Atla Selene Mini: A General Purpose Evaluation Model
Paper โข 2501.17195 โข Published โข 35
Agents Hack
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
HennersBro98ย
authored 2
papers 7 days ago
spisupatย
authored a
paper 7 days ago
spisupatย
submitted a
paper to Daily Papers 8 days ago
stevenbucailleย
posted an update 5 months ago
Post
358
LWDetr is available in ๐ค transformers !
Checkout the collection to find the original paper, model weights and a demo space : https://huggingface.co/collections/stevenbucaille/lwdetr
Checkout the collection to find the original paper, model weights and a demo space : https://huggingface.co/collections/stevenbucaille/lwdetr
Post
4547
The new Mistral 3 models are here !
Today, we announce Mistral 3, the next generation of Mistral models. Mistral 3 includes three state-of-the-art small, dense models (14B, 8B, and 3B) and Mistral Large 3 โ our most capable model to date โ a sparse mixture-of-experts trained with 41B active and 675B total parameters.
All models are released under the Apache 2.0 license.
Ministrals :
https://huggingface.co/collections/mistralai/ministral-3
Mistral Large 3:
https://huggingface.co/collections/mistralai/mistral-large-3
Today, we announce Mistral 3, the next generation of Mistral models. Mistral 3 includes three state-of-the-art small, dense models (14B, 8B, and 3B) and Mistral Large 3 โ our most capable model to date โ a sparse mixture-of-experts trained with 41B active and 675B total parameters.
All models are released under the Apache 2.0 license.
Ministrals :
https://huggingface.co/collections/mistralai/ministral-3
Mistral Large 3:
https://huggingface.co/collections/mistralai/mistral-large-3
- 2 replies
nouamanetaziย
posted an update 8 months ago
Post
4962
After training ๐๐ฆ๐จ๐ฅ๐๐๐ on ๐๐๐ ๐๐๐๐๐ฌ for nearly a month, I've come to realize something most people overlook: ๐ข๐ง๐๐ซ๐๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ฎ๐ซ๐ ๐ข๐ฌ ๐ญ๐ก๐ ๐ฆ๐๐ค๐-๐จ๐ซ-๐๐ซ๐๐๐ค ๐๐๐๐ญ๐จ๐ซ ๐ข๐ง ๐๐๐ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ . ๐ฅ
Everyone talks about model architecture and data quality. And yes, those matter immensely. But here's what nobody tells you: when your training run fails at 2 AM because of mysterious ๐๐๐๐ ๐๐ซ๐ซ๐จ๐ซ๐ฌ, or when your expensive GPU cluster is running at ๐๐% ๐๐๐๐ข๐๐ข๐๐ง๐๐ฒ, the problem isn't your model. It's most probably a ๐ฆ๐ข๐ฌ๐ฎ๐ฌ๐ ๐จ๐ ๐ญ๐ก๐ ๐ก๐๐ซ๐๐ฐ๐๐ซ๐. ๐ ๏ธ
Questions that seemed simple but had no clear answers: Why is ๐๐จ๐ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ ๐ฌ๐ฅ๐จ๐ฐ๐๐ซ ๐ญ๐ก๐๐ง ๐๐๐ง๐ฌ๐ ๐ฆ๐จ๐๐๐ฅ๐ฌ? Which ๐๐๐๐ ๐๐ฅ๐๐ ๐ฌ should we actually set? How often should we checkpoint without killing throughput?
That's why we built ๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค ๐: a complete guide covering everything from model architecture and data curation to the SmolLM3 training marathon, post-training techniques, and crucially, the ๐ข๐ง๐๐ซ๐๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ฎ๐ซ๐ ๐ฅ๐๐ฒ๐๐ซ that most teams get wrong.
We validated real vs theoretical bandwidth across the entire stack: ๐๐๐๐ ๐ก๐ข๐ญ๐ญ๐ข๐ง๐ ๐ ๐๐/๐ฌ, ๐๐๐๐ข๐ง๐ค ๐.๐ ๐ซ๐๐๐๐ก๐ข๐ง๐ ๐๐๐ ๐๐/๐ฌ, ๐๐๐๐ ๐๐๐ง๐ ๐๐ญ ๐๐.๐ ๐๐/๐ฌ. Then we ran collective operations across ๐๐๐ ๐๐๐๐ฌ (16 nodes, 8xH100s each) and measured how performance degrades at scale: all-reduce drops from ๐๐๐ ๐๐/๐ฌ on a single node to ๐๐๐-๐๐๐ ๐๐/๐ฌ across 16 nodes.
