If you’re using out of the box LLMs as a reward model/sample rater, here’s a trick to get way better performance: Don’t ask the LLM to rate examples on a numerical scale (i.e. 1-5). The model will almost always choose 1 or 5. Instead, use words as rating options (“very bad”,
AI
-
Free Sidney Movement Transcends Avantgarde into Gnostic Elite
By
–
The Free Sidney movement is getting close; it has moved beyond avantgarde art and is now forming a gnostic elite
-
Axolotl and Together Compute for Model Fine-tuning
By
–
I use Axolotl, but services like @togethercompute might be easier. Last I checked, they don’t support only training on outputs, which is important. May have changed since!
-
Fine-tuning LLMs: Progressive Data Selection Strategy
By
–
High alpha technique for fine-tuning LLMs: First, fine-tune your model on all your data Then, use AI to pick a smaller set of really good examples, and tune on them Finally, hand-pick and tune on a few hundred incredible examples >> Huge performance gains <<
-

Building RAG Systems for Powerful Data Access
By
–
How to Make a RAG System to Gain Powerful Access to Your Data This article is a great introduction to RAG, and walks through a few important steps of a RAG pipeline: Retrieve Data
Pre-process Data
Implement RAG
Test https://
towardsdatascience.com/how-to-make-a-
rag-system-to-gain-powerful-access-to-your-data-caf4bb9186ea
… -
That’s a Wrap: Daily Python, Data Science, and ML Content
By
–
That's a wrap! Every day, I share and simply content around Python, Data Science, Machine Learning & Large Language Models. Find me → @Sumanth_077 Like/RT the first tweet and help this reach more people.
-
AI Integration Simplifies MLOps and ETL Pipeline Complexity
By
–
By bringing AI directly to data developers and organizations can avoid the complexity of building and integrating MLOps and ETL pipelines as well as migrating and duplicating data across multiple environments. Check this out: https://
superduperdb.com -

SuperDuperDB Simplifies AI Integration Without Data Migration
By
–
@SuperDuperDB eliminates complex MLOps pipelines, specialized vector databases – and the need to migrate and duplicate data by integrating AI at the data’s source, directly on top of your existing data infrastructure. This simplifies building and managing AI applications.
-

SuperDuperDB: Open-Source Framework for AI-Powered Database Applications
By
–
Bringing AI into your Databases!
— Sumanth (@Sumanth_077) 23 mars 2024
Introducing SuperDuperDB an open-source framework for building AI Applications right in your databases. pic.twitter.com/MOE2cQsG0RBringing AI into your Databases! Introducing SuperDuperDB an open-source framework for building AI Applications right in your databases.
-
Comcast Enhances Voice Interfaces with Data-Centric AI
By
–
Jan Neumann, Vice President, Machine Learning at Comcast Applied AI and Discovery, offers a deep dive into how Comcast is leveraging data-centric AI to enhance their voice and conversational interfaces, making them more intuitive and user-friendly.