Revolutionizing Language Models
Arcee's Domain Adaptation Kit, powered by MergeKit, enables the training of a smaller language model, which can then be seamlessly merged with a larger model. This innovative approach not only yields significant cost savings and efficiency but also ensures unparalleled scalability and performance
Merge established models with your own trained model for enhanced power
Frequently Asked Questions
All your top questions about MergeKit, answered here.
MergeKit is a great tool for combining the strengths of multiple language models. With MergeKit, you can train a model on just the data that matters to you, and add the capabilities of cutting edge open source models without further training. This brings the benefits of efficiency, cost savings and reduces complexity in your LLM pipeline.
MergeKit supports most decoder-only language models implemented in the transformers library. MergeKit features first-class support for Llama, Mistral, Phi-2, StableLM, GPT-NeoX, Mixtral, and many more.
Yes, MergeKit will remain open source and we will be extending and expanding it to be the most powerful toolkit in the world for model merging.
MergeKit is utilized under the hood of the Arcee product in our Adaptation and Alignment layers.
Absolutely, you can go to the examples folder in the repo for a variety of examples.
The easiest way to get started with model merging and MergeKit is to follow the open source repo guide to installation and getting started.
Train, deploy, and continuously maintain your AI for any use case
Thanks to the domain adaptability of our product, you can efficiently train and deploy your own SLMs across a plethora of use cases, whether it is for internal tooling, or for your customers.
Healthcare
Learn how Arcee's end-to-end adaptation system can help you build specialized LLMs for healthcare.
Finance
Learn how Arcee's end-to-end adaptation system can help you build specialized LLMs for finance.
Legal
Learn how Arcee's end-to-end adaptation system can help you build your own language models across your legal function.
Insurance
Learn how Arcee's end-to-end adaptation system can help you build specialized LLMs for insurance.
Start building your SLMsĀ today
Book a call with our team to discuss how Arcee can help you train, deploy, maintain, and continuously improve your smaller, secure, specialized, and scalable language models.