Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

🧑‍🍳 Introducing the 𝑮𝑷𝑻 𝑩𝒂𝒌𝒆𝒓 A completely open-source implementation of OpenAI's custom GPTs on 🤗 Spaces. You own the weights, you own the code, so you can deploy your GPT on ANY platform at any time 🔥 Powered by the remarkably good Zephyr-β 7B 🪁

🍉 Abubakar Abid

14,659 subscribers

143,630 views • 2 years ago •via X (Twitter)

Science & Technology Education

Anya Rossi• Live Now

Private livecam show

10 Comments

Abubakar Abid2 years ago

Try it right now, or bookmark it for Thanksgiving break:

Diego Alejandro2 years ago

Well well well ❤️‍🩹

Abubakar Abid2 years ago

@ko_kay_o I don’t think math is Zephyr’s strong suit, but it’s easy to swap in another open source model which might be better at math

Michael Ten 🌨🎶🫐🍀2 years ago

How good are 7B models and how much video memory is needed for them?

Fabul.io2 years ago

@ClementDelangue Great

Diego Alejandro2 years ago

Now this I'm Hugging Chat and I'm good to Christmas 🎄🎁

kent2 years ago

Can it do web scraping?

Peter Dilworth2 years ago

make it good at math

Crystalwizard2 years ago

this is hysterical! the default request prompt is

Nathan Saunders2 years ago

@Scobleizer From Florida to AZ coin skin hat helped the hack life saver on a bike

Related Videos

build your own OpenAI Operator at home 🔥 use any VLM - open source or claude sonnet, deepseek-reasoner powered by smolagents! enjoy! 🤗

build your own OpenAI Operator at home 🔥 use any VLM - open source or claude sonnet, deepseek-reasoner powered by smolagents! enjoy! 🤗

Vaibhav (VB) Srivastav

67,625 views • 1 year ago

Introducing deep-research - my own open source implementation of OpenAI's new Deep Research agent. Get the same capability without paying $200. You can even tweak the behavior of the agent with adjustable breadth and depth. Run it for 5 min or 5 hours, it'll auto adjust.

Introducing deep-research - my own open source implementation of OpenAI's new Deep Research agent. Get the same capability without paying $200. You can even tweak the behavior of the agent with adjustable breadth and depth. Run it for 5 min or 5 hours, it'll auto adjust.

David

522,795 views • 1 year ago

1/ Introducing Glider - the smallest model to beat GPT-4o-mini on eval tasks ⚡🚀 - Open source, open weights, open code - Explainable evaluations by nature - Trained on 183 criteria and 685 domains Try it out for free at 🔥

1/ Introducing Glider - the smallest model to beat GPT-4o-mini on eval tasks ⚡🚀 - Open source, open weights, open code - Explainable evaluations by nature - Trained on 183 criteria and 685 domains Try it out for free at 🔥

PatronusAI

14,879 views • 1 year ago

How to build an agent that does what you want without writing any code. • This is open-source, so you can host it anywhere • Vendor-neutral, so you can use any model you want • You can set the entire agent loop without writing any code See the GitHub Repository below.

How to build an agent that does what you want without writing any code. • This is open-source, so you can host it anywhere • Vendor-neutral, so you can use any model you want • You can set the entire agent loop without writing any code See the GitHub Repository below.

Santiago

25,450 views • 2 months ago

Introducing llms.txt Generator ✨ You can now concatenate any website into a single text file that can be fed into any LLM. We crawl the whole website with and extract data with gpt-4o-mini. Create your own llms.txt at

Introducing llms.txt Generator ✨ You can now concatenate any website into a single text file that can be fed into any LLM. We crawl the whole website with and extract data with gpt-4o-mini. Create your own llms.txt at

Eric Ciarla (hiring)

230,151 views • 1 year ago

Introducing Querio The first analytics platform that puts your entire data stack in a git repo you own Querio makes your agents 100% consistent on your data Comment 'data teams' and i'll send you our open-source repo to move your BI tool to a git repo you own

