LLM Reference

Dolly Models by Databricks Mosaic

1 model2023Up to 2k ctx

About

The Dolly family of large language models (LLMs), developed by Databricks, includes notable models like Dolly v1 and Dolly v2. Dolly v1, based on EleutherAI's GPT-J with 6 billion parameters, showcased that older, open-source models can exhibit strong instruction-following capabilities with limited fine-tuning on a high-quality dataset 248. Initially, its commercial use was limited by the licensing of its training data 48. To overcome this, Dolly v2 introduced a new dataset, "databricks-dolly-15k," which allows for both research and commercial utilization, and includes a model with 12 billion parameters based on EleutherAI's Pythia-12b 13. The Dolly models are engineered to comprehend and execute instructions articulated in natural language. Although they may not match the cutting-edge models in terms of performance, they provide an economical and versatile solution for entities aspiring to develop customized LLMs 212.

Current Variants

Use-when guidance is derived from seed capabilities, context, release, and replacement fields.

1 in view
Dolly 1.6BCurrent

Use when the workload needs 2k context and 1.6B parameters.

2023-032k context1.6B parameters

Release Timeline

1 release group
2023-03
1 current
Dolly 1.6B
2k context1.6B parameters
Current

Specifications(1 models)

Dolly model specifications comparison
ModelReleasedContextParameters
Dolly 1.6B2023-032k1.6b

Frequently Asked Questions

What is Dolly used for?
Dolly is used for chatbot and role-playing use cases. The family description and listed model capabilities point to those workloads as the best fit.
How does Dolly compare to MPT?
Dolly by Databricks Mosaic is strongest where you need chatbot and role-playing use cases, while MPT by Databricks Mosaic is the closest related family to check for coding. Dolly has 1 listed variant and reaches up to 2k context, while MPT reaches up to 8k context, so compare the specs and pricing tables before choosing a production model.
Which Dolly model should I use?
If price is the main constraint, use the pricing table first because Dolly does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Dolly 1.6B with 2k context.

Models(1)