Add FP16 note

README.md

@@ -37,6 +37,8 @@ Here is an overview of the models we deliver publicly:
 | [vectorizer.guava](https://huggingface.co/sinequa/vectorizer.guava)                         | de, en, es, fr, it, ja, nl, pl, pt, zh-trad, zs | 0.616     | 12 ms          | 550 MiB    |
 | [vectorizer.banana](https://huggingface.co/sinequa/vectorizer.banana)                       | 100+ languages                                  | [details](https://huggingface.co/sinequa/vectorizer.banana#scores) | 35 ms          | 1450 MiB    |
 
+Inference times and GPU memory usage reported are for FP16 models.
+
 ## Passage Ranker
 
 Passage Rankers are models which produce a relevance score given a query-passage pair and are used to order search
@@ -52,3 +54,5 @@ Here is an overview of the models we deliver publicly:
 | [passage-ranker.pistachio](https://huggingface.co/sinequa/passage-ranker.pistachio)                   | de, en, es, fr, it, ja, nl, pl, pt, zs, zh-trad         | 0.474     | 65 ms          | 850 MiB    |
 | [passage-ranker.apricot](https://huggingface.co/sinequa/passage-ranker.apricot)                       | ar, de, en, es, fr, it, ja, kr, nl, pl, pt, zs, zh-trad | 0.449     | 13 ms          | 550 MiB    |
 | [passage-ranker.nectarine](https://huggingface.co/sinequa/passage-ranker.nectarine)                   | ar, de, en, es, fr, it, ja, kr, nl, pl, pt, zs, zh-trad | 0.455     | 65 ms          | 850 MiB    |
+
+Inference times and GPU memory usage reported are for FP16 models.