Fix various snippets; add required safe_serialization (#2)

- Fix various snippets; add required safe_serialization (6d202215e2046ffea6078235fd60d7be11da64fc)

README.md

@@ -2675,9 +2675,9 @@ from sentence_transformers import SentenceTransformer
 
 matryoshka_dim = 512
 
-model = SentenceTransformer(".", trust_remote_code=True)
+model = SentenceTransformer("nomic-ai/nomic-embed-text-v1.5", trust_remote_code=True)
 sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?']
-embeddings = model.encode(sentences)
+embeddings = model.encode(sentences, convert_to_tensor=True)
 embeddings = F.layer_norm(embeddings, normalized_shape=(embeddings.shape[1],))
 embeddings = embeddings[:, :matryoshka_dim]
 embeddings = F.normalize(embeddings, p=2, dim=1)
@@ -2699,7 +2699,7 @@ def mean_pooling(model_output, attention_mask):
 sentences = ['search_query: What is TSNE?', 'search_query: Who is Laurens van der Maaten?']
 
 tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
-model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1', trust_remote_code=True)
+model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1.5', trust_remote_code=True, safe_serialization=True)
 model.eval()
 
 encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

sentence_bert_config.json

@@ -1,4 +1,7 @@
 {
     "max_seq_length": 8192,
-    "do_lower_case": false
+    "do_lower_case": false,
+    "model_args": {
+        "safe_serialization": true
+    }
 }