imodelsx

We have hosted the application imodelsx in order to run this application in our online workstations with Wine or directly.

Quick description about imodelsx:

Interpretable prompting and models for NLP (using large language models). Generates a prompt that explains patterns in data (Official) Explain the difference between two distributions. Find a natural-language prompt using input-gradients. Fit a better linear model using an LLM to extract embeddings. Fit better decision trees using an LLM to expand features. Finetune a single linear layer on top of LLM embeddings. Use these just a like a sci-kit-learn model. During training, they fit better features via LLMs, but at test-time, they are extremely fast and completely transparent.

Features:

• Linear finetune
• Easy-to-fit baseline that follows the same API
• Aug-models
• D3 (DescribeDistributionalDifferences)
• Demos available
• Research paper and reference code

Programming Language: Python.
Categories: