Specify add_pooling_layer=False via configuration instead

README.md

@@ -8722,9 +8722,7 @@ queries = ['what is snowflake?', 'Where can I get the best tacos?']
 documents = ['The Data Cloud!', 'Mexico City of Course!']
 
 # Load the model.
-model = SentenceTransformer(
-    MODEL_ID, model_kwargs=dict(add_pooling_layer=False),
-)
+model = SentenceTransformer(MODEL_ID)
 
 # Generate text embeddings.
 query_embeddings = model.encode(queries, prompt_name="query")

sentence_bert_config.json

@@ -1,4 +1,7 @@
 {
   "max_seq_length": 512,
-  "do_lower_case": false
+  "do_lower_case": false,
+  "model_args": {
+    "add_pooling_layer": false
+  }
 }