Single-minus gluon tree amplitudes are nonzero
Paper • 2602.12176 • Published • 8
AI & ML interests
None defined yet.
lewtun
submitted a
paper to Daily Papers 8 months ago
lewtun
submitted a
paper to Daily Papers 9 months ago
alozowski
authored a
paper 11 months ago
nouamanetazi
posted an update 12 months ago
Post
5,296
After training 𝐒𝐦𝐨𝐥𝐋𝐌𝟑 on 𝟑𝟖𝟒 𝐇𝟏𝟎𝟎𝐬 for nearly a month, I've come to realize something most people overlook: 𝐢𝐧𝐟𝐫𝐚𝐬𝐭𝐫𝐮𝐜𝐭𝐮𝐫𝐞 𝐢𝐬 𝐭𝐡𝐞 𝐦𝐚𝐤𝐞-𝐨𝐫-𝐛𝐫𝐞𝐚𝐤 𝐟𝐚𝐜𝐭𝐨𝐫 𝐢𝐧 𝐋𝐋𝐌 𝐭𝐫𝐚𝐢𝐧𝐢𝐧𝐠. 🔥
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 𝐍𝐂𝐂𝐋 𝐞𝐫𝐫𝐨𝐫𝐬, or when your expensive GPU cluster is running at 𝟔𝟎% 𝐞𝐟𝐟𝐢𝐜𝐢𝐞𝐧𝐜𝐲, the problem isn't your model. It's most probably a 𝐦𝐢𝐬𝐮𝐬𝐞 𝐨𝐟 𝐭𝐡𝐞 𝐡𝐚𝐫𝐝𝐰𝐚𝐫𝐞. 🛠️
Questions that seemed simple but had no clear answers: Why is 𝐌𝐨𝐄 𝐭𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝐬𝐥𝐨𝐰𝐞𝐫 𝐭𝐡𝐚𝐧 𝐝𝐞𝐧𝐬𝐞 𝐦𝐨𝐝𝐞𝐥𝐬? Which 𝐍𝐂𝐂𝐋 𝐟𝐥𝐚𝐠𝐬 should we actually set? How often should we checkpoint without killing throughput?
That's why we built 𝐓𝐡𝐞 𝐒𝐦𝐨𝐥 𝐓𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝐏𝐥𝐚𝐲𝐛𝐨𝐨𝐤 📖: a complete guide covering everything from model architecture and data curation to the SmolLM3 training marathon, post-training techniques, and crucially, the 𝐢𝐧𝐟𝐫𝐚𝐬𝐭𝐫𝐮𝐜𝐭𝐮𝐫𝐞 𝐥𝐚𝐲𝐞𝐫 that most teams get wrong.
We validated real vs theoretical bandwidth across the entire stack: 𝐇𝐁𝐌𝟑 𝐡𝐢𝐭𝐭𝐢𝐧𝐠 𝟑 𝐓𝐁/𝐬, 𝐍𝐕𝐋𝐢𝐧𝐤 𝟒.𝟎 𝐫𝐞𝐚𝐜𝐡𝐢𝐧𝐠 𝟕𝟖𝟔 𝐆𝐁/𝐬, 𝐏𝐂𝐈𝐞 𝐆𝐞𝐧𝟒 𝐚𝐭 𝟏𝟒.𝟐 𝐆𝐁/𝐬. Then we ran collective operations across 𝟏𝟐𝟖 𝐆𝐏𝐔𝐬 (16 nodes, 8xH100s each) and measured how performance degrades at scale: all-reduce drops from 𝟒𝟖𝟎 𝐆𝐁/𝐬 on a single node to 𝟑𝟐𝟎-𝟑𝟓𝟎 𝐆𝐁/𝐬 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.
