Hugging Face (Twitter)
RT @reach_vb: Want to run the latest @OpenAI gpt-oss models with Continuous Batching, Tensor Parallelism, Flash Attention 3 and more?
Checkout our detailed Inference and Fine-tuning recipes 🤗
RT @reach_vb: Want to run the latest @OpenAI gpt-oss models with Continuous Batching, Tensor Parallelism, Flash Attention 3 and more?
Checkout our detailed Inference and Fine-tuning recipes 🤗
Hugging Face (Twitter)
RT @ClementDelangue: Lots of conflicting takes about gpt-oss (yay open-source in the spotlight)!
We’re powering the official @openai demo gpt-oss.com with HF inference providers thanks to @FireworksAI_HQ, @CerebrasSystems, @GroqInc and @togethercompute so we have a front-row seat of what’s happening.
Something to remember: inference for new frontier open models isn’t easy, especially with a new format like harmony and the volume of interest that gpt-oss is getting out of the gate.
Early spikes can temporarily affect quality, accuracy, and overall "vibes," particularly just 24 hours post-release when providers are racing against the clock with barely any sleep!
Some advice to avoid forming the wrong opinions:
- If you care about getting vibes as fast as possible, use a hosted setup that gives you a diversity of providers like HF inference providers (https://huggingface.co/docs/inference-providers/guides/gpt-oss) and follow official standard...
Перейти на оригинальный пост
RT @ClementDelangue: Lots of conflicting takes about gpt-oss (yay open-source in the spotlight)!
We’re powering the official @openai demo gpt-oss.com with HF inference providers thanks to @FireworksAI_HQ, @CerebrasSystems, @GroqInc and @togethercompute so we have a front-row seat of what’s happening.
Something to remember: inference for new frontier open models isn’t easy, especially with a new format like harmony and the volume of interest that gpt-oss is getting out of the gate.
Early spikes can temporarily affect quality, accuracy, and overall "vibes," particularly just 24 hours post-release when providers are racing against the clock with barely any sleep!
Some advice to avoid forming the wrong opinions:
- If you care about getting vibes as fast as possible, use a hosted setup that gives you a diversity of providers like HF inference providers (https://huggingface.co/docs/inference-providers/guides/gpt-oss) and follow official standard...
Перейти на оригинальный пост
This media is not supported in your browser
VIEW IN TELEGRAM
Hugging Face (Twitter)
RT @dylan_ebert_: @dylan_ebert_: Hugging Face Explained in 45 seconds https://twitter.com/hamiltonsucks76/status/1952813334102983029#m
RT @dylan_ebert_: @dylan_ebert_: Hugging Face Explained in 45 seconds https://twitter.com/hamiltonsucks76/status/1952813334102983029#m
Hugging Face (Twitter)
RT @elonmusk: @BasedBeffJezos: It’s high time we open sourced Grok 2. Will make it happen next week.
We’ve just been fighting fires and burning the 4am oil nonstop for a while now.
RT @elonmusk: @BasedBeffJezos: It’s high time we open sourced Grok 2. Will make it happen next week.
We’ve just been fighting fires and burning the 4am oil nonstop for a while now.
Hugging Face (Twitter)
RT @romainhuet: Great perspective and tips from @ClementDelangue on the early days of gpt-oss.
Building strong foundations take time, and we’re excited to be working with inference providers and @huggingface to help these models perform at their best. Please keep your feedback coming! https://twitter.com/ClementDelangue/status/1953119901649891367#m
RT @romainhuet: Great perspective and tips from @ClementDelangue on the early days of gpt-oss.
Building strong foundations take time, and we’re excited to be working with inference providers and @huggingface to help these models perform at their best. Please keep your feedback coming! https://twitter.com/ClementDelangue/status/1953119901649891367#m
Hugging Face (Twitter)
RT @romainhuet: Both gpt-oss models are trending #1 and #2 among 2M models on @huggingface! 🤗 Thanks to the open-source AI community for your support since launch.
We’re following discussions and will pop in when we can—feel free to ask questions, share ideas, and show what you’re building!
RT @romainhuet: Both gpt-oss models are trending #1 and #2 among 2M models on @huggingface! 🤗 Thanks to the open-source AI community for your support since launch.
We’re following discussions and will pop in when we can—feel free to ask questions, share ideas, and show what you’re building!
This media is not supported in your browser
VIEW IN TELEGRAM
Hugging Face (Twitter)
RT @roo_code: ICYMI: Roo Code now integrates with Hugging Face 🤗
Plug in your API key, explore 90+ models, and run them directly from your editor—no wrappers, no token copy-paste.
Try it now!
RT @roo_code: ICYMI: Roo Code now integrates with Hugging Face 🤗
Plug in your API key, explore 90+ models, and run them directly from your editor—no wrappers, no token copy-paste.
Try it now!
This media is not supported in your browser
VIEW IN TELEGRAM
Hugging Face (Twitter)
RT @reach_vb: BOOOOM! You can now run @OpenAI gpt-oss 20B natively in @GoogleColab T4 for FREE! 🔥
Powered by Transformers ⚡
The setup takes a bit since everything is bleeding edge, but once done it should work as expected
Link to our cookbook in comments 👇
RT @reach_vb: BOOOOM! You can now run @OpenAI gpt-oss 20B natively in @GoogleColab T4 for FREE! 🔥
Powered by Transformers ⚡
The setup takes a bit since everything is bleeding edge, but once done it should work as expected
Link to our cookbook in comments 👇
Hugging Face (Twitter)
RT @calebfahlgren: The @huggingface trending is filled with absolute bangers 😮💨
RT @calebfahlgren: The @huggingface trending is filled with absolute bangers 😮💨
Hugging Face (Twitter)
RT @mervenoyann: new TRL comes with GRPO & MPO support for vision language models 💥
we also dropped an explainer on them & how to train with one-liner CLI commands 🫡
RT @mervenoyann: new TRL comes with GRPO & MPO support for vision language models 💥
we also dropped an explainer on them & how to train with one-liner CLI commands 🫡
Hugging Face (Twitter)
RT @abidlabs: Don't lock in your experiment tracking data into proprietary vendors!
