Alina Lozovskaya (@ailozovskaya) 's Twitter Profile
Alina Lozovskaya

@ailozovskaya

ML Research Engineer at @huggingface LLM Evaluation Team 🤗 | Linguist who codes 👩🏻‍💻 | Take photos and play music after work

she / her

ID: 1775204234666881024

linkhttps://huggingface.co/alozowski calendar_today02-04-2024 16:50:52

417 Tweet

663 Followers

227 Following

Julien Chaumond (@julien_c) 's Twitter Profile Photo

GAME CHANGER FOR AI-CENTRIC ORGANIZATIONS Organizations on Hugging Face can now provision+monitor the usage of Inference Providers by their team members 👀 Subcribe to Enterprise Hub to get it!

GAME CHANGER FOR AI-CENTRIC ORGANIZATIONS

Organizations on <a href="/huggingface/">Hugging Face</a> can now provision+monitor the usage of Inference Providers by their team members 👀

Subcribe to Enterprise Hub to get it!
Alina Lozovskaya (@ailozovskaya) 's Twitter Profile Photo

Just noticed Yourbench has 30 forks on Github! 💥 If you've got suggestions, feel free to open an issue, make a PR, or tag Sumuk 🤗 / me here!

Just noticed Yourbench has 30 forks on Github! 💥
If you've got suggestions, feel free to open an issue, make a PR, or tag <a href="/sumukx/">Sumuk 🤗</a> / me here!
merve (@mervenoyann) 's Twitter Profile Photo

stop writing CUDA kernels yourself we have launched Kernel Hub: easy optimized kernels for all models on Hugging Face Hub 🔥 use them right away! it's where the community populates optimized kernels 🤝 keep reading 😏

stop writing CUDA kernels yourself

we have launched Kernel Hub: easy optimized kernels for all models on <a href="/huggingface/">Hugging Face</a> Hub 🔥 use them right away! 
it's where the community populates optimized kernels 🤝
keep reading 😏
Niels Rogge (@nielsrogge) 's Twitter Profile Photo

Want to use ChatGPT but 100% private and offline? I show how to use LM Studio with open Hugging Face models in my new YouTube tutorial 🤗 Explains things like GGUF, quantization, why Mistral 3.2-Small takes up 15GB in 4 bit etc. Also showcases the OpenAI API compatibility!

Want to use ChatGPT but 100% private and offline?

I show how to use <a href="/lmstudio/">LM Studio</a> with open <a href="/huggingface/">Hugging Face</a> models in my new <a href="/YouTube/">YouTube</a> tutorial 🤗

Explains things like GGUF, quantization, why Mistral 3.2-Small takes up 15GB in 4 bit etc. Also showcases the OpenAI API compatibility!
Loubna Ben Allal (@loubnabenallal1) 's Twitter Profile Photo

Introducing SmolLM3: a strong, smol reasoner! > SoTA 3B model > dual mode reasoning (think/no_think) > long context, up to 128k > multilingual: en, fr, es, de, it, pt > fully open source (data, code, recipes) huggingface.co/blog/smollm3

Introducing SmolLM3: a strong, smol reasoner!

&gt; SoTA 3B model
&gt; dual mode reasoning (think/no_think)
&gt; long context, up to 128k
&gt; multilingual: en, fr, es, de, it, pt
&gt; fully open source (data, code, recipes)

huggingface.co/blog/smollm3
Thomas Wolf (@thom_wolf) 's Twitter Profile Photo

Thrilled to finally share what we've been working on for months at Hugging Face 🤝Pollen Robotics Our first robot: Reachy Mini A dream come true: cute and low priced, hackable yet easy to use, powered by open-source and the infinite community. Tiny price, small size, huge

Gradio (@gradio) 's Twitter Profile Photo

Complex Gradio apps running slow? 😤 We just fixed the root cause 💪 Gradio v5.36 only renders visible components → huge performance gains No more rendering everything behind the scenes ⚡⚡⚡ Time to upgrade: pip install --upgrade gradio

Complex Gradio apps running slow? 😤
We just fixed the root cause 💪
Gradio v5.36 only renders visible components → huge performance gains
No more rendering everything behind the scenes ⚡⚡⚡

Time to upgrade: pip install --upgrade gradio