Arcee Blog

Adapting an LLM to a specific domain might sound straightforward, but it in fact opens a Pandora's box of challenges. Our research team explains the shortfalls of some of the most common techniques.

Looking for proof that Small is the new Big when it comes to language models? Look no further than the model we've just dropped here at Arcee AI: you get top-notch results with just 7B parameters.

We built Llama-3-SEC upon the powerful Meta-Llama-3-70B-Instruct model, with the goal of providing unparalleled insights and analysis capabilities for financial professionals, investors, researchers, and anyone working with SEC filings and related financial data.

We’re thrilled to announce that we’re launching Arcee Cloud, a fully hosted SaaS offering that makes world-class LLM production accessible to all – in an easy-to-use platform for Training, Merging, and Deploying custom language models.

We show you how to use Arcee's MergeKit to extract LoRA adapters from fine-tuned models, then leverage the Hugging Face Hub to create a library of general and task-specific LoRA adapters.

We've been focused on developing this groundbreaking technique for the community, and we're now excited to announce the launch of this state-of-the-art functionality in MergeKit.

Arcee's research shows that the Standard Continual Pre-Training (CPT) approach performs better than QLORA-based CPT.

And what do we do at Arcee when an exciting new model drops? We MERGE IT on MergeKit! We walk you through the process and share the initial results.

Arcee & MergeKit advance model merging innovations with launch of MergeKit Hackathon, co-sponsored by AWS. Submit your model merging research, experiments, and results for the chance to win cash prizes!