Upload README.md with huggingface_hub

README.md

@@ -26,13 +26,15 @@ twelve layers instead of six, the same 384-dimensional output and the same recip
 ## The pooling is in the graph, on purpose
 
 sentence-transformers keeps the recipe per model in `1_Pooling/config.json` and
-`modules.json`, and the four small models on this shelf do not agree:
+`modules.json`, and the six embedding models on this shelf do not agree:
 
 | | pooling | normalised |
 |---|---|---|
 | all-MiniLM-L6-v2 | mean | yes |
 | **all-MiniLM-L12-v2** | **mean** | **yes** |
 | bge-small-en-v1.5 | **CLS** | yes |
+| multilingual-e5-base | mean | yes |
+| multilingual-e5-large | mean | yes |
 | paraphrase-multilingual-L12 | mean | **no** |
 
 This one was read off the repo rather than assumed from the family name: `modules.json`