Download
kaleidoscope-sdk is a Python module used to interact with large language models hosted via the Kaleidoscope service available at: https://github.com/VectorInstitute/kaleidoscope. It provides a simple interface to launch LLMs on an HPC cluster, asking them to perform basic features like text generation, but also retrieve intermediate information from inside the model, such as log probabilities and activations. Users must authenticate using their Vector Institute cluster credentials. This can be done interactively instantiating a client object. This will generate an authentication token that will be used for all subsequent requests. The token will expire after 30 days, at which point the user will be prompted to re-authenticate.
Features
- Shows a list of all active LLMs instantiated by the model service
- Loads an LLM via the model service
- Returns an LLM text generation based on prompt input
- Returns all modules names in the LLM neural network
- Retrieves all activations for a set of modules
- Requires Python version >= 3.8
Project Samples
