Update app.py

app.py

@@ -82,8 +82,8 @@ with demo:
         gr.Markdown(
             """Notes:
             <ul>
-            <li> Throughputs and peak memory usage are measured using <a href="https://github.com/huggingface/optimum-benchmark/tree/main">Optimum-Benchmark</a> which powers <a href="https://huggingface.co/spaces/optimum/llm-perf-leaderboard">🤗 Open LLM-Perf Leaderboard 🏋️</a>. (0 throughput corresponds to OOM).</li>
-            <li> All models were evaluated with the <a href="https://github.com/bigcode-project/bigcode-evaluation-harness/tree/main">🔍 bigcode-evaluation-harness</a> with top-p=0.95, temperature=0.2 and n_samples=50.</li>
+            <li> Throughputs and peak memory usage are measured using <a href="https://github.com/huggingface/optimum-benchmark/tree/main">Optimum-Benchmark</a> which powers <a href="https://huggingface.co/spaces/optimum/llm-perf-leaderboard">Open LLM-Perf Leaderboard</a>. (0 throughput corresponds to OOM).</li>
+            <li> All models were evaluated with the <a href="https://github.com/bigcode-project/bigcode-evaluation-harness/tree/main">bigcode-evaluation-harness</a> with top-p=0.95, temperature=0.2 and n_samples=50.</li>
             <li> HumanEval-Python, reports the pass@1 on HumanEval, the rest is from MultiPL-E benchmark.</li>
             <li> Average score is the average pass@1 over all languages. During the averaging, we exclude languages with a pass@1 score lower than 1 for each model.</li>
             <li> #Languages column represents the number of programming languages included during the pretraining.