𝐓𝐡𝐞 𝐒𝐦𝐨𝐥 𝐓𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝐏𝐥𝐚𝐲𝐛𝐨𝐨𝐤: https://lnkd.in/e5MKXUHS
Shared with ❤️ 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 𝐍𝐂𝐂𝐋 𝐞𝐫𝐫𝐨𝐫𝐬, or when your expensive GPU cluster is running at 𝟔𝟎% 𝐞𝐟𝐟𝐢𝐜𝐢𝐞𝐧𝐜𝐲, the problem isn't your model. It's most probably a 𝐦𝐢𝐬𝐮𝐬𝐞 𝐨𝐟 𝐭𝐡𝐞 𝐡𝐚𝐫𝐝𝐰𝐚𝐫𝐞. 🛠️
Questions that seemed simple but had no clear answers: Why is 𝐌𝐨𝐄 𝐭𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝐬𝐥𝐨𝐰𝐞𝐫 𝐭𝐡𝐚𝐧 𝐝𝐞𝐧𝐬𝐞 𝐦𝐨𝐝𝐞𝐥𝐬? Which 𝐍𝐂𝐂𝐋 𝐟𝐥𝐚𝐠𝐬 should we actually set? How often should we checkpoint without killing throughput?
That's why we built 𝐓𝐡𝐞 𝐒𝐦𝐨𝐥 𝐓𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝐏𝐥𝐚𝐲𝐛𝐨𝐨𝐤 📖: a complete guide covering everything from model architecture and data curation to the SmolLM3 training marathon, post-training techniques, and crucially, the 𝐢𝐧𝐟𝐫𝐚𝐬𝐭𝐫𝐮𝐜𝐭𝐮𝐫𝐞 𝐥𝐚𝐲𝐞𝐫 that most teams get wrong.
We validated real vs theoretical bandwidth across the entire stack: 𝐇𝐁𝐌𝟑 𝐡𝐢𝐭𝐭𝐢𝐧𝐠 𝟑 𝐓𝐁/𝐬, 𝐍𝐕𝐋𝐢𝐧𝐤 𝟒.𝟎 𝐫𝐞𝐚𝐜𝐡𝐢𝐧𝐠 𝟕𝟖𝟔 𝐆𝐁/𝐬, 𝐏𝐂𝐈𝐞 𝐆𝐞𝐧𝟒 𝐚𝐭 𝟏𝟒.𝟐 𝐆𝐁/𝐬. Then we ran collective operations across 𝟏𝟐𝟖 𝐆𝐏𝐔𝐬 (16 nodes, 8xH100s each) and measured how performance degrades at scale: all-reduce drops from 𝟒𝟖𝟎 𝐆𝐁/𝐬 on a single node to 𝟑𝟐𝟎-𝟑𝟓𝟎 𝐆𝐁/𝐬 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.
𝐓𝐡𝐞 𝐒𝐦𝐨𝐥 𝐓𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝐏𝐥𝐚𝐲𝐛𝐨𝐨𝐤: https://lnkd.in/e5MKXUHS
Shared with ❤️ by the HuggingFace team
ariG23498
authored a
paper about 1 year ago
Post
16,491
deepseek-ai/DeepSeek-OCR is out! 🔥 my take ⤵️
> pretty insane it can parse and re-render charts in HTML
> it uses CLIP and SAM features concatenated, so better grounding
> very efficient per vision tokens/performance ratio
> covers 100 languages
> pretty insane it can parse and re-render charts in HTML
> it uses CLIP and SAM features concatenated, so better grounding
> very efficient per vision tokens/performance ratio
> covers 100 languages
- 5 replies
Post
4,979
🚀 New blog: Maintain the unmaintainable – 1M+ Python LOC, 400+ models
How do you stop a million-line library built by thousands of contributors from collapsing under its own weight?
At 🤗 Transformers, we do it with explicit software-engineering tenets, principles that make the codebase hackable at scale.
🔍 Inside the post:
– One Model, One File: readability first — you can still open a modeling file and see the full logic, top to bottom.
