LLM: Guanaco

Developer

UW NLP

Genealogy

LLaMA → Guanaco

Initial Release

2023-05-23

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.

Description

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.

Open Source

Yes

Instruct Tuned

Yes

Model Sizes

7B, 13B, 33B, 65B

Finetuning

Yes

License

Noncommercial

Pricing

-

Link

Visit

Further Reading

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

Unsure? Contact us with a brief description of your use case if you'd like for us to make a snap assessment. Depending on your requirements, a smaller, custom language model may even be the best option.