Fine-Tuning vs. Frozen Embeddings: When to Adapt the LLM vs. the Sklearn Head
Summary
The article weighs two ways to adapt a model to a domain — LoRA fine-tuning versus frozen embeddings with only the sklearn head trained — and shows how to choose by scenario.
Why this matters
Covers model and LLM · Relevant to this topic
Source: Machine Learning Mastery · machinelearningmastery.com