llm-perf-leaderboard / src /assets /text_content.py
BenchmarkBot's picture
made models clickable
d262fb3
raw
history blame
630 Bytes
TITLE = """<h1 align="center" id="space-title">πŸ€— Open LLM-Perf Leaderboard</h1>"""
INTRODUCTION_TEXT = f"""
The πŸ€— Open LLM-Perf Leaderboard aims to benchmark the performance (latency & throughput) of Large Language Models (LLMs) on different backends and hardwares using [Optimum-Benchmark](https://github.com/huggingface/optimum-benchmark)
πŸ€— Anyone from the community can submit a model for automated benchmarking on the πŸ€— GPU cluster, as long as it is a πŸ€— Transformers model with weights on the Hub. We also support benchmarks of models with delta-weights for non-commercial licensed models, such as LLaMa.
"""