LLMS

→ View original post on X — @jiqizhixin

Microsoft LLM-Augmenter Reduces ChatGPT Hallucinations Improves Factual Accuracy

By

@jiqizhixin

–

02 March 2023 22h00

Tackling Hallucinations: Microsoft’s LLM-Augmenter Boosts ChatGPT’s Factual Answer Score

C4 Pretraining Limits in Base Model Development

By

–

02 March 2023 20h45

We might be hitting limits of the c4 pretraining that the base model uses as well.

Flan-PaLM 62B Model Shows Modest Performance Improvements

By

–

02 March 2023 20h44

Good point. It's a modest boost. When you take into account Flan-PaLM 62b results, this falls within expectation. It's modest. We didn't expect game changing results from this model either. We just give folks the option to squeeze a little more quality if they could afford to.

→ View original post on X — @predibase

Fine-tune Foundation Models on Your Data with Predibase and Ludwig

By

@predibase

–

02 March 2023 20h16

Want to tune a #FoundationModel on your own data without sending it to a vendor?

With Predibase and #opensource @ludwig_ai, tuning #LargeLanguageModels is as easy as changing a few lines in a config file.

Request a demo to learn more: https://t.co/B0edFxmICc #DeepLearning #GPT pic.twitter.com/PyDvI1A1RJ
— Predibase by Rubrik (@predibase) 2 mars 2023

Want to tune a #FoundationModel on your own data without sending it to a vendor? With Predibase and #opensource @ludwig_ai
, tuning #LargeLanguageModels is as easy as changing a few lines in a config file. Request a demo to learn more: https://
lnkd.in/gTdE8gxh #DeepLearning #GPT

→ View original post on X — @rodneyabrooks

LLM Potential: From Lead to Gold Transmutation Success

By

@rodneyabrooks

–

02 March 2023 19h53

My take on LLM/CHATters. We're going to transmute lead to gold! Why now? We just pumped massive energy in and got Pb to turn to liquid. First time ever. It logically follows that soon we will have AgI(silver incalculable) and even AuI. We (my in group) are going to be RIIICCCHHH!

UL2 Model Now Available on Hugging Face

By

–

02 March 2023 19h52

The ul2 model is already on Huggingface. I don't know how HF works but it should be minimal work to make it available there. It's an identical model config to ul2 20b. Cc:
@huggingface

Flan Model Update Released Following Academic Industry Success

By

–

02 March 2023 19h23

With the great success of Flan on both academia/ industry, this update was long overdue! In fact, this was the "bonus model" that we had plan to release because the original tweet got > 1k likes. lol. but i got busy . @jeremyphoward @_jasonwei https://
x.com/quocleix/statu
s/1583523186376785921
…