LoRA
1 creator use or recommend it
Low-Rank Adaptation - a technique for efficiently fine-tuning large language models by training only small adapter layers.
Recently discussed in
What creators say
"I started playing around with LoRA. I think LoRA at lower ranks for lower amounts of sample size actually does impressively well"
More from Y Combinator →"Legal is like a really interesting example. Bessemer has been a longtime investor in Lora, which is like a great example of this. And I think they're still very early actually in this transition towards what's possible... in a lot of use cases, Lo..."
More from Talia Goldberg →"If you're a lawyer and you're talking to your main assistant about legal things, it's immediately just talking to Lora, right? Because that might be your work agent if you're a lawyer, because there's a bunch of like data privacy and privilege and..."
More from Jean-Denis Grèze →
"For the character training thing, I think this research is built on fine-tuning about 7 billion parameter models with LoRA, which is essentially only fine-tuning a small subset of the weights of the model."
More from Sebastian Raschka →Created by
"We built every single functionality in Lora as a boat and when the tide rises, everything improves. What's interesting now compared to 3 years ago is that different models are good at different things. So if you break down legal work, there's so m..."
More from Max Junestrand →Keep exploring
About this data
- ✓44,000+ mentions extracted from real podcast transcripts
- ✓Every quote links to the source episode
- ✓Sponsored mentions are always labeled
- ✓Critical takes are shown, never filtered out