Загрузка видео...

Не удалось загрузить видео

На главную

Inference in Unsloth Studio is now ~20% faster. You can also use older pre-downloaded GGUFs from Hugging Face etc. AMD chat support for Linux now works. Data Recipes now works on macOS, AMD, CPU setups. GitHub: Changelog:

UnslothAI's profile picture

Unsloth AI

65,215 subscribers

25,355 просмотров • 4 месяцев назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Introducing Unsloth Desktop 🦥 The first desktop app to run and train models locally. • Open-source. Runs on Mac, Windows and Linux • Supports MLX, diffusion image/video, audio, GGUF • Connect Claude Code and Codex to local LLMs • 50% more accurate, self-healing tool calls + sandboxed code exec • Works for CPU + multiGPU setups - NVIDIA, AMD, Intel, Mac • Train models 2× faster with 70% less VRAM • Private web search, deep research, RAG, MCP and exports (NVFP4, GGUF) • Use Unsloth’s OpenAI-compatible API and cloud models • Securely deploy LLMs remotely and access anywhere Unsloth Desktop is now available on and GitHub. GitHub: Blog and Guide:
0:46

Introducing Unsloth Desktop 🦥 The first desktop app to run and train models locally. • Open-source. Runs on Mac, Windows and Linux • Supports MLX, diffusion image/video, audio, GGUF • Connect Claude Code and Codex to local LLMs • 50% more accurate, self-healing tool calls + sandboxed code exec • Works for CPU + multiGPU setups - NVIDIA, AMD, Intel, Mac • Train models 2× faster with 70% less VRAM • Private web search, deep research, RAG, MCP and exports (NVFP4, GGUF) • Use Unsloth’s OpenAI-compatible API and cloud models • Securely deploy LLMs remotely and access anywhere Unsloth Desktop is now available on and GitHub. GitHub: Blog and Guide:

Unsloth AI

748,915 просмотров • 4 дней назад

ACE-Step-UI Studio 1-Click Launcher Is it a Suno alternative? A Spotify alternative? A never-ending generative radio? One thing's for sure: it’s a whole new experience. Works on ALL OS: Windows/Mac/Linux (in fact it works FASTER on Macs!!) 1-click launch on pinokio, now!
0:37

ACE-Step-UI Studio 1-Click Launcher Is it a Suno alternative? A Spotify alternative? A never-ending generative radio? One thing's for sure: it’s a whole new experience. Works on ALL OS: Windows/Mac/Linux (in fact it works FASTER on Macs!!) 1-click launch on pinokio, now!

cocktail peanut

34,900 просмотров • 6 месяцев назад

👀 Now you see it 🪄 Now you don’t You can use the Clean Up tool in Photos to remove distracting items from the background of your photos. Here’s how it works in iOS 18.1, iPadOS 18.1, and macOS Sequoia 15.1.
0:43

👀 Now you see it 🪄 Now you don’t You can use the Clean Up tool in Photos to remove distracting items from the background of your photos. Here’s how it works in iOS 18.1, iPadOS 18.1, and macOS Sequoia 15.1.

Apple Support

56,403 просмотров • 1 год назад

BOOM! Huge update for AI app developers by Hugging Face you can now deploy models directly from Hugging Face with Gradio while choosing your preferred inference provider from SambaNova, Hyperbolic, Together AI, Fireworks, Replicate, fal, Nebius, Novita AI Additionally, you can choose to require Space users to log in, ensuring that inference usage is billed to their accounts
0:30

BOOM! Huge update for AI app developers by Hugging Face you can now deploy models directly from Hugging Face with Gradio while choosing your preferred inference provider from SambaNova, Hyperbolic, Together AI, Fireworks, Replicate, fal, Nebius, Novita AI Additionally, you can choose to require Space users to log in, ensuring that inference usage is billed to their accounts

AK

59,352 просмотров • 1 год назад

Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: Blog and Guide: Available now on Hugging Face, NVIDIA, Docker and Colab.
0:45

Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: Blog and Guide: Available now on Hugging Face, NVIDIA, Docker and Colab.

Unsloth AI

1,735,159 просмотров • 5 месяцев назад

You can now run Nebius AI Studio models directly in Visual Studio Code, just select Hugging Face as your Copilot provider and enter your HF key. ✅ Use models like Qwen, DeepSeek, Kimi, GLM ⚡ Powered by Nebius inference infrastructure Open models, instant APIs, zero setup.
0:27

You can now run Nebius AI Studio models directly in Visual Studio Code, just select Hugging Face as your Copilot provider and enter your HF key. ✅ Use models like Qwen, DeepSeek, Kimi, GLM ⚡ Powered by Nebius inference infrastructure Open models, instant APIs, zero setup.