– Modular Transformers: visible inheritance that cuts maintenance cost by ~15× while keeping models readable.
– Config-Driven Performance: FlashAttention, tensor parallelism, and attention scheduling are config-level features, not rewrites.
Written with @lysandre ,@pcuenq and @yonigozlan , this is a deep dive into how Transformers stays fast, open, and maintainable.
Read it here → transformers-community/Transformers-tenets
How do you stop a million-line library built by thousands of contributors from collapsing under its own weight?
At 🤗 Transformers, we do it with explicit software-engineering tenets, principles that make the codebase hackable at scale.
🔍 Inside the post:
– One Model, One File: readability first — you can still open a modeling file and see the full logic, top to bottom.
– Modular Transformers: visible inheritance that cuts maintenance cost by ~15× while keeping models readable.
– Config-Driven Performance: FlashAttention, tensor parallelism, and attention scheduling are config-level features, not rewrites.
Written with @lysandre ,@pcuenq and @yonigozlan , this is a deep dive into how Transformers stays fast, open, and maintainable.
Read it here → transformers-community/Transformers-tenets
burtenshaw
authored a
paper about 1 year ago
Post
7,362
large AI labs open-sourced a ton of models last week 🔥
here's few picks, find even more here merve/sep-16-releases-68d13ea4c547f02f95842f05 🤝
> IBM released a new Docling model with 258M params based on Granite (A2.0) 📝 ibm-granite/granite-docling-258M
> Xiaomi released 7B audio LM with base and instruct variants (MIT) XiaomiMiMo/mimo-audio-68cc7202692c27dae881cce0
> DecartAI released Lucy Edit, open Nano Banana 🍌 (NC) decart-ai/Lucy-Edit-Dev
> OpenGVLab released a family of agentic computer use models (3B/7B/32B) with the dataset 💻 OpenGVLab/scalecua-68c912cf56f7ff4c8e034003
> Meituan Longcat released thinking version of LongCat-Flash 💭 meituan-longcat/LongCat-Flash-Thinking
here's few picks, find even more here merve/sep-16-releases-68d13ea4c547f02f95842f05 🤝
> IBM released a new Docling model with 258M params based on Granite (A2.0) 📝 ibm-granite/granite-docling-258M
> Xiaomi released 7B audio LM with base and instruct variants (MIT) XiaomiMiMo/mimo-audio-68cc7202692c27dae881cce0
> DecartAI released Lucy Edit, open Nano Banana 🍌 (NC) decart-ai/Lucy-Edit-Dev
> OpenGVLab released a family of agentic computer use models (3B/7B/32B) with the dataset 💻 OpenGVLab/scalecua-68c912cf56f7ff4c8e034003
> Meituan Longcat released thinking version of LongCat-Flash 💭 meituan-longcat/LongCat-Flash-Thinking
- 2 replies
Post
3,785
IBM just released small swiss army knife for the document models: granite-docling-258M on Hugging Face 🔥
> not only a document converter but also can do document question answering, understand multiple languages 🤯
> best part: released with Apache 2.0 license 👏 use it with your commercial projects!
> it supports transformers, vLLM and MLX from the get-go! 🤗
> built on SigLIP2 & granite-165M
model: ibm-granite/granite-docling-258M
demo: ibm-granite/granite-docling-258m-demo 💗
> not only a document converter but also can do document question answering, understand multiple languages 🤯
> best part: released with Apache 2.0 license 👏 use it with your commercial projects!
> it supports transformers, vLLM and MLX from the get-go! 🤗
> built on SigLIP2 & granite-165M
model: ibm-granite/granite-docling-258M
demo: ibm-granite/granite-docling-258m-demo 💗
Post
10,499
We're kick-starting the process of Transformers v5, with @ArthurZ and @cyrilvallez !
v5 should be significant: we're using it as a milestone for performance optimizations, saner defaults, and a much cleaner code base worthy of 2025.
