Scaling Laws for Looped Mixture of Experts
Paper • 2609.40316 • Published • 19
AI & ML interests
None defined yet.
Recent Activity
View all activity
yanbeic
authored a
paper 2 days ago
yanbeic
submitted a
paper to Daily Papers 2 days ago
Fix: support reasoning_effort in chat template
1
#4 opened 10 days ago
by 
Molbap
Fix: support reasoning_effort in chat template
#65 opened 10 days ago
by Molbap
yanbeic
authored 4
papers 4 months ago
BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks
Paper • 2207.06873 • Published
The Amazon Nova Family of Models: Technical Report and Model Card
Paper • 2506.12103 • Published • 1
ScaleDet: A Scalable Multi-Dataset Object Detector
Paper • 2306.04849 • Published
MobileMoE: Scaling On-Device Mixture of Experts
Paper • 2605.27358 • Published • 16
gchauras
authored a
paper 7 months ago
gchauras
authored 2
papers 11 months ago
Post
15936
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
4929
🚀 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
Post
7343
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
3772
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
10221
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
1468
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
1224
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
1990
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!
Post
3859
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!