Integrate with Sentence Transformers v5.4

1_Pooling/