Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Introducing: HuggingChat Omni 💫 Select the best model for every prompt automatically 🚀 - Automatic model selection for your queries - 115 models available across 15 providers Available now all Hugging Face users. 100% open source.

Victor M

30,352 subscribers

72,451 Aufrufe • vor 11 Monaten •via X (Twitter)

Wissenschaft & Technologie Nachrichten & Politik

Anya Rossi• Live Now

Private livecam show

39 Kommentare

Profilbild von Victor M

Victor Mvor 11 Monaten

Powered by Hugging Face Inference Providers: access hundreds of AI models using only world-class inference providers.

Profilbild von Victor M

Victor Mvor 11 Monaten

Omni uses a policy-based approach to model selection (after experimenting with different methods). Credits to Katanemo for their small routing model: katanemo/Arch-Router-1.5B

Profilbild von Victor M

Victor Mvor 11 Monaten

Coming next: - MCP support with web search - File support - Omni router improvements - Customisable policies (maybe)

Profilbild von Christopher

Christophervor 11 Monaten

This is the correct repo? It looks like it from the readme but the included chat url is still 404?

Profilbild von Victor M

Victor Mvor 11 Monaten

should always work now

Profilbild von Christopher

Christophervor 11 Monaten

It’s active thank you. 👍 I jumped on way to quick because I saw you were using the router @salman_paracha created. All hail SLMs and the teams building and fine tuning them. 😀

Profilbild von Caleb

Calebvor 11 Monaten

letsss gooo!

Profilbild von Arindam Majumder 𝕏

Arindam Majumder 𝕏vor 11 Monaten

I just tried it here's my First Impression:

Profilbild von Luc Georges

Luc Georgesvor 11 Monaten

LET'S GOOOOO

Profilbild von Anai_

Anai_vor 11 Monaten

That’s great.

Profilbild von KarthiDreamr

KarthiDreamrvor 11 Monaten

@ClementDelangue is this reincarnation of Closed Hugging Chat ?

Profilbild von Benny (Yufei) Chen

Benny (Yufei) Chenvor 11 Monaten

Nice work! Here is me trying GPT-OSS from @OpenAI served on @FireworksAI_HQ on HuggingChat!

Profilbild von Natz Trader

Natz Tradervor 11 Monaten

Is it for free @grok ?

Profilbild von Saïd Aitmbarek

Saïd Aitmbarekvor 11 Monaten

based for auto model-selection love the fact you made it oss guys :) let's launch/spotlight you on when it helps btw

Profilbild von Aaliya

Aaliyavor 11 Monaten

That’s awesome! Automatic model selection sounds super handy.

Profilbild von Túlio Sousa ✪

Túlio Sousa ✪vor 11 Monaten

Can you tell me which app did you use to record the screen?

Profilbild von Victor M

Victor Mvor 11 Monaten

screenstudio

Profilbild von Túlio Sousa ✪

Túlio Sousa ✪vor 11 Monaten

Thank you, bro!!!

Profilbild von Krish Dasgupta

Krish Dasguptavor 11 Monaten

@_akhaliq Brilliant !!!!!!!?!

Profilbild von Chris McMaster

Chris McMastervor 11 Monaten

Looks great. Do you accept community feedback on the routing?

Profilbild von Robert Piosik CWC

Robert Piosik CWCvor 11 Monaten

Alright, so I have to add support for this chatbot to Code Web Chat!

Profilbild von Igor

Igorvor 11 Monaten

nice!

Profilbild von Ai Machete

Ai Machetevor 11 Monaten

@_akhaliq Massive! 🔥

Profilbild von Daniel Vila Suero

Daniel Vila Suerovor 11 Monaten

Yessss

Profilbild von Abdulmuiz Adeyemo

Abdulmuiz Adeyemovor 11 Monaten

Incredible

Profilbild von Matt Rice

Matt Ricevor 11 Monaten

Super cool release 😎

Profilbild von Suhrab Khan⚡️

Suhrab Khan⚡️vor 11 Monaten

HuggingChat Omni is a game-changer! Automatic model selection across 115 models makes it effortless to pick the best tool for any prompt.

Profilbild von Reuben Fernandes ルーベン

Reuben Fernandes ルーベンvor 11 Monaten

man wish i could work on improving it i had planned to improve the previous one but then they shut it down

Profilbild von Victor M

Victor Mvor 11 Monaten

Looks quite cool!

Profilbild von célina

célinavor 11 Monaten

Neat! 🔥

Profilbild von Aakash

Aakashvor 11 Monaten

T3chat stocks 📉

Profilbild von Dan Brown

Dan Brownvor 11 Monaten

Cool

Profilbild von Arindam Majumder 𝕏

Arindam Majumder 𝕏vor 11 Monaten

Oh Wow! Let me try this out!

