LLM-Finetuning-Toolkit VS LLM-Finetuning-Hub

Hi everyone, we've been working on benchmarking different open-source LLMs. We measure, in particular, on the performance of these models once finetued (via QLoRA) on classic NLP downstream tasks like summarization and classification. We also put particular emphasis on benchmarking inference time/cost for these models once deployed.

Hello all,

I have been working on benchmarking different LLMs -- both open-source and closed-source.

Repo: https://github.com/georgian-io/LLM-Finetuning-Hub

Precisely, I am comparing their out-of-the-box capabilities (prompting) and their fine-tuned conterparts!

So far, the following models have been benchmarked:

Open-Source:

- Finetuning with QLoRA

I evaluate how Falcon does on classification tasks when compared to Bert and Distilbert.

Moreover, I talk about different ways you can deploy the model, and the associated costs!

The code for all of my experiments are available on: https://github.com/georgian-io/LLM-Finetuning-Hub

Happy reading and learning!