EvoMerge: Neuroevolution for Large Language Models
Extensive fine-tuning on Large Language Models does not always yield better results. Oftentimes, models tend to get better at imitating one form of data without gaining greater reasoning ability and may even end up losing some intelligence. Here I introduce EvoMerge, a systematic approach to large language model training and merging. Leveraging model merging for weight crossover and fine-tuning for weight mutation, EvoMerge establishes an evolutionary process aimed at pushing models beyond the limits of conventional fine-tuning.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingLarge Language ModelSimilar Papers 제목 키워드 기반
Neuroevolution with Perceptron Turing Machines
We introduce the perceptron Turing machine and show how it can be used to create a system of neuroevolution. Advantages of this approach include automatic scaling of solutions to larger problem sizes, the ability to expe…
Low Rank Factorizations are Indirect Encodings for Deep Neuroevolution
Deep neuroevolution is a highly scalable alternative to reinforcement learning due to its unique ability to encode network updates in a small number of bytes. Recent insights from traditional deep learning indicate high-…
Language ModelingLanguage Modellingreinforcement-learningReinforcement LearningVINE: An Open Source Interactive Data Visualization Tool for Neuroevolution
Recent advances in deep neuroevolution have demonstrated that evolutionary algorithms, such as evolution strategies (ES) and genetic algorithms (GA), can scale to train deep neural networks to solve difficult reinforceme…
Data VisualizationEvolutionary AlgorithmsReinforcement LearningReinforcement Learning (RL)Provably Sub-Linear Two-Timescale NeuroEvolution with Online Plasticity
NeuroEvolution of Augmenting Topologies (NEAT) is a widely used neuroevolution algorithm for learning neural network architectures and weights for control tasks. However, standard offline optimisation searches for connec…
Reinforcement LearningContinuous ControlNeuroevolutionary Multi-objective approaches to Trajectory Prediction in Autonomous Vehicles
The incentive for using Evolutionary Algorithms (EAs) for the automated optimization and training of deep neural networks (DNNs), a process referred to as neuroevolution, has gained momentum in recent years. The configur…
Autonomous VehiclesEvolutionary AlgorithmsTrajectory Prediction