OPEN SOURCE

–

31 October 2024 19h50

Check out the model weights here:

SmolLM2 1.7B Beats Larger Models with Apache 2.0 License

By

–

31 October 2024 19h50

Fuck it – it’s raining smol LMs – SmolLM2 1.7B – beats Qwen 2.5 1.5B & Llama 3.21B, Apache 2.0 licensed, trained on 11 Trillion tokens > 135M, 360M, 1.7B parameter model
> Trained on FineWeb-Edu, DCLM, The Stack, along w/ new mathematics and coding datasets
> Specialises in

→ View original post on X — @hwchase17

LangGraph Platform Enables Easy Agent Deployment

By

@hwchase17

–

31 October 2024 18h25

LangGraph Platform We've made the infra that is used to deploy agents in LangGraph Cloud more readily available. This easily deploys LangGraph agents with:
– Streaming support
– Background runs
– Support for long running agents
and more! https://
langchain-ai.github.io/langgraph/conc
epts/langgraph_platform/
…

→ View original post on X — @palantir

Drupal Code Reference Guide Updated for Versions 9 and 10

By

@palantir

–

31 October 2024 16h52

The quick code reference guide by @selwynpolit is a handy resource, and the good news is that it's been recently updated to reflect the changes in @Drupal 9 and 10. Take a look: https://
bit.ly/3YBntMt #drupal9 #drupal10 #drupal #opensource #FOSS

→ View original post on X — @01ai_yi, 2024-10-31 15:00 UTC

Refactor Earth Wins Hackathon with Sustainable AI Code Optimization

By

@01ai_yi

–

31 October 2024 16h00

🌍Exciting news from our developer community! We're thrilled to share a blog on Refactor Earth, which explores an innovative approach to sustainable AI. By combining Yi-Large and CodeBERT, this project optimizes code for efficiency, achieving over a 10% reduction in its environmental footprint! 🏆 Proud to announce that this project won 1st Place at the GenLab x AI Engineer World's Fair Hackathon. Huge kudos to @Shalini_Ananda for this remarkable achievement! 01-ai.github.io/blog.html?po… #YiLarge #AI #Hackathon

Model Checkpoints Available for Download and Review

By

–

31 October 2024 11h10

Check out the model checkpoints here:

Meta Releases MobileLLM: Depth Critical Over Width

By

–

31 October 2024 11h10

Meta released MobileLLM – 125M, 350M, 600M, 1B model checkpoints! Notes on the release: Depth vs. Width: Contrary to the scaling law (Kaplan et al., 2020), depth is more critical than width for small LLMs, enhancing abstract concept capture and final performance Embedding