He is still constantly learning and sharing. Aleksa even recently did a 30-day coding live streaming working on replicating Meta's NLLB (No Language Left Behind approach)
TOOLS
-
Using Midjourney GenAI to Envision and Create Wonderful Futures
By
–
Using Midjourney or other GenAI tools to envision a future where we actually make wonderful things happen is something I just love doing. And now you can do it too. Happy prompting.
-
70B LLM Inference Optimization in Kaggle Competitions
By
–
Yes exactly that – although it's particularly used by Kagglers in competitions, since many of them *require* using Kaggle's infra. In a recent competition one person got 70B inference running in 14GB RAM! :O
-
Generative AI Customer Service Solutions at SC23 Booth
By
–
Stop by booth #1681 at @Supercomputing to explore the transformative power of #GenerativeAI with live demonstrations of AI-driven customer service solutions. #SC23
-
Midjourney Legacy URL Alternative Access Solution
By
–
Try using https://
legacy.midjourney.com for now -
WANT Workshop Trains Neural Networks at Scale
By
–
(2/2) The WANT workshop provides researchers with the tools to train neural networks at scale. It will provide an interactive platform for researchers and practitioners to delve into the latest advancements in neural network training Learn more here: https://
want-ai-hpc.github.io -
MetaGPT: AI Evolution from Queries to Autonomous Task Agents
By
–
Observe AI's progress from simple text processing to artificial agents like ChatGPT interacting with different apps. MetaGPT is a new idea where AI performs tasks, not just queries, serving as a digital assistant for tasks from content creation to software manipulation.
-
LangChain Templates README Instructions on GitHub
By
–
https://
github.com/langchain-ai/l
angchain/blob/master/templates/README.md
… instructions here -
Domino’s Fall ’23: AI Project Hub and Responsible Development
By
–
Domino's Fall '23 release: Accelerate AI projects with AI Project Hub, code swiftly with Jupyter AI, and enhance data governance. Faster, easier, responsible AI development awaits! Learn More https://
domino.buzz/3FALsBe #DataScience #ResponsibleAI #DataGovernance -
MLflow 2.8 Introduces LLM-as-Judge Metrics for RAG
By
–
This just in: MLflow 2.8 supports our LLM-as-a-judge metrics. Discover how to use LLM-as-a-judge best practices and methodology to evaluate your RAG applications quickly and efficiently