Fine-Tuning
Quick Definition
Further training pre-trained models on specific domain data
Full Definition
Further training a pre-trained language model on domain-specific or task-specific data.
Examples
domain adaptation, instruction tuning, task specialization
Related Terms
transfer-learning
lora
pre-training
More Large Language Models Terms
Semantic Search
Search technique understanding meaning rather than keywords
Training LLM
Adjusting parameters on large datasets to learn language
Sliding Window Attention
Attention limiting tokens to nearby window only
Structured Output
Generating LLM responses in predefined machine-readable formats
Sparse Attention
Attention attending to only a subset of tokens
Nucleus Sampling
Generation using cumulative probability threshold for token selection