Spaces:
Running
Running
| LOGO = '<img src="https://nyunai.com/assets/images/logo.png">' | |
| TITLE = """<h1 align="center" id="space-title"> Edge-LLM Leaderboard </h1>""" | |
| ABOUT = """ | |
| ## 📝 About | |
| The Edge-LLM Leaderboard is a leaderboard to gauge practical performance and quality of edge LLMs. | |
| Its aim is to benchmark the performance (throughput and memory) | |
| of Large Language Models (LLMs) on Edge hardware - starting with a Raspberry Pi 5 (8GB) based on the ARM Cortex A76 CPU. | |
| Anyone from the community can request a new base model or edge hardware/backend/optimization | |
| configuration for automated benchmarking: | |
| - Model evaluation requests will be made live soon, in the meantime feel free to email to - arnav[dot]chavan[@]nyunai[dot]com | |
| ## ✍️ Details | |
| - To avoid multi-thread discrepencies, all 4 threads are used on the Pi 5. | |
| - LLMs are running on a singleton batch with a prompt size of 512 and generating 128 tokens. | |
| All of our throughput benchmarks are ran by this single tool | |
| [llama-bench](https://github.com/ggerganov/llama.cpp/tree/master/examples/llama-bench) | |
| using the power of [llama.cpp](https://github.com/ggerganov/llama.cpp) to guarantee reproducibility and consistency. | |
| """ | |
| CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results." | |
| CITATION_BUTTON = r"""@misc{edge-llm-leaderboard, | |
| author = {}, | |
| title = {Edge-LLM Leaderboard}, | |
| year = {2024}, | |
| publisher = {}, | |
| howpublished = "\url{https://huggingface.co/spaces/nyunai/edge-llm-leaderboard}", | |
| } | |
| """ | |