Nebius Token Factory

12,233 просмотров • 10 месяцев назад

📣 now works with GitHub Copilot chat! You can also filter development prompts with a new toggle 🥳 A big P.S.: I collaborated with the GitHub Copilot team on this, and they added a prompt injection feature to Copilot Chat for — it was the best pair-programming experience I’ve ever had! 🥹
0:38

📣 now works with GitHub Copilot chat! You can also filter development prompts with a new toggle 🥳 A big P.S.: I collaborated with the GitHub Copilot team on this, and they added a prompt injection feature to Copilot Chat for — it was the best pair-programming experience I’ve ever had! 🥹

fatih kadir akın

63,640 просмотров • 1 год назад

GitHub Copilot Edits for JetBrains IDEs is generally available. ✅ You can now refactor, optimize, and iterate on your code faster—across one or multiple files—all from within Copilot Chat. Learn more about what this means for your workflow. ⬇️
0:43

GitHub Copilot Edits for JetBrains IDEs is generally available. ✅ You can now refactor, optimize, and iterate on your code faster—across one or multiple files—all from within Copilot Chat. Learn more about what this means for your workflow. ⬇️

GitHub

40,710 просмотров • 1 год назад

AI is changing everything, but how does it actually work? We break down machine learning, training, inference, and what happens behind the scenes when you use AI in the latest episode of #TheBringUp, featuring a hands-on model demo. 🎥 Watch now:
0:37

AI is changing everything, but how does it actually work? We break down machine learning, training, inference, and what happens behind the scenes when you use AI in the latest episode of #TheBringUp, featuring a hands-on model demo. 🎥 Watch now:

AMD

23,492 просмотров • 1 месяц назад

AMD's Anush Elangovan explains why he thinks his company's open source ethos combined with agentic AI superpowers their leverage as a company: Because AMD publishes a lot of technical details about its hardware, when engineers use AI tools, the models already “understand” AMD’s systems and can help write code for them, debug them, or even generate new tools. And that makes developers more productive on AMD hardware without AMD having to do all the work internally. "AMD has had this ethos of open source, which really plays to our advantage. Every frontier model that I use has already seen every bit of AMD source code." "It'll rewrite my spec for me because it's already in the training data. Which you can't get from closed ecosystems." "In fact I built a virtual GPU simulator just based off our public specs, and now I'm running it on the GPU. So now I can run cross-generational GPU simulations on existing hardware." "We have that advantage. And we've run a Dev Day contest where we generated more tokens on AMD — Triton kernels and HIP kernels — than existed on the internet at the time." "So now that's all part of the pre-training data. It's a superpower because now you're open source, and you're agentically accelerating this process."
1:22

AMD's Anush Elangovan explains why he thinks his company's open source ethos combined with agentic AI superpowers their leverage as a company: Because AMD publishes a lot of technical details about its hardware, when engineers use AI tools, the models already “understand” AMD’s systems and can help write code for them, debug them, or even generate new tools. And that makes developers more productive on AMD hardware without AMD having to do all the work internally. "AMD has had this ethos of open source, which really plays to our advantage. Every frontier model that I use has already seen every bit of AMD source code." "It'll rewrite my spec for me because it's already in the training data. Which you can't get from closed ecosystems." "In fact I built a virtual GPU simulator just based off our public specs, and now I'm running it on the GPU. So now I can run cross-generational GPU simulations on existing hardware." "We have that advantage. And we've run a Dev Day contest where we generated more tokens on AMD — Triton kernels and HIP kernels — than existed on the internet at the time." "So now that's all part of the pre-training data. It's a superpower because now you're open source, and you're agentically accelerating this process."

TBPN

34,469 просмотров • 3 месяцев назад

Pump Markets NFT secondary marketplace - NOW LIVE 📢 we aren't the ultimate pre-markets protocol for nothing 😉 now you can use your Pump Market NFTs to unlock liquidity on our secondary market 🔑 here's how it works 🎥🧵
0:56

Pump Markets NFT secondary marketplace - NOW LIVE 📢 we aren't the ultimate pre-markets protocol for nothing 😉 now you can use your Pump Market NFTs to unlock liquidity on our secondary market 🔑 here's how it works 🎥🧵

Pump!

20,085 просмотров • 2 лет назад

Biggest news from Google I/O - Gemma 3n is out 🔥 > True multimodal - Audio, Image, Video AND Text in > Can be used in 4B and 2B sizes > Supports 140 languages > Even works on CPU w/ LiteRT (on Hugging Face) > Optimised for on-device 😍 BONUS: Coming to other open source libraries near you soon ;)
0:57

Biggest news from Google I/O - Gemma 3n is out 🔥 > True multimodal - Audio, Image, Video AND Text in > Can be used in 4B and 2B sizes > Supports 140 languages > Even works on CPU w/ LiteRT (on Hugging Face) > Optimised for on-device 😍 BONUS: Coming to other open source libraries near you soon ;)

