Today we’re celebrating 10 years of the Meta FAIR lab in Paris by sharing a collection of new models, datasets and some exciting milestones in the impacts of open source — all laddering up to our ongoing work to achieve Advanced Machine Intelligence (AMI). Meta PARTNR is a
OPEN SOURCE
-
Reasoning LLMs: Paper, Article, and S1 GitHub Repository
By
–
– Link to the paper: https://
arxiv.org/abs/2501.19393
– My reasoning LLM article (they use methods 1 and 4): https://
magazine.sebastianraschka.com/p/understandin
g-reasoning-llms
…
– The s1 GitHub repo: https://
github.com/simplescaling/
s1
… -
Deepseek demonstrates open competition drives superior AI development
By
–
IMO, Deepseek shows that strong open competition (as in open science and open-source AI) works to produce better AI and that we need more of this in the US or we run the risk of losing the lead.
-
Using Ollama for Testing and vLLM for Production Serving
By
–
I use ollama most of the times for testing and prototyping and then vLLM when i need to serve it.
-
LIMO: Less Data Improves Reasoning Performance
By
–
LIMO: Less is More for Reasoning With only 817 examples, it outperforms previous models, proving less data can enhance reasoning. https://
arxiv.org/pdf/2502.03387 https://
github.com/GAIR-NLP/LIMO https://
huggingface.co/datasets/GAIR/
LIMO
… -
Pydantic AI: Agent Engineering with Graphs and Tools
By
–
Agent Engineering with Pydantic + Graphs https://
latent.space/p/pydantic with @samuelcolvin
! We've heard from @jxnlco 3 years running that @Pydantic Is All We Need, and this is even more true today with the launch of Pydantic AI! With a little @marimo_io love at the end 🙂 -
DeepSeek-R1 RL Training Simplicity Versus Process Reward Models
By
–
From an open-research point of view, probably the greatest thing about DeepSeek–R1 is how its RL training technique appears so straightforward and simple in comparison to the cumbersome approaches people were starting to think necessary for learning reasoning like Process Reward
-
Open-Source AI Advocacy at Paris AI Summit 2026
By
–
I'll travel to Paris next week for the AI Summit to represent the open-source AI community. I'll try to push world leaders & big tech CEOs to recognize that open science and open-source AI are critical for distributing power, creating value, and reducing risks in AI.
-
Keras Community Meeting Tomorrow at 11am PT
By
–
The Keras team will be doing a community meeting on Friday morning (tomorrow) at 11am PT. it's a public Meet call, anyone can join. You'll get updates on what's new in Keras, what will land next, and you'll be able to ask any question you have.