extremely common use case (that also allowed us to distinguish ourselves from some competitors)

Very grateful to you and Pear for the all the lessons on talking to customers. Will remember for a long time!

What I like most about Copilot is seeing different programming styles suggested to me

For example, I didn't know about self.fail() in unittests and had never used it, but Copilot suggested it and it produced the most readable version of the unit test

You can run it right now with your own queries: see https://twitter.com/abidlabs/status/1450118978051903488

You can run it right now with your own queries: see https://twitter.com/abidlabs/status/1450118978051903488

Are there details on how it works? How is CLIP being used here?

(Original blogger here.) This isn't a research paper describing a novel contribution! Just a simple blog post with some observations I made with a Python library (Gradio) that I helped develop :)