Large Language Models
22 views
GGUF
Quick Definition
File format for LLMs optimized for local inference
Full Definition
GPT-Generated Unified Format, a file format for LLMs optimized for local CPU/GPU inference.
Examples
llama.cpp, local AI, quantized model distribution
Related Terms
quantization
llama
local-inference
More Large Language Models Terms
LoRA
Parameter-efficient fine-tuning using low-rank matrix decomposition
Guardrails LLM
Frameworks for monitoring and controlling LLM I/O
Pre-training
Initial training learning general language patterns from text
Mixture of Experts
Architecture routing tokens to specialized expert sub-networks
DPO
Alignment method bypassing reward model for preference learning
BPE
Subword tokenization algorithm merging frequent character pairs