Profilbild von thoddnn

thoddnnvor 11 Monaten

@mervenoyann This is really cool !

Profilbild von Krish Dasgupta

Krish Dasguptavor 11 Monaten

@_akhaliq This is so amazing !!!!! Victor - I had built an automatic model router concept which I presented at the Linux Foundation . Do check this out too. 😇🙏🏽

Profilbild von @ChuckBaggett Chuck Baggett Peace Freedom Ad Astra

@ChuckBaggett Chuck Baggett Peace Freedom Ad Astravor 11 Monaten

I asked Omni if it can do web searches to make answers more complete and up to date, and give links, and it said it can't do web searches or give links. I asked it about writing an app using TTS and STT, and it gave obsolete info on Google voices, wasting my time in reading.

Profilbild von VibeEdge

VibeEdgevor 11 Monaten

Impressive work on HuggingChat Omni! The automatic model routing is a game-changer for seamless, task specific AI responses. Excited to see how web search and customizable policies enhance it further!

Profilbild von John Townsend

John Townsendvor 11 Monaten

I havent tried in a while, but I couldn't get hugging face to work in the past. Is it easier now? Can I just click the URL and begin interacting with it like ChatGPT, Gemini, etc?

Profilbild von Abdulmuiz Adeyemo

Abdulmuiz Adeyemovor 11 Monaten

Wow this is great

Ähnliche Videos

MagenticLite's models are now fully open source. MagenticBrain and Fara 1.5, previously available on Microsoft Foundry, are live on Hugging Face with open weights. The app, the harness, and every model in the stack are now open.

MagenticLite's models are now fully open source. MagenticBrain and Fara 1.5, previously available on Microsoft Foundry, are live on Hugging Face with open weights. The app, the harness, and every model in the stack are now open.

Microsoft Research

19,429 Aufrufe • vor 2 Monaten

Introducing Pirate Face The first verifiable torrent index for AI - every Hugging Face open model, provably identical to the original and kept alive forever by the swarm. The permanence layer for AI. How it works 👇

Introducing Pirate Face The first verifiable torrent index for AI - every Hugging Face open model, provably identical to the original and kept alive forever by the swarm. The permanence layer for AI. How it works 👇

Pirate Face

13,134 Aufrufe • vor 2 Monaten

Stop explaining your creative workflow over and over again Introducing Custom Templates Turn your prompts, characters, models and references into shareable links. Work across Images, Videos, and Audio Now available for all Freepik users

Stop explaining your creative workflow over and over again Introducing Custom Templates Turn your prompts, characters, models and references into shareable links. Work across Images, Videos, and Audio Now available for all Freepik users

Magnific

124,297 Aufrufe • vor 8 Monaten

Exciting update for AI developers! The Hugging Face Hub is now more natively integrated into Google Cloud Vertex AI Model Garden. Search through thousands of open Generative AI models from Hugging Face models & deploy them with one click to Vertex AI or GKE. 🤯 What's new: 🔎 Browse and search thousands of Hugging Face models directly within the Vertex AI Model Garden and filter based on what is currently trending in the community. 🚀 Accelerate your AI projects by leveraging readily available one-click deploy your model to Vertex AI or Google Kubernetes Engine (GKE). ⭐️ Featuring popular open models from BlackForestLabsAI - Unofficial FLUX.1, AI at Meta Llama 3.1, Mistral AI, Google DeepMind Gemma, and countless others. Get Started:

Exciting update for AI developers! The Hugging Face Hub is now more natively integrated into Google Cloud Vertex AI Model Garden. Search through thousands of open Generative AI models from Hugging Face models & deploy them with one click to Vertex AI or GKE. 🤯 What's new: 🔎 Browse and search thousands of Hugging Face models directly within the Vertex AI Model Garden and filter based on what is currently trending in the community. 🚀 Accelerate your AI projects by leveraging readily available one-click deploy your model to Vertex AI or Google Kubernetes Engine (GKE). ⭐️ Featuring popular open models from BlackForestLabsAI - Unofficial FLUX.1, AI at Meta Llama 3.1, Mistral AI, Google DeepMind Gemma, and countless others. Get Started:

Philipp Schmid

34,757 Aufrufe • vor 2 Jahren

Flux.2 Max is out NOW 💥 UNLIMITED for 1 month for Premium+ and Pro users The highest-quality and most consistent FLUX.2 model Built for maximum prompt adherence, multi-reference consistency, and production-ready editing at blazing speed Available for all users

