Dolly vs. Phi

Overview

Dolly is an LLM trained using the Databricks machine learning platform. Originally released without instruct-finetuning, Dolly v2 included tuning on the Stanford Alpaca dataset.

Initial release: 2023-03-24

Reference

https://www.databricks.com/blog/2023/04/12/dolly-first-open-commercially-viable-instruction-tuned-llm

Further Reading

Overview

Phi is Microsoft's family of compact open models designed for efficient local and edge deployment. Phi-4 is the current generation.

Microsoft introduced Phi-1 and Phi-2 to demonstrate how carefully curated and synthetic training data can make small models unusually capable. Phi-3 expanded the family for mobile and multimodal use. The Phi-4 generation includes a 14B general model and reasoning variants, plus smaller and multimodal checkpoints. Phi models are released under the MIT license and are designed for research, local inference, and resource-constrained production workloads.

Initial release: 2023-06-20

Current generation: Phi-4

Reference

https://azure.microsoft.com/en-us/products/phi

Further Reading

• https://huggingface.co/microsoft/phi-2
• https://arxiv.org/abs/2306.11644
• https://huggingface.co/microsoft/phi-4