Spaces:

optimum
/

llm-perf-leaderboard

Running

BenchmarkBot commited on Jul 3, 2023

Commit

570bffa

•

1 Parent(s): af2159b

corrected introduction text

Files changed (1) hide show

src/assets/text_content.py CHANGED Viewed

@@ -2,11 +2,11 @@ TITLE = """<h1 align="center" id="space-title">🤗 Open LLM-Perf Leaderboard
 INTRODUCTION_TEXT = f"""
 The 🤗 Open LLM-Perf Leaderboard 🏋️ aims to benchmark the performance (latency & throughput) of Large Language Models (LLMs) on different hardwares and backends using [Optimum-Benchmark](https://github.com/huggingface/optimum-benchmark) and [Optimum](https://github.com/huggingface/optimum) flavors.
-Anyone from the community can submit a model or a hardware+backend configuration for automated benchmarking:
-- Model submissions should be made in the [🤗 Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) and will be added to the 🤗 Open LLM-Perf Leaderboard 🏋️ once they're publicly available.
-- Hardware+Backend submissions should be made in the 🤗 Open LLM-Perf Leaderboard 🏋️ [community discussions](https://huggingface.co/spaces/optimum/llm-perf-leaderboard/discussions); An automated process will be set up soon.
-[Config files](https://github.com/huggingface/optimum-benchmark/blob/main/examples/bert.yaml) (which can be used with Optimum-Benchmark) will be available soon for reproduction and questioning/correction of the results.
 """
 CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results."

 INTRODUCTION_TEXT = f"""
 The 🤗 Open LLM-Perf Leaderboard 🏋️ aims to benchmark the performance (latency & throughput) of Large Language Models (LLMs) on different hardwares and backends using [Optimum-Benchmark](https://github.com/huggingface/optimum-benchmark) and [Optimum](https://github.com/huggingface/optimum) flavors.
+Anyone from the community can request a model or a hardware+backend configuration for automated benchmarking:
+- Model requests should be made in the [🤗 Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) and will be added to the 🤗 Open LLM-Perf Leaderboard 🏋️ once they're publicly available.
+- Hardware+Backend requests should be made in the 🤗 Open LLM-Perf Leaderboard 🏋️ [community discussions](https://huggingface.co/spaces/optimum/llm-perf-leaderboard/discussions).
+[Config files](https://github.com/huggingface/optimum-benchmark/blob/main/examples/bert.yaml) (which can be used with Optimum-Benchmark) will be available soon for reproduction, questioning and correction of our results.
 """
 CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results."