Introducing Querio The first analytics platform that puts your entire data stack in a git repo you own Querio makes your agents 100% consistent on your data Comment 'data teams' and i'll send you our open-source repo to move your BI tool to a git repo you own

rami

311,127 views • 8 days ago

See it. Screenshot it. Ship it. 🌊 With NoahAI you can take a screenshot of any site and vibe code your own onchain version in minutes. Watch how easy it is: Raydium screenshot → “VibeSwap” DEX, powered by @RaydiumProtocol on the backend ⚡️

See it. Screenshot it. Ship it. 🌊 With NoahAI you can take a screenshot of any site and vibe code your own onchain version in minutes. Watch how easy it is: Raydium screenshot → “VibeSwap” DEX, powered by @RaydiumProtocol on the backend ⚡️

Noah Network

40,545 views • 1 year ago

Introducing web-agent, an open framework for building web agents 🔥 Build AI agents that search, scrape, and interact with the web - powered by the same architecture behind our /agent endpoint. 100% open source. Bring any model. Anthropic, OpenAI, or your own.

Introducing web-agent, an open framework for building web agents 🔥 Build AI agents that search, scrape, and interact with the web - powered by the same architecture behind our /agent endpoint. 100% open source. Bring any model. Anthropic, OpenAI, or your own.

Firecrawl

123,983 views • 6 months ago

Setting up your first Safe is easier than you think. By following a simple, memorable framework, the S.A.F.E. setup any user can deploy their own on-chain fortress in minutes. 👇👇👇

Setting up your first Safe is easier than you think. By following a simple, memorable framework, the S.A.F.E. setup any user can deploy their own on-chain fortress in minutes. 👇👇👇

Safe.eth

19,188 views • 1 year ago

You can now fine-tune Llama 3 without writing a single line of code! We are moving at breakneck speed. I recorded a video to show you how to fine-tune any open-source model in a few minutes. I'm using a GPT capable of taking a problem and turning it into a fine-tuned model that will solve it. You don't have to write any code. You only need to explain to a GPT what problem you want to solve and tell it you want to use Llama 3. For example, "fine-tune Llama 3" or "deploy zephyr." It feels magic. The system will recommend a dataset and fine-tune the model for you. I'm using Monster API, a platform that specializes in making fine-tuning and deploying open-source models easy and fast. Their stack is well-optimized to maximize fine-tuning efficiency using techniques like Q-Lora and vLLM. They are behind the GPT. Here is what you need to do: 1. Create an account at 2. Load the GPT with the link below This is as simple as it gets. When you are done, you can click a button to deploy the model and start using it. I have 10,000 free credits for anyone using the code "SANTIAGO" in the dashboard. You can use these credits to access, fine-tune, and deploy these open-source models. You can also keep up with their latest updates, and get free credits and special offers on their Discord server:

You can now fine-tune Llama 3 without writing a single line of code! We are moving at breakneck speed. I recorded a video to show you how to fine-tune any open-source model in a few minutes. I'm using a GPT capable of taking a problem and turning it into a fine-tuned model that will solve it. You don't have to write any code. You only need to explain to a GPT what problem you want to solve and tell it you want to use Llama 3. For example, "fine-tune Llama 3" or "deploy zephyr." It feels magic. The system will recommend a dataset and fine-tune the model for you. I'm using Monster API, a platform that specializes in making fine-tuning and deploying open-source models easy and fast. Their stack is well-optimized to maximize fine-tuning efficiency using techniques like Q-Lora and vLLM. They are behind the GPT. Here is what you need to do: 1. Create an account at 2. Load the GPT with the link below This is as simple as it gets. When you are done, you can click a button to deploy the model and start using it. I have 10,000 free credits for anyone using the code "SANTIAGO" in the dashboard. You can use these credits to access, fine-tune, and deploy these open-source models. You can also keep up with their latest updates, and get free credits and special offers on their Discord server:

Santiago

324,696 views • 2 years ago

Introducing the Mint 3D API You can now build your own Blender on the web!

Introducing the Mint 3D API You can now build your own Blender on the web!

tamrat

44,312 views • 3 months ago

Introducing Fireplexity - our open source Perplexity clone 🔥 Ask any question and get AI-powered answers with cited sources, all powered by our /search and /scrape endpoints. Fork the example and build your own AI answer engine today 👇

Introducing Fireplexity - our open source Perplexity clone 🔥 Ask any question and get AI-powered answers with cited sources, all powered by our /search and /scrape endpoints. Fork the example and build your own AI answer engine today 👇

Firecrawl

81,200 views • 1 year ago

I've created 2 GPTs that will get you all the right prompts to be able to do this 👇 If you want the tutorial and access to the custom GPTs so that you can make these results with 10 seconds of work, comment GPT, and I'll send over the tutorial and the GPTs. Follow so I can DM.

