Clarify normalization and folded linear head loading

README.md

@@ -41,6 +41,14 @@ encoder = fse.Encoder.from_pretrained("fse/paranmt-300-raw")
 vectors = encoder.encode(["A sentence."])
 ```
 
+The encoder normalizes every vector to unit length (the stored step `normalize@1`). To get the raw weighted mean instead, for example to fold a linear head into the table, load it with `normalize=False`:
+
+```python
+encoder = fse.Encoder.from_pretrained("fse/paranmt-300-raw", normalize=False)
+```
+
+The suffix `-raw` means without SIF weighting, not without normalization. Both `-raw` and `-sif10` models load normalized by default.
+
 ## Source and license
 
 Converted from the gensim model fse/paranmt-300 at revision `a08e15771891207a22f840a3091a00a1657d888b`.