Add final benchmarks on A100

bench/generation/README.md

@@ -8,7 +8,7 @@ This repository contains scripts to evaluate the performances of quantized model
 
 A `evaluate_model.py` utility script is also provided to evaluate the metrics on a specific model for several quantization configurations, and output the result to a `png` barchart and/or a `json` file.
 
-The paragraphs below display results for some popular models.
+The paragraphs below display results for some popular models on a NVIDIA A100 GPU.
 
 ## facebook/opt-125m
 
@@ -137,3 +137,19 @@ The paragraphs below display results for some popular models.
   </div>
  </center>
 </div>
+
+## google/gemma-2b
+
+<div class="row"><center>
+  <div class="column">
+    <img src="https://github.com/huggingface/quanto/blob/main/bench/generation/charts/google-gemma-2b_Accuracy.png" alt="google-gemma-2b Lambada prediction accuracy">
+  </div>
+ </center>
+</div>
+
+<div class="row"><center>
+  <div class="column">
+    <img src="https://github.com/huggingface/quanto/blob/main/bench/generation/charts/google-gemma-2b_Perplexity.png" alt="google-gemma-2b Lambada prediction accuracy">
+  </div>
+ </center>
+</div>