I've created 2 GPTs that will get you all the right prompts to be able to do this 👇 If you want the tutorial and access to the custom GPTs so that you can make these results with 10 seconds of work, comment GPT, and I'll send over the tutorial and the GPTs. Follow so I can DM.

Murray Frost

121,025 views • 1 year ago

Introducing PDF to Lesson! Create interactive personalized courses from any PDF. 100% free & open source! Powered by GPT OSS on Together AI.

Introducing PDF to Lesson! Create interactive personalized courses from any PDF. 100% free & open source! Powered by GPT OSS on Together AI.

Hassan

24,028 views • 5 months ago

Our new RAG CLI tool lets you RAG any file on your filesystem, using only on-device LLMs/embeddings! 💾🔎 Using LlamaIndex 🦙, Mistral-7B on ollama, and bge-m3, you have access to an LLM-powered grep that you can easily install, use, and customize. Can input any files including glob strings. LlamaPack: We also have the recipe for you to build your own RAG CLI from scratch. Check out this excellent guide by Sourabh Desai:

Our new RAG CLI tool lets you RAG any file on your filesystem, using only on-device LLMs/embeddings! 💾🔎 Using LlamaIndex 🦙, Mistral-7B on ollama, and bge-m3, you have access to an LLM-powered grep that you can easily install, use, and customize. Can input any files including glob strings. LlamaPack: We also have the recipe for you to build your own RAG CLI from scratch. Check out this excellent guide by Sourabh Desai:

LlamaIndex 🦙

40,124 views • 2 years ago

👀 Ever want a second set of eyes on your code? GitHub Copilot code review can help! Available in preview, Copilot code review offers fast, AI-powered feedback on your code as you write it. You can quickly apply any feedback that Copilot suggests, directly in the editor.

👀 Ever want a second set of eyes on your code? GitHub Copilot code review can help! Available in preview, Copilot code review offers fast, AI-powered feedback on your code as you write it. You can quickly apply any feedback that Copilot suggests, directly in the editor.

Visual Studio Code

75,224 views • 1 year ago

Enough with LLMs - exciting things are happening in the world of atoms. This is Stanford ALOHA, a low-cost and agile robot platform. The whole system is open-source (!!): hardware design, CAD models for 3D printing, simulator, and training code. Time to graft a physical arm onto GPTs 🦾 Led by my friend Tony Zhao at Stanford, and advised by Chelsea Finn Sergey Levine Vikash Kumar ✈️IROS2026. Project page: If you don't want to 3D print your own components, you can buy the setup at

Enough with LLMs - exciting things are happening in the world of atoms. This is Stanford ALOHA, a low-cost and agile robot platform. The whole system is open-source (!!): hardware design, CAD models for 3D printing, simulator, and training code. Time to graft a physical arm onto GPTs 🦾 Led by my friend Tony Zhao at Stanford, and advised by Chelsea Finn Sergey Levine Vikash Kumar ✈️IROS2026. Project page: If you don't want to 3D print your own components, you can buy the setup at

Jim Fan

819,054 views • 3 years ago

Social media can be a scam. The moment you become a traitor to the people who trusted and followed you, they can turn your own platform into your biggest source of stress. Just look at Bettina256. 😂

Social media can be a scam. The moment you become a traitor to the people who trusted and followed you, they can turn your own platform into your biggest source of stress. Just look at Bettina256. 😂

Goodhe4rted

61,638 views • 2 months ago

Introducing AstaBrief 8B, an open model that turns complex research questions + literature excerpts into cited reports. Run it locally on your own hardware, with open weights + training data you can inspect & build on. 🧵 🤗 Download:

Introducing AstaBrief 8B, an open model that turns complex research questions + literature excerpts into cited reports. Run it locally on your own hardware, with open weights + training data you can inspect & build on. 🧵 🤗 Download:

Ai2

32,667 views • 1 month ago