With Trackio, all of your metrics are stored in a (public or private, you choose) Hugging Face Dataset, so that you can export them at any time!
https://github.com/gradio-app/trackio
RT @abidlabs: Don't lock in your experiment tracking data into proprietary vendors!
With Trackio, all of your metrics are stored in a (public or private, you choose) Hugging Face Dataset, so that you can export them at any time!
https://github.com/gradio-app/trackio
Hugging Face (Twitter)
RT @wjb_mattingly: TIL you can add a duration to spaces.GPU() when you expect a model to take longer than 60 seconds to run inference. I needed to do this because NuMarkedown-8B-Thinking took about 300 seconds to process a WW2 passport
RT @wjb_mattingly: TIL you can add a duration to spaces.GPU() when you expect a model to take longer than 60 seconds to run inference. I needed to do this because NuMarkedown-8B-Thinking took about 300 seconds to process a WW2 passport
Hugging Face (Twitter)
RT @ClementDelangue: So excited to announce that @huggingface @LeRobotHF can now be installed with a simple pip install and just crossed 15,000 @github stars!
It's already integrated into hundreds of robots, ranging from simple hand grippers like the SO-100/101 all the way to some of the most complex humanoid robots like @pollenrobotics Reachy 2.
Thanks to all contributors of policies, models & datasets (like @nvidia, @physical_int, @microsoft, SmolVLA,...) who already shared over 1,500 models & 15,000 datasets, it's becoming the standard to bridge hardware and software in AI robotics.
Let's go open AI robotics 🦾🦾🦾
RT @ClementDelangue: So excited to announce that @huggingface @LeRobotHF can now be installed with a simple pip install and just crossed 15,000 @github stars!
It's already integrated into hundreds of robots, ranging from simple hand grippers like the SO-100/101 all the way to some of the most complex humanoid robots like @pollenrobotics Reachy 2.
Thanks to all contributors of policies, models & datasets (like @nvidia, @physical_int, @microsoft, SmolVLA,...) who already shared over 1,500 models & 15,000 datasets, it's becoming the standard to bridge hardware and software in AI robotics.
Let's go open AI robotics 🦾🦾🦾
Hugging Face (Twitter)
RT @QuixiAI: I really don't know why people are whining about gpt-oss.
I'm using 120b for real work and other than being overly structured and prudish, I've no problem. And I appreciate the innovation in the chat template. (Which was a happy bonus of this release)
Finally - it's open source and apache 2.0 - it there's anything you don't like about it you can fine-tune it to act differently. (And you can sell your fine-tune and keep all the profit!)
120b is way way faster than other models in its class (Mistral large, llama 3.3 70b, qwen 2.5 72b) and thus it's perfect for home and small office use running on consumer hardware like 4x3090. (Can be built for $5,000)
We don't need data centers to run capable AI.
I chatted with it much of the day yesterday and as a coding model the code works the first time. Even complex code.
It's not as good as gpt5 and Claude of course but that's a stupid comparison.
Compare it to llama 3.3 70b. It's better at everything I tried, except for creative writing.
It's a good model. It's not perfect but it's really nice and I appreciate that it's free and it's American. We need to praise good behavior and appreciate good things.
RT @QuixiAI: I really don't know why people are whining about gpt-oss.
I'm using 120b for real work and other than being overly structured and prudish, I've no problem. And I appreciate the innovation in the chat template. (Which was a happy bonus of this release)
Finally - it's open source and apache 2.0 - it there's anything you don't like about it you can fine-tune it to act differently. (And you can sell your fine-tune and keep all the profit!)
120b is way way faster than other models in its class (Mistral large, llama 3.3 70b, qwen 2.5 72b) and thus it's perfect for home and small office use running on consumer hardware like 4x3090. (Can be built for $5,000)
We don't need data centers to run capable AI.
I chatted with it much of the day yesterday and as a coding model the code works the first time. Even complex code.
It's not as good as gpt5 and Claude of course but that's a stupid comparison.
Compare it to llama 3.3 70b. It's better at everything I tried, except for creative writing.
It's a good model. It's not perfect but it's really nice and I appreciate that it's free and it's American. We need to praise good behavior and appreciate good things.
Hugging Face (Twitter)
RT @PGelsinger: Open always wins.
https://venturebeat.com/ai/why-open-source-ai-became-an-american-national-priority/
RT @PGelsinger: Open always wins.
https://venturebeat.com/ai/why-open-source-ai-became-an-american-national-priority/
VentureBeat
Why open-source AI became an American national priority
To reflect democratic principles, AI must be built in the open. If the U.S. wants to lead the AI race, it must lead the open-source AI race.
Hugging Face (Twitter)
RT @HuggingPapers: Tencent AI Lab introduces R-Zero!
A groundbreaking framework enabling LLMs to self-evolve their reasoning capabilities
from zero human-curated data, through an autonomous Challenger-Solver loop.
RT @HuggingPapers: Tencent AI Lab introduces R-Zero!
A groundbreaking framework enabling LLMs to self-evolve their reasoning capabilities
from zero human-curated data, through an autonomous Challenger-Solver loop.