Large Language Models
371 views
Model Merging
Quick Definition
Combining fine-tuned LLMs without additional training
Full Definition
Combining multiple fine-tuned LLMs into a single model without additional training.
Examples
model soup, weight merging, multi-task models
Related Terms
fine-tuning
ensemble
More Large Language Models Terms
Context Window
Maximum tokens a language model can process at once
Prompt Template
Reusable structured format with dynamic input placeholders
Quantization LLM
Reducing LLM weight precision for efficient inference
Prompt Caching
Storing key-value states for repeated prompt prefixes
Grounding LLM
Connecting LLM outputs to verifiable external sources
DPO
Alignment method bypassing reward model for preference learning