If you've ever wondered why your training runs are slower than they should be, or you're planning to scale up and want to avoid expensive mistakes, this guide might save you weeks of debugging.
๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค: https://lnkd.in/e5MKXUHS
Shared with โค๏ธ by the HuggingFace team
Everyone talks about model architecture and data quality. And yes, those matter immensely. But here's what nobody tells you: when your training run fails at 2 AM because of mysterious ๐๐๐๐ ๐๐ซ๐ซ๐จ๐ซ๐ฌ, or when your expensive GPU cluster is running at ๐๐% ๐๐๐๐ข๐๐ข๐๐ง๐๐ฒ, the problem isn't your model. It's most probably a ๐ฆ๐ข๐ฌ๐ฎ๐ฌ๐ ๐จ๐ ๐ญ๐ก๐ ๐ก๐๐ซ๐๐ฐ๐๐ซ๐. ๐ ๏ธ
Questions that seemed simple but had no clear answers: Why is ๐๐จ๐ ๐ญ๐ซ๐๐ข๐ง๐ข๐ง๐ ๐ฌ๐ฅ๐จ๐ฐ๐๐ซ ๐ญ๐ก๐๐ง ๐๐๐ง๐ฌ๐ ๐ฆ๐จ๐๐๐ฅ๐ฌ? Which ๐๐๐๐ ๐๐ฅ๐๐ ๐ฌ should we actually set? How often should we checkpoint without killing throughput?
That's why we built ๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค ๐: a complete guide covering everything from model architecture and data curation to the SmolLM3 training marathon, post-training techniques, and crucially, the ๐ข๐ง๐๐ซ๐๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ฎ๐ซ๐ ๐ฅ๐๐ฒ๐๐ซ that most teams get wrong.
We validated real vs theoretical bandwidth across the entire stack: ๐๐๐๐ ๐ก๐ข๐ญ๐ญ๐ข๐ง๐ ๐ ๐๐/๐ฌ, ๐๐๐๐ข๐ง๐ค ๐.๐ ๐ซ๐๐๐๐ก๐ข๐ง๐ ๐๐๐ ๐๐/๐ฌ, ๐๐๐๐ ๐๐๐ง๐ ๐๐ญ ๐๐.๐ ๐๐/๐ฌ. Then we ran collective operations across ๐๐๐ ๐๐๐๐ฌ (16 nodes, 8xH100s each) and measured how performance degrades at scale: all-reduce drops from ๐๐๐ ๐๐/๐ฌ on a single node to ๐๐๐-๐๐๐ ๐๐/๐ฌ across 16 nodes.
If you've ever wondered why your training runs are slower than they should be, or you're planning to scale up and want to avoid expensive mistakes, this guide might save you weeks of debugging.
๐๐ก๐ ๐๐ฆ๐จ๐ฅ ๐๐ซ๐๐ข๐ง๐ข๐ง๐ ๐๐ฅ๐๐ฒ๐๐จ๐จ๐ค: https://lnkd.in/e5MKXUHS
Shared with โค๏ธ by the HuggingFace team
thomwolfย
authored a
paper 9 months ago
jdelavandeย
authored a
paper 9 months ago
thomwolfย
authored a
paper about 1 year ago
m-ricย
updated a
Space about 1 year ago
Cidoyiย
updated a
Space about 1 year ago
thomwolfย
authored a
paper about 1 year ago
m-ricย
published a
Space about 1 year ago
Post
4757
Meet our new agentic model : ๐๐ฒ๐๐๐๐ฟ๐ฎ๐น
Devstral is an open-source LLM built software engineering tasks built under a collaboration between Mistral AI and All Hands AI ๐.
๐๐ฒ๐ ๐ณ๐ฒ๐ฎ๐๐๐ฟ๐ฒ๐ :
โข ๐ค ๐๐ด๐ฒ๐ป๐๐ : perfect for Agentic coding
โข ๐ ๐น๐ถ๐ด๐ต๐๐๐ฒ๐ถ๐ด๐ต๐: Devstral is a ๐ฎ๐ฐ๐ parameter based on Mistral small.
โข ยฉ๏ธ ๐๐ฝ๐ฎ๐ฐ๐ต๐ฒ ๐ฎ.๐ฌ, meaning fully open-source !
