Results for "instruction tuning"

Fine-tuning on (prompt, response) pairs to align a model with instruction-following behaviors.

Techniques that fine-tune small additional components rather than all weights to reduce compute and storage.

Updating a pretrained model’s weights on task-specific data to improve performance or adapt style/behavior.

Task instruction without examples.

A high-priority instruction layer setting overarching behavior constraints for a chat model.

PEFT method injecting trainable low-rank matrices into layers, enabling efficient fine-tuning.

Automated detection/prevention of disallowed outputs (toxicity, self-harm, illegal instruction, etc.).

One example included to guide output.

Multiple examples included in prompt.

Controlling robots via language.

Reusing knowledge from a source task/domain to improve learning on a target task/domain, typically via pretrained models.

A high-capacity language model trained on massive corpora, exhibiting broad generalization and emergent behaviors.

Ensuring model behavior matches human goals, norms, and constraints, including reducing harmful or deceptive outputs.

Practices for operationalizing ML: versioning, CI/CD, monitoring, retraining, and reliable production management.

Automated testing and deployment processes for models and data workflows, extending DevOps to ML artifacts.

Removing weights or neurons to shrink models and improve efficiency; can be structured or unstructured.

End-to-end process for model training.