Flux.2 Max is out NOW 💥 UNLIMITED for 1 month for Premium+ and Pro users The highest-quality and most consistent FLUX.2 model Built for maximum prompt adherence, multi-reference consistency, and production-ready editing at blazing speed Available for all users

Magnific

24,333 Aufrufe • vor 9 Monaten

offers full-stack privacy across queries, data, payments and devices / hardware 1. The best open-source models (eg. Kimi K2.5) served in secure enclaves (TEEs) 2. The best closed-source models (eg. GPT-5.2 Pro) with queries pooled into proxy servers and PII anonymized with a specialized Silo model 3. The only available implementation of private Deep Research for secure reasoning 4. Fully private crypto payments via Zcash or discounted payments with FAI 5. A hardware offering to run everything on-prem from your own home with 288 GB GPU RAM (Silo Box) All with encrypted sync between devices so users can uniformly + privately access their AI sessions

offers full-stack privacy across queries, data, payments and devices / hardware 1. The best open-source models (eg. Kimi K2.5) served in secure enclaves (TEEs) 2. The best closed-source models (eg. GPT-5.2 Pro) with queries pooled into proxy servers and PII anonymized with a specialized Silo model 3. The only available implementation of private Deep Research for secure reasoning 4. Fully private crypto payments via Zcash or discounted payments with FAI 5. A hardware offering to run everything on-prem from your own home with 288 GB GPU RAM (Silo Box) All with encrypted sync between devices so users can uniformly + privately access their AI sessions

Freysa

16,930 Aufrufe • vor 6 Monaten

Introducing Arena Mode in Windsurf: One prompt. Two models. Your vote. Benchmarks don't reflect real-world coding quality. The best model for you depends on your codebase and stack. So we made real-world coding the benchmark. Free for the next week. May the best model win.

Introducing Arena Mode in Windsurf: One prompt. Two models. Your vote. Benchmarks don't reflect real-world coding quality. The best model for you depends on your codebase and stack. So we made real-world coding the benchmark. Free for the next week. May the best model win.

Devin Desktop

1,070,695 Aufrufe • vor 7 Monaten

Introducing Alpamayo 2 Super: the frontier open reasoning VLA for autonomous vehicles and robotaxis. 34B parameters. Full-surround awareness. Available for commercial use under under OpenMDW-1.1. Download now on Hugging Face →

Introducing Alpamayo 2 Super: the frontier open reasoning VLA for autonomous vehicles and robotaxis. 34B parameters. Full-surround awareness. Available for commercial use under under OpenMDW-1.1. Download now on Hugging Face →

NVIDIA DRIVE

17,214 Aufrufe • vor 1 Monat

Introducing Magnific Precision, now on the Freepik AI Suite Upscale your images while keeping the original intact. The lastest state of the art model by Magnific.ai Available for all plans

Introducing Magnific Precision, now on the Freepik AI Suite Upscale your images while keeping the original intact. The lastest state of the art model by Magnific.ai Available for all plans

Magnific

51,831 Aufrufe • vor 1 Jahr

Announcing the Open Model Series: a new series on open source AI models, with merve of Hugging Face. Hugging Face is the open model hub: it hosts model weights, datasets, evals, & demo apps, and maintains the open-source libraries (like transformers) used to run and train them. I think of it like GitHub, but for AI models. You can download open models and run them on your own machines. In this series we'll cover what open source and open weight models are, how they work, how to run them yourself, and why they're important. By the way - this video is edited entirely with Claude! I can make a tutorial on how I did it. If there's a question you want answered about open models, leave it in the comments. We will read them all. Episode 1 is out soon.

Announcing the Open Model Series: a new series on open source AI models, with merve of Hugging Face. Hugging Face is the open model hub: it hosts model weights, datasets, evals, & demo apps, and maintains the open-source libraries (like transformers) used to run and train them. I think of it like GitHub, but for AI models. You can download open models and run them on your own machines. In this series we'll cover what open source and open weight models are, how they work, how to run them yourself, and why they're important. By the way - this video is edited entirely with Claude! I can make a tutorial on how I did it. If there's a question you want answered about open models, leave it in the comments. We will read them all. Episode 1 is out soon.

