Update quantized pipeline artifacts (modules.json, weights, tokenizer, README)

1_Pooling/config.json

@@ -1,10 +1,10 @@
 {
     "word_embedding_dimension": 4096,
     "pooling_mode_cls_token": false,
-    "pooling_mode_mean_tokens": true,
+    "pooling_mode_mean_tokens": false,
     "pooling_mode_max_tokens": false,
     "pooling_mode_mean_sqrt_len_tokens": false,
     "pooling_mode_weightedmean_tokens": false,
-    "pooling_mode_lasttoken": false,
+    "pooling_mode_lasttoken": true,
     "include_prompt": true
 }

README.md

@@ -36,7 +36,7 @@ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [S
 ```
 SentenceTransformer(
   (0): Transformer({'max_seq_length': 32768, 'do_lower_case': False, 'architecture': 'MistralModel'})
-  (1): Pooling({'word_embedding_dimension': 4096, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+  (1): Pooling({'word_embedding_dimension': 4096, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': True, 'include_prompt': True})
   (2): Normalize()
 )
 ```
@@ -70,9 +70,9 @@ print(embeddings.shape)
 # Get the similarity scores for the embeddings
 similarities = model.similarity(embeddings, embeddings)
 print(similarities)
-# tensor([[1.0000, 0.7891, 0.6680],
-#         [0.7891, 1.0078, 0.6523],
-#         [0.6680, 0.6523, 1.0078]], dtype=torch.bfloat16)
+# tensor([[1.0000, 0.7070, 0.5469],
+#         [0.7070, 1.0078, 0.5469],
+#         [0.5469, 0.5469, 1.0000]], dtype=torch.bfloat16)
 ```
 
 <!--