Improve auto-generated readme with section on tokenizer, fix error in…

… example

bm25s/hf.py

@@ -107,6 +107,32 @@
 retriever = BM25HF.load_from_hub("{username}/{repo_name}", token=token)
 ```
 
+## Tokenizer
+
+If you have saved a `Tokenizer` object with the index using the following approach:
+
+```python
+from bm25s.hf import TokenizerHF
+
+token = "your_hugging_face_token"
+tokenizer = TokenizerHF(corpus=corpus, stopwords="english")
+tokenizer.save_to_hub("{username}/{repo_name}", token=token)
+
+# and stopwords too
+tokenizer.save_stopwords_to_hub("{username}/{repo_name}", token=token)
+```
+
+Then, you can load the tokenizer using the following code:
+
+```python
+from bm25s.hf import TokenizerHF
+
+tokenizer = TokenizerHF(corpus=corpus, stopwords=[])
+tokenizer.load_vocab_from_hub("{username}/{repo_name}", token=token)
+tokenizer.load_stopwords_from_hub("{username}/{repo_name}", token=token)
+```
+
+
 ## Stats
 
 This dataset was created using the following data:

examples/index_to_hf.py

@@ -55,7 +55,7 @@ def main(user, save_dir="datasets", repo_name="bm25s-scifact-testing", dataset="
     tokenizer.save_vocab_to_hub(repo_id=f"{user}/{repo_name}", token=hf_token)
 
     # you can also load the retriever and tokenizer from the hub
-    tokenizer_new = bm25s.hf.TokenizerHF(stemmer=stemmer)
+    tokenizer_new = bm25s.hf.TokenizerHF(stemmer=stemmer, stopwords=[])
     tokenizer_new.load_vocab_from_hub(repo_id=f"{user}/{repo_name}", token=hf_token)
 
     # You can do the same for stopwords