Harper Carroll

30,392 Aufrufe • vor 1 Monat

Introducing Wan 2.2 A video model designed for precise control over every shot, lighting, color, camera and composition Available now in the Freepik AI Suite

Introducing Wan 2.2 A video model designed for precise control over every shot, lighting, color, camera and composition Available now in the Freepik AI Suite

Magnific

15,238 Aufrufe • vor 1 Jahr

Introducing: Auto Private Model Routing on June Choose Low, Balanced, or High. June picks the right model for every request. Defaults to zero data retention and private models. Powered by Venice. Free to try. Open source. MIT. Try June:

Introducing: Auto Private Model Routing on June Choose Low, Balanced, or High. June picks the right model for every request. Defaults to zero data retention and private models. Powered by Venice. Free to try. Open source. MIT. Try June:

OpenSoftware

112,941 Aufrufe • vor 2 Monaten

DeepSite V2 just dropped (insane for Vibe Coding) 🤯 🔹Amazingly good at UI Design 🔹DeepSeek-R1 model now available 🔹Targeted Edits on any element 🔹Redesign any existing website 🔹100% open source (UI + models)

DeepSite V2 just dropped (insane for Vibe Coding) 🤯 🔹Amazingly good at UI Design 🔹DeepSeek-R1 model now available 🔹Targeted Edits on any element 🔹Redesign any existing website 🔹100% open source (UI + models)

Victor M

105,886 Aufrufe • vor 1 Jahr

Introducing ZEPHY — every AI model. One window. Zero terminal. What you can do without ever leaving a single window: → Chat with cloud OR local/offline models, with smart routing that automatically picks the best one → Pull any model straight from Hugging Face uncensored too, auto-fit to your GPU → Write & run code in the built-in code editor → Chain steps into workflows on the node canvas → Generate media → Manage assets with an integrated crypto wallet Open source · Windows / macOS / Linux · no keys, no card. Site live -

Introducing ZEPHY — every AI model. One window. Zero terminal. What you can do without ever leaving a single window: → Chat with cloud OR local/offline models, with smart routing that automatically picks the best one → Pull any model straight from Hugging Face uncensored too, auto-fit to your GPU → Write & run code in the built-in code editor → Chain steps into workflows on the node canvas → Generate media → Manage assets with an integrated crypto wallet Open source · Windows / macOS / Linux · no keys, no card. Site live -

Pemersatu bangsa

20,391 Aufrufe • vor 3 Monaten

Introducing Figure out which open model is best for your use case. Compare models across coding, agents, long context, vision, finance, and more. Then see how they compare on cost + quality, including what you could save by moving to open models.

Introducing Figure out which open model is best for your use case. Compare models across coding, agents, long context, vision, finance, and more. Then see how they compare on cost + quality, including what you could save by moving to open models.

Hassan

17,354 Aufrufe • vor 2 Tagen

Claude 3 is now available for Pro users, replacing Claude 2.1 as the default model and for rewriting existing answers. You'll get 5 daily queries using Claude 3 Opus, the most capable and largest model surpassing GPT-4. Remaining daily queries will run on the faster Claude 3 Sonnet, which is competitive with GPT-4. Enjoy this upgraded experience!

Claude 3 is now available for Pro users, replacing Claude 2.1 as the default model and for rewriting existing answers. You'll get 5 daily queries using Claude 3 Opus, the most capable and largest model surpassing GPT-4. Remaining daily queries will run on the faster Claude 3 Sonnet, which is competitive with GPT-4. Enjoy this upgraded experience!

Perplexity

115,380 Aufrufe • vor 2 Jahren

Segment Anything Model 2 (SAM 2) is a foundation model from Meta FAIR for promptable visual segmentation in images & videos. Available now for anyone to build on for free, open source under an Apache license. Try the demo ➡️

Segment Anything Model 2 (SAM 2) is a foundation model from Meta FAIR for promptable visual segmentation in images & videos. Available now for anyone to build on for free, open source under an Apache license. Try the demo ➡️

AI at Meta

97,811 Aufrufe • vor 2 Jahren

We believe an open approach is the right one for the development of today's Al models. Today, we’re releasing Llama 2, the next generation of Meta’s open source Large Language Model, available for free for research & commercial use. Details ➡️

We believe an open approach is the right one for the development of today's Al models. Today, we’re releasing Llama 2, the next generation of Meta’s open source Large Language Model, available for free for research & commercial use. Details ➡️

AI at Meta

1,235,329 Aufrufe • vor 3 Jahren

Studio Mode and Nano Banana Pro are now available to all users! Nano Banana Pro looks best in Studio Mode and lets you create the most cinematic visuals with sharp text rendering and better theme matching for your gammas. Nano Banana Pro HD (4k model) is also available to Gamma Ultra users.

Studio Mode and Nano Banana Pro are now available to all users! Nano Banana Pro looks best in Studio Mode and lets you create the most cinematic visuals with sharp text rendering and better theme matching for your gammas. Nano Banana Pro HD (4k model) is also available to Gamma Ultra users.

Gamma

37,316 Aufrufe • vor 9 Monaten