Efficient Model Training

Discover how Lora drastically reduces the number of trainable parameters in large language models, making training more efficient and accessible. With the introduction of Ada Lora, fine-tuning becomes even smarter by targeting specific parts of the model architecture. This episode highlights innovative tools that are transforming the landscape for data scientists, making it an exhilarating time to be in the field.

In this clip
From this podcast
Super Data Science: ML & AI Podcast with Jon Krohn
674: Parameter-Efficient Fine-Tuning of LLMs using LoRA (Low-Rank Adaptation) — with Jon Krohn
Related Questions
- How are large language models (LLMs) trained, as discussed in the episode 670: LLaMA: GPT-3 performance, 10x smaller — with Jon Krohn (@JonKrohnLearns) ?
- Should models have more parameters, as discussed in the episode ThursdAI Aug 24 - Seamless Voice Model, LLaMa Code, GPT3.5 FineTune API & IDEFICS vision model from HF and the clip Quantization and Model Size?

Efficient Model Training

In this clip

From this podcast

Super Data Science: ML & AI Podcast with Jon Krohn

674: Parameter-Efficient Fine-Tuning of LLMs using LoRA (Low-Rank Adaptation) — with Jon Krohn

Related Questions

How are large language models (LLMs) trained, as discussed in the episode 670: LLaMA: GPT-3 performance, 10x smaller — with Jon Krohn (@JonKrohnLearns) ?

Should models have more parameters, as discussed in the episode ThursdAI Aug 24 - Seamless Voice Model, LLaMa Code, GPT3.5 FineTune API & IDEFICS vision model from HF and the clip Quantization and Model Size?