BTLM-3B-8K: 7B Parameter Performance in a 3B Parameter Model.
Nolan DeyDaria SobolevaFaisal Al-KhateebBowen YangRibhu PathriaHemant KhachaneShaheer MuhammadZhiming ChenRobert MyersJacob Robert SteevesNatalia VassilievaMarvin TomJoel HestnessPublished in: CoRR (2023)
Keyphrases
- parameter values
- high level
- linear model
- computational model
- parameter space
- mathematical model
- multi agent
- prior knowledge
- probabilistic model
- probability distribution
- statistical model
- management system
- prediction model
- neural network model
- theoretical analysis
- database
- support vector
- face recognition
- learning algorithm
- data sets