Assets Overview in aiXplain

Modified on Fri, Oct 13, 2023 at 7:13 AM

This article provides an overview of how to manage and utilize assets within your workspace. Assets encompass subscribed models, collected models, and the process of comparing and benchmarking them.


Asset types

Assets are the building blocks of aiXplain's platform. They are the components that enable you to create, explore, and optimize content using various tools and services. There are six types of assets that you can use in aiXplain:


Corpus

A corpus is a collection of texts that are related to a specific topic or domain. A corpus can be used to train or fine-tune models, or to generate new content using natural language processing techniques.


Dataset

A dataset is a collection of data points that are structured in a table or a hierarchy. A dataset can be used for training or testing models, or for doing data analysis using machine learning approaches.


Benchmark

A benchmark is a set of criteria or metrics that are used to evaluate the performance or quality of a model. A benchmark can be used to compare different models against each other or just for a specific model.


Model

A model is a computational algorithm that has been trained on a set of data to perform specific tasks or functions. A model can be used to generate, transform, or analyze content using artificial intelligence methods.


Pipeline

A pipeline is a sequence of steps or operations that are applied to an input to produce an output. A pipeline can be used to automate workflows or to combine different models or tools to create complex functionalities.


File

A file is a document or an image that contains information or data. A file can be used as an input or an output for various tools or services, or to store and share content.


Subscribing to models

To integrate models into your workflow, you can subscribe to them. Subscribing to a model allows you to bookmark a model for later use. 


The models are then saved into your assets via the dashboard. 


To subscribe to a model, follow these steps:


  • Choose a model.
  • Select “Subscribe”.


You would then visit the ‘Dashboard’ to view your saved models.



Accessing subscribed models

Subscribed models can be accessed through your team's Dashboard. This centralized location provides an overview of your subscribed models, enabling easy access and management.


To access subscribed models:

  1. Navigate to your team's Dashboard.
  2. Locate the section dedicated to subscribed models.
  3. Explore and manage your subscribed models from this interface.


Dashboard:



To unsubscribe from a model, you can click on the “Subscribed”. 


Collecting models for asset drawer

The asset drawer is a crucial component of aiXplain's toolbox. It allows you to collect different assets, making them readily available for use with aiXplain's tools.


To collect models for the asset drawer:

Click “Collect” on the model you want collecting


You can then bring the collected models into various toolkits on the platform, such as Benchmark, FineTune or Design.


Comparing models

Comparing models is a useful feature that allows you to evaluate and contrast the performance of different models on a given task or dataset. Comparing models can help you select the best model for your needs or identify areas of improvement for your existing models. To compare models, follow these steps:


  1. First, Collect the models that you want to compare using the asset drawer.
  2. Select "Compare models".
  3. Type your data or upload a dataset that you want to use for comparison.
  4. Click "Compare models" to start the comparison process.
  5. View and analyze the results of the comparison, such as accuracy, speed, and quality.




I hope this article has proven to be both helpful and informative for you. We greatly appreciate your decision to select aiXplain as your AI creation and optimization partner. Should you have any inquiries or feedback, please don't hesitate to reach out to us at your convenience.


Contact us at support@aixplain.com.


Was this article helpful?

That’s Great!

Thank you for your feedback

Sorry! We couldn't be helpful

Thank you for your feedback

Let us know how can we improve this article!

Select at least one of the reasons
CAPTCHA verification is required.

Feedback sent

We appreciate your effort and will try to fix the article