LLaMA-NAS: Efficient Neural Architecture Search for Large Language Models.
Anthony SarahSharath Nittur SridharMaciej SzankinSairam SundaresanPublished in: CoRR (2024)
Keyphrases
- language model
- neural architecture
- language modeling
- n gram
- statistical language models
- probabilistic model
- information retrieval
- query expansion
- speech recognition
- language modelling
- test collection
- retrieval model
- query specific
- document ranking
- search space
- relevance model
- neural network
- genetic algorithm
- activation function
- parallel computing
- computing systems
- multilayer perceptron
- feed forward
- user queries
- support vector machine
- document collections