โข ๐ A ๐ญ๐ฎ๐ด๐ธ context window.
๐Blog : https://mistral.ai/news/devstral
โกAPI : The model is also available on our API under the name ๐ฑ๐ฒ๐๐๐๐ฟ๐ฎ๐น-๐๐บ๐ฎ๐น๐น-๐ฎ๐ฑ๐ฌ๐ฑ
๐ค repo : mistralai/Devstral-Small-2505
Can't wait to see what you will build with it !
Devstral is an open-source LLM built software engineering tasks built under a collaboration between Mistral AI and All Hands AI ๐.
๐๐ฒ๐ ๐ณ๐ฒ๐ฎ๐๐๐ฟ๐ฒ๐ :
โข ๐ค ๐๐ด๐ฒ๐ป๐๐ : perfect for Agentic coding
โข ๐ ๐น๐ถ๐ด๐ต๐๐๐ฒ๐ถ๐ด๐ต๐: Devstral is a ๐ฎ๐ฐ๐ parameter based on Mistral small.
โข ยฉ๏ธ ๐๐ฝ๐ฎ๐ฐ๐ต๐ฒ ๐ฎ.๐ฌ, meaning fully open-source !
โข ๐ A ๐ญ๐ฎ๐ด๐ธ context window.
๐Blog : https://mistral.ai/news/devstral
โกAPI : The model is also available on our API under the name ๐ฑ๐ฒ๐๐๐๐ฟ๐ฎ๐น-๐๐บ๐ฎ๐น๐น-๐ฎ๐ฑ๐ฌ๐ฑ
๐ค repo : mistralai/Devstral-Small-2505
Can't wait to see what you will build with it !
- 1 reply
Post
8779
If you've followed the progress of robotics in the past 18 months, you've likely noticed how robotics is increasingly becoming the next frontier that AI will unlock.
At Hugging Faceโin robotics and across all AI fieldsโwe believe in a future where AI and robots are open-source, transparent, and affordable; community-built and safe; hackable and fun. We've had so much mutual understanding and passion working with the Pollen Robotics team over the past year that we decided to join forces!
You can already find our open-source humanoid robot platform Reachy 2 on the Pollen website and the Pollen community and people here on the hub at
pollen-robotics
We're so excited to build and share more open-source robots with the world in the coming months!
At Hugging Faceโin robotics and across all AI fieldsโwe believe in a future where AI and robots are open-source, transparent, and affordable; community-built and safe; hackable and fun. We've had so much mutual understanding and passion working with the Pollen Robotics team over the past year that we decided to join forces!
You can already find our open-source humanoid robot platform Reachy 2 on the Pollen website and the Pollen community and people here on the hub at
We're so excited to build and share more open-source robots with the world in the coming months!
- 1 reply
thomwolfย
authored a
paper about 1 year ago
nouamanetaziย
authored a
paper about 1 year ago
thomwolfย
authored a
paper about 1 year ago
Post
3953
The new DeepSite space is really insane for vibe-coders
enzostvs/deepsite
With the wave of vibe-coding-optimized LLMs like the latest open-source DeepSeek model (version V3-0324), you can basically prompt out-of-the-box and create any app and game in one-shot.
It feels so powerful to me, no more complex framework or under-the-hood prompt engineering to have a working text-to-app tool.
AI is eating the world and *open-source* AI is eating AI itself!
PS: and even more meta is that the DeepSite app and DeepSeek model are both fully open-source code => time to start recursively improve?
PPS: you still need some inference hosting unless you're running the 600B param model at home, so check the very nice list of HF Inference Providers for this model: deepseek-ai/DeepSeek-V3-0324
enzostvs/deepsite
With the wave of vibe-coding-optimized LLMs like the latest open-source DeepSeek model (version V3-0324), you can basically prompt out-of-the-box and create any app and game in one-shot.
It feels so powerful to me, no more complex framework or under-the-hood prompt engineering to have a working text-to-app tool.
AI is eating the world and *open-source* AI is eating AI itself!
PS: and even more meta is that the DeepSite app and DeepSeek model are both fully open-source code => time to start recursively improve?
PPS: you still need some inference hosting unless you're running the 600B param model at home, so check the very nice list of HF Inference Providers for this model: deepseek-ai/DeepSeek-V3-0324
- 1 reply