Vaibhav (VB) Srivastav

62,763 просмотров • 1 год назад

🤯🤯 You can now create a chatbot on ANY GitHub repo using the Llama 3.1 405B model with Hugging Face assistants -- FOR FREE! 💰 This is insane! 🚀 Link: clem 🤗 Julien Chaumond
1:22

🤯🤯 You can now create a chatbot on ANY GitHub repo using the Llama 3.1 405B model with Hugging Face assistants -- FOR FREE! 💰 This is insane! 🚀 Link: clem 🤗 Julien Chaumond

Satvik Paramkusham

162,863 просмотров • 2 лет назад

Grok-3 now has an Artifacts feature. xAI team is adding new features and improving Grok-3 significantly. Currently, it supports HTML, CSS, and JS, but I guess we may soon see support for other languages too. Note: You can also use DeepSearch to pull data from the internet on any topic and later use it for page creation, it works really well. I have tested it too.
0:34

Grok-3 now has an Artifacts feature. xAI team is adding new features and improving Grok-3 significantly. Currently, it supports HTML, CSS, and JS, but I guess we may soon see support for other languages too. Note: You can also use DeepSearch to pull data from the internet on any topic and later use it for page creation, it works really well. I have tested it too.

AshutoshShrivastava

153,968 просмотров • 1 год назад

OBS Studio 32.2 Beta is now available! Windows/macOS users can switch Update Channel in settings. GitHub: This update includes a brand new window for adding sources. Please test and give us feedback on our Discord before the full release!
0:33

OBS Studio 32.2 Beta is now available! Windows/macOS users can switch Update Channel in settings. GitHub: This update includes a brand new window for adding sources. Please test and give us feedback on our Discord before the full release!

OBS

159,486 просмотров • 1 месяц назад

The xDoctor web app is now mobile enabled, so it works from your phone. Use it to identify posts, reposts, lists, community notes, etc. that perform poorly in the algorithm so that you can learn from them, remove them and avoid them in the future.
2:00

The xDoctor web app is now mobile enabled, so it works from your phone. Use it to identify posts, reposts, lists, community notes, etc. that perform poorly in the algorithm so that you can learn from them, remove them and avoid them in the future.

Shane 𝕏

10,899 просмотров • 2 месяцев назад

$AMD will become a multi-trillion dollar company. The AI boom is no longer just about GPUs. In early AI data centers, the CPU-to-GPU ratio was around 1:8. Now it’s moving closer to 1:1 because agentic AI requires dramatically more CPU compute. Lisa Su: “Based on the demand signals we are seeing today and the structural increase in CPU compute requirements driven by agentic AI, we now expect the server CPU TAM to grow at greater than 35% annually, reaching over $120 billion by 2030.” Add to that the 6GW AI infrastructure deals with $META and OpenAI, plus deep collaboration on multiple future chip generations, and it becomes clear why $AMD is positioned to compound for years. I’m not chasing $AMD here after a +110% move in just over a month. But the long-term story remains intact.
1:34

$AMD will become a multi-trillion dollar company. The AI boom is no longer just about GPUs. In early AI data centers, the CPU-to-GPU ratio was around 1:8. Now it’s moving closer to 1:1 because agentic AI requires dramatically more CPU compute. Lisa Su: “Based on the demand signals we are seeing today and the structural increase in CPU compute requirements driven by agentic AI, we now expect the server CPU TAM to grow at greater than 35% annually, reaching over $120 billion by 2030.” Add to that the 6GW AI infrastructure deals with $META and OpenAI, plus deep collaboration on multiple future chip generations, and it becomes clear why $AMD is positioned to compound for years. I’m not chasing $AMD here after a +110% move in just over a month. But the long-term story remains intact.

Daniel

39,622 просмотров • 3 месяцев назад

iOS support for Tether's upcoming AI runtime works well now. Translations are fully local, fully private. Model's weights are downloaded from P2P network (Holepunch) the first time you use the app. Unstoppable, resilient. Write code once in JavaScript ( ) and run it everywhere, on any device. Marian, Llama and Whisper fully supported. Can't wait to open source it.
0:21

iOS support for Tether's upcoming AI runtime works well now. Translations are fully local, fully private. Model's weights are downloaded from P2P network (Holepunch) the first time you use the app. Unstoppable, resilient. Write code once in JavaScript ( ) and run it everywhere, on any device. Marian, Llama and Whisper fully supported. Can't wait to open source it.

Paolo Ardoino 🤖

74,039 просмотров • 1 год назад

"I don’t have a GPU" is no longer an excuse 🤯 You can now train LLMs directly in VS Code using a free Google Colab runtime. → Connect any fine-tuning notebook to Colab → Train locally or on a free cloud GPU → Works with Unsloth
0:38

"I don’t have a GPU" is no longer an excuse 🤯 You can now train LLMs directly in VS Code using a free Google Colab runtime. → Connect any fine-tuning notebook to Colab → Train locally or on a free cloud GPU → Works with Unsloth

Alvaro Cintas

86,284 просмотров • 5 месяцев назад