Results for "instruction tuning"
SFT
Intermediate
Fine-tuning on (prompt, response) pairs to align a model with instruction-following behaviors.
LoRA
Intermediate
PEFT method injecting trainable low-rank matrices into layers, enabling efficient fine-tuning.
System Prompt
Intermediate
A high-priority instruction layer setting overarching behavior constraints for a chat model.
Safety Filter
Intermediate
Automated detection/prevention of disallowed outputs (toxicity, self-harm, illegal instruction, etc.).
Zero-Shot Prompting
Intro
Task instruction without examples.
Fine-Tuning
Intermediate
Updating a pretrained model’s weights on task-specific data to improve performance or adapt style/behavior.
Parameter-Efficient Fine-Tuning
Intermediate
Techniques that fine-tune small additional components rather than all weights to reduce compute and storage.
Natural Language Instruction
Frontier
Controlling robots via language.