Fun fact: v4.0.0-rc-1 came out on Nov 19, 2020, nearly five years ago!
v5 should be significant: we're using it as a milestone for performance optimizations, saner defaults, and a much cleaner code base worthy of 2025.
Fun fact: v4.0.0-rc-1 came out on Nov 19, 2020, nearly five years ago!
- 6 replies
Post
1,479
a ton of image/video generation models and LLMs from big labs 🔥
> Meta released facebook/mobilellm-r1-68c4597b104fac45f28f448e, smol LLMs for on-device use 💬
> Tencent released tencent/SRPO, high res image generation model and tencent/POINTS-Reader, cutting edge OCR 📝
> ByteDance released bytedance-research/HuMo, video generation from any input ⏯️
find more models, datasets, demos here merve/sep-11-releases-68c7dbfa26bea8cd921fa0ac
> Meta released facebook/mobilellm-r1-68c4597b104fac45f28f448e, smol LLMs for on-device use 💬
> Tencent released tencent/SRPO, high res image generation model and tencent/POINTS-Reader, cutting edge OCR 📝
> ByteDance released bytedance-research/HuMo, video generation from any input ⏯️
find more models, datasets, demos here merve/sep-11-releases-68c7dbfa26bea8cd921fa0ac
Post
1,235
fan-favorite vision LM Florence-2 is now officially supported in transformers 🤗
find all the models in
florence-community org 🫡
find all the models in
Post
3,357
New post is live!
This time we cover some major updates to
🤗
This time we cover some major updates to
transformers.🤗
- 2 replies
burtenshaw
posted an update about 1 year ago
Post
10,583
Smol course has a distinctive approach to teaching post-training, so I'm posting about how it’s different to other post-training courses, including the llm course that’s already available.
In short, the smol course is just more direct that any of the other course, and intended for semi-pro post trainers.
- It’s a minimal set of instructions on the core parts.
- It’s intended to bootstrap real projects you're working on.
- The material handsover to existing documentation for details
- Likewise, it handsover to the LLM course for basics.
- Assessment is based on a leaderboard, without reading all the material.
To start the smol course, follow here:
smol-course
In short, the smol course is just more direct that any of the other course, and intended for semi-pro post trainers.
- It’s a minimal set of instructions on the core parts.
- It’s intended to bootstrap real projects you're working on.
- The material handsover to existing documentation for details
- Likewise, it handsover to the LLM course for basics.
- Assessment is based on a leaderboard, without reading all the material.
To start the smol course, follow here:
Post
1,998
past week was great for open LLMs 🔥 merve/sep-1-releases-68bede0e729c12597eefd050
> Google released google/embeddinggemma-300m, new embedding model with 300M params
> new update to Kimi-K2 just landed moonshotai/Kimi-K2-Instruct-0905 😍
> OpenBMB released a new version to MiniCPM with 8B params openbmb/MiniCPM4.1-8B
also soooo many Qwen-Image & Kontext LoRAs dropped!
> Google released google/embeddinggemma-300m, new embedding model with 300M params
> new update to Kimi-K2 just landed moonshotai/Kimi-K2-Instruct-0905 😍
> OpenBMB released a new version to MiniCPM with 8B params openbmb/MiniCPM4.1-8B
also soooo many Qwen-Image & Kontext LoRAs dropped!
burtenshaw
posted an update about 1 year ago
Post
5,746
new smol course
If you’re building with or learning about post training AI models right now, we have a new FREE and CERTIFIED course.
🔗 Follow the org to join in smol-course
The course builds on smol course v1 which was the fastest way to learn to train your custom AI models. It now has:
- A leaderboard for students to submit models to
- Certification based on exams and leaderboards
- Prizes based on Leaderboards
- Up to date content on TRL and SmolLM3
- Deep integration with the Hub’s compute for model training and evaluation
We will release chapters every few weeks, so you can follow the org to stay updated.
