Large Language Models
302 views
QLoRA
Quick Definition
Combining 4-bit quantization with LoRA for efficiency
Full Definition
Combining 4-bit quantization with LoRA for memory-efficient fine-tuning of large models.
Examples
consumer GPU fine-tuning, large model adaptation
Related Terms
lora
quantization
fine-tuning
More Large Language Models Terms
Prompt Caching
Storing key-value states for repeated prompt prefixes
DPO
Alignment method bypassing reward model for preference learning
Grounded Generation
Generating outputs faithful to provided source documents
Guardrails LLM
Frameworks for monitoring and controlling LLM I/O
RoPE
Position encoding using rotation matrices for relative positions
Tree-of-Thought
Framework exploring multiple reasoning paths for optimal solutions