Large Language Models
303 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
Masked Language Model
Training objective predicting randomly masked input tokens
Speculative Decoding
Using draft model candidates verified by large model
Streaming
Sending LLM tokens to clients as they are generated
Nucleus Sampling
Generation using cumulative probability threshold for token selection
Positional Encoding
Incorporating token position information into transformers
Prompt Template
Reusable structured format with dynamic input placeholders