TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.
After reading the API, I believe I cannot do post-training model compression, as for example I would do with a model implemented in Keras, where I would have access to each and every layer of the model - which I understand why this is the case.
So, I would like to ask if, in the spirit of Google Gemini, TimeGPT has (or plans to) have a Nano version? For example Gemini has Ultra, Pro and Nano versions.
After reading the API, I believe I cannot do post-training model compression, as for example I would do with a model implemented in Keras, where I would have access to each and every layer of the model - which I understand why this is the case.
So, I would like to ask if, in the spirit of Google Gemini, TimeGPT has (or plans to) have a Nano version? For example Gemini has Ultra, Pro and Nano versions.