From 040fc3c221aadd9157f6307a51b47dd86cac25de Mon Sep 17 00:00:00 2001 From: Maram Hasanain Date: Sun, 17 Sep 2023 12:34:34 +0300 Subject: [PATCH] Update README.md Added disclaimer on data download license --- README.md | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index e714dc15..53287831 100644 --- a/README.md +++ b/README.md @@ -1,6 +1,6 @@ # LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking -This repository contains code for the [LLMeBench framework](https://youtu.be/FkQn4UjYA0s?feature=shared) (described in this paper). The framework currently supports evaluation of a variety of NLP tasks using **three** model providers: OpenAI (e.g., [GPT](https://platform.openai.com/docs/guides/gpt)), [HuggingFace Inference API](https://huggingface.co/docs/api-inference/), and Petals (e.g., [BLOOMZ](https://huggingface.co/bigscience/bloomz)); it can be seamlessly customized for any NLP task, LLM model and dataset, regardless of language. +This repository contains code for the LLMeBench framework (described in this paper). The framework currently supports evaluation of a variety of NLP tasks using **three** model providers: OpenAI (e.g., [GPT](https://platform.openai.com/docs/guides/gpt)), [HuggingFace Inference API](https://huggingface.co/docs/api-inference/), and Petals (e.g., [BLOOMZ](https://huggingface.co/bigscience/bloomz)); it can be seamlessly customized for any NLP task, LLM model and dataset, regardless of language. @@ -73,6 +73,8 @@ sequence_tagging_ner_pos_etc speech ``` +**Disclaimer:** The datasets associated with the current version of LLMeBench are either existing datasets or processed versions of them. We refer users to the original license accompanying each dataset as provided in the metadata for [each dataset script](https://github.com/qcri/LLMeBench/tree/main/llmebench/datasets). It is our understanding that these licenses allow for their use and redistribution for research or non-commercial purposes . + ## Usage To run the benchmark,