Viewing profile — stonebraker

One commit at a time, we are keeping multimodal document understanding, parsing, and information extraction free under a permissive license. If you like the idea, or if something i…

Nice! This should be helpful. https://github.com/oidlabs-com/Lexoid?tab=readme-ov-file#ben...

True, but the cost for other models will continue to go down as well.

recently, started using rye. Convenient for sure.

Blog: https://medium.com/the-story-within/state-of-text-to-sql-dc3...

Might also be worth scanning, Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies https://arxiv.org/abs/2308.03188

I guess for self-evaluation and generation, we might want to choose a model that's performant for the job. This means that if the 70B is fine-tuned, that is probably the judge + au…

Thanks

So you would rather connect to a databricks lake from a privately hosted jupyterhub if that's an option?

I wonder if this is a common scenario to save costs across different cloud vendors. e.g. https://learn.microsoft.com/en-us/azure/databricks/dev-tools/databricks-connect/python/jupy…

Interesting

With the latest LLMs/codex improvements, the quality of SQL generation has improved but how do folks feel about the idea in-general? - Is it an overkill? - Will it be helpful such …

Has anyone compared performance between LLaMa.cpp vs Alpaca.cpp?

this is awesome. great work :)

I have a need to do HTTP load testing. Going through the web realized split in opinion in-regards to the right tool. Have narrowed down my focus to 2 vegeta and JMeter. Before i do…

Great intro on the topic using pymc package