Guanaco vs. Phi

Overview

Guanaco is an LLM based off the QLoRA 4-bit finetuning method developed by Tim Dettmers et. al. in the UW NLP group. Guanaco achieves 99% ChatGPT performance on the Vicuna benchmark.

Guanaco is an LLM that uses a finetuning method called LoRA that was developed by Tim Dettmers et. al. in the UW NLP group. With QLoRA, it becomes possible to finetune up to a 65B parameter model on a 48GB GPU without loss of performance relative to a 16-bit model. The Guanaco model family outperforms all previously released models on the Vicuna benchmark. However, given the models are based off of the LLaMA model family, commercial use is not permitted.

Initial release: 2023-05-23

Reference

https://github.com/artidoro/qlora

Further Reading

• https://arxiv.org/abs/2305.14314
• https://twitter.com/Tim_Dettmers/status/1661379354507476994

Overview

Phi is a series of compact language models developed by Microsoft using textbooks and synthetic data.

Phi-1 and Phi-2 are 1.3B and 2.7B parameter language models, respectively, developed by Microsoft to demonstrate the ability of smaller language models trained on high-quality data. Despite its size and not having an instruct finetuned counterpart, the Phi-2 model is well-suited to research and experimentation given its size and MIT license.

Initial release: 2023-06-20

Reference

https://ai.azure.com/explore/models/microsoft-phi-2/version/4/registry/azureml-msr

Further Reading

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