MACHINE LEARNING

–

05 August 2023 19h51

NN + Gzip because we got bored waiting https://
magazine.sebastianraschka.com/p/large-langua
ge-models-and-nearest
…

Foundation math textbooks and advanced ML AI resources

By

–

05 August 2023 19h48

Depends on your background and interests. Math textbooks are usually a good foundation for most technical fields.
Shameless plug: if you are into ML and AI and want to pick up some more advanced concepts after an intro book, my ML Q & AI might be useful:

→ View original post on X — @databricks

Lakehouse Monitoring: Unified Data and ML Asset Quality Control

By

@databricks

–

05 August 2023 19h43

#Lakehouse Monitoring offers a unified service to monitor the quality of your data and #ML assets. Check out this demo to learn how to: Diagnose errors in your projects Set up a monitor with low friction Enable self-serve experiences & more https://
bit.ly/44Si3xa

→ View original post on X — @hwchase17

Improving Question Answering Systems for Tabular Data

By

@hwchase17

–

05 August 2023 19h13

CSV Question Answering Most QA applications deal with asking questions of unstructured data. But a lot of data is in tabular (excel, csv) format! This has always been tricky to get right. We want to improve that! But we need your help

Comparison of decoder models with ChatGPT and GPT-4 after RLHF

By

–

05 August 2023 19h01

! I’m mainly curious how it compared to decoders like ChatGPT or GPT-4 after RHLF

Comparing Decoder-Only Models to Encoder-Decoder Architectures for Translation

By

–

05 August 2023 18h55

The original transformer is an encoder-decoder arch for translation. T5 is a great encoder-encoder that’s pretty good at translation. ChatGPT / GPT-4 is a decoder-only that’s pretty good at translation too. How does it compare to encoder-decoder architectures of similar size?

Clarification on inference versus pretraining data requirements

By

–

05 August 2023 18h30

You mean during inference or regarding amount of data needed for pretraining?

Encoder-Decoder vs Decoder-Only Architecture Training Efficiency

By

–

05 August 2023 18h28

You mean, assuming that both an encoder-decoder and a decoder-only architecture, the encoder-decoder is easier to train because you make better use of the data due to the masking pretraining tasks?

Encoder vs Decoder LLMs: Benefits for Seq2Seq Tasks

By

–

05 August 2023 18h20

Use cases for encoder LLMs (classification) & decoder LLMs (chatbots) are obvious. Seq2seq tasks like translation, where it makes sense to have access to the whole input, is where it gets interesting.
Re encoder-decoder LLMs (eg T5): Is there still a benefit of using an encoder?