If you’re building with or learning about post training AI models right now, we have a new FREE and CERTIFIED course.
🔗 Follow the org to join in
The course builds on smol course v1 which was the fastest way to learn to train your custom AI models. It now has:
- A leaderboard for students to submit models to
- Certification based on exams and leaderboards
- Prizes based on Leaderboards
- Up to date content on TRL and SmolLM3
- Deep integration with the Hub’s compute for model training and evaluation
We will release chapters every few weeks, so you can follow the org to stay updated.
- 2 replies
Post
3,867
upgrade your transformers 🔥
it comes with insanely capable models like merve/sam2-66ac9deac6fca3bc5482fe30, microsoft/kosmos-2.5, and more 🫡
I built a notebook you can run with free Colab T4 to walk through the API for new models 🙋🏻♀️ merve/smol-vision
fine-tuning will follow-up soon!
it comes with insanely capable models like merve/sam2-66ac9deac6fca3bc5482fe30, microsoft/kosmos-2.5, and more 🫡
I built a notebook you can run with free Colab T4 to walk through the API for new models 🙋🏻♀️ merve/smol-vision
fine-tuning will follow-up soon!
burtenshaw
posted an update about 1 year ago
Post
3,331
The open source AI community is just made of people who are passionate and care about their work. So we thought it would be cool to share our favourite icons of the community with a fun award.
Winners get free Hugging Face Pro Subscriptions, Merchandise, or compute credits for the hub.
🔗 Follow and nominate here:
community-spotlight
This is a new initiative to recognise and celebrate the incredible work being done by community members. It's all about inspiring more collaboration and innovation in the world of machine learning and AI.
They're highlighting contributors in four key areas:
- model creators: building and sharing innovative and state-of-the-art models.
- educators: sharing knowledge through posts, articles, demos, and events.
- tool builders: creating the libraries, frameworks, and applications that we all use.
- community champions: supporting and mentoring others in forums.
Know someone who deserves recognition? Nominate them by opening a post in the Hugging Face community forum.
Winners get free Hugging Face Pro Subscriptions, Merchandise, or compute credits for the hub.
🔗 Follow and nominate here:
This is a new initiative to recognise and celebrate the incredible work being done by community members. It's all about inspiring more collaboration and innovation in the world of machine learning and AI.
They're highlighting contributors in four key areas:
- model creators: building and sharing innovative and state-of-the-art models.
- educators: sharing knowledge through posts, articles, demos, and events.
- tool builders: creating the libraries, frameworks, and applications that we all use.
- community champions: supporting and mentoring others in forums.
Know someone who deserves recognition? Nominate them by opening a post in the Hugging Face community forum.
- 1 reply
Post
6,414
large AI labs have dropped so many open models last week 🔥 don't miss out on them
→ Apple released on-device vision LMs apple/fastvlm-68ac97b9cd5cacefdd04872e & apple/mobileclip2-68ac947dcb035c54bcd20c47
→ OpenGVLab released InternVL3.5, 32 new vision LMs with one based on gpt-oss! (OS) OpenGVLab/internvl35-68ac87bd52ebe953485927fb
→ MSFT released a killer small TTS model (OS) microsoft/VibeVoice-1.5B
find more herehttps://huggingface.co/collections/merve/august-29-releases-68b5a3754cfb8abf59e2b486
→ Apple released on-device vision LMs apple/fastvlm-68ac97b9cd5cacefdd04872e & apple/mobileclip2-68ac947dcb035c54bcd20c47
→ OpenGVLab released InternVL3.5, 32 new vision LMs with one based on gpt-oss! (OS) OpenGVLab/internvl35-68ac87bd52ebe953485927fb
→ MSFT released a killer small TTS model (OS) microsoft/VibeVoice-1.5B
find more herehttps://huggingface.co/collections/merve/august-29-releases-68b5a3754cfb8abf59e2b486
- 1 reply