Congratulations on the release! Very exciting to see the impressive RAG performance you're achieving built on Llama 3.3!
OPEN SOURCE
-
Hugging Face Smolagents Benchmark Examples Notebook
By
–
https://
github.com/huggingface/sm
olagents/blob/main/examples/benchmark.ipynb
… -
Abacus AI: Enterprise AI Platform for Fortune 500 Companies
By
–
Explore @AbacusAI — https://
abacus.ai An #AI Brain for your Organization Trusted by Fortune 500 companies Leader in open-source AGI Research State-of-the-Art end-to-end AI Platform Large-Scale AI Solution with Enterprise Class Security #LLMOps + #MLOps -
alphaXiv: Community-Curated Research Platform for ArXiv Papers
By
–
Goodreads for arXiv papers💡
— alphaXiv (@askalphaxiv) 15 janvier 2025
What if instead of arbitrary algorithms and tweets, arXiv papers were curated by your research community?
Introducing communities on alphaXiv: bridging papers, discussions, and people in one space. pic.twitter.com/1tpls6bEC6Goodreads for arXiv papers What if instead of arbitrary algorithms and tweets, arXiv papers were curated by your research community? Introducing communities on alphaXiv: bridging papers, discussions, and people in one space.
-
Open Source Projects, Conference Papers, and Top Kaggle Notebooks
By
–
Something like an open source project, a conference paper (with code), a top Kaggle notebook
-
Drupal Cache Bubbling: Automatic Caching Metadata Propagation
By
–
Ovanes Budakyan talks @drupal cache bubbling, the automatic propagation of caching metadata — including tags, contexts, and max-age — from smaller components to larger containers in his latest installment https://
bit.ly/3DgevMo #drupal #opensource #foss -
Llama 3, Inference Scaling, and Multimodal LLM Paradigms 2025
By
–
The TOC as a tl;dr
1. Of course, the Llama 3 series as one of the main open-weight model releases this year, featuring more sophisticated pre- and post-training pipelines
2. Techniques for improving LLMs by scaling inference-time compute
3. The different multimodal LLM paradigms -
GUI Setup for LoRA Trainer Tools
By
–
Ok maybe it’ll setup a GUI for you like some of the Lora trainers
-
GPU Optimization Performance Comparison FP8 Quantization Testing
By
–
Understood, testing now! I got your previous version working too and that seemed to be much faster on 2×3090 (fp8 part disabled) than the code above, not sure why yet…
-
Eko JavaScript Framework Enables Reliable Agent Development
By
–
Eko (pronounced like ‘echo’) is a production-ready JavaScript framework that enables developers to create reliable agents, from simple commands to complex workflows. It provides a unified interface for running agents in both computer and browser environments.