Large Language Models
192 views
Instruction Tuning
Quick Definition
Fine-tuning on instruction-response pairs for better following
Full Definition
Fine-tuning models on instruction-response pairs to improve instruction following ability.
Examples
chatbot training, assistant development, task alignment
Related Terms
fine-tuning
rlhf
alignment
More Large Language Models Terms
Quantization LLM
Reducing LLM weight precision for efficient inference
LoRA
Parameter-efficient fine-tuning using low-rank matrix decomposition
RLHF
Aligning LLMs with human preferences using reinforcement learning
Top-K Sampling
Generation strategy considering top k most probable tokens
Tree-of-Thought
Framework exploring multiple reasoning paths for optimal solutions
WordPiece
Subword tokenization splitting words into frequent units