Rubra
Click to visit website
About
Rubra is a collection of open-weight large language models (LLMs) that have been enhanced to support tool-calling capability. This allows Rubra models to interact with user-defined external tools in a deterministic manner, making them ideal for complex, agentic use cases. These models are built from top open-source LLMs and undergo further training to teach them new skills while minimizing catastrophic forgetting. Rubra models offer various enhanced capabilities, including the ability to perform complex multi-step function calls. The tool also provides local inferencing options and welcomes contributions from the community to improve its functionality further.
Platform
Task
Features
• local inferencing support
• post-training techniques to mitigate forgetting
• enhanced complex function calls
• tool-calling capability
• open-weight llms
FAQs
Who are the intended users of Rubra?
Rubra models are for anyone looking to use open source LLMs with native function calling support.
Why use Rubra models over other fine-tunes?
Rubra models excel in both chat and complex function calling compared to models like Hermes Pro or Gorilla OpenFunctions.
How were Rubra models trained?
Rubra models were trained using a high-quality tool calling dataset curated from millions of conversations and tool calls.
Why do benchmark results differ from parent model cards?
Benchmark tools are constantly evolving, which may lead to variations in results compared to parent models.
How did you construct the training set for Rubra models?
The training set was created using a phrase called 'chain of function' to integrate LLMs with user-defined tools.
Average Rating: 0.0
Average Rating: 0.0
5 Stars:
0 Ratings
4 Stars:
0 Ratings
3 Stars:
0 Ratings
2 Stars:
0 Ratings
1 Star:
0 Ratings
User Ratings
No ratings available.
Sign In to Rate this Tool
Featured Tools
Scalytics Connect
A federated AI framework that integrates decentralized data sources for AI development.
View Details
WhyHow.AI
Transform unstructured data into structured knowledge for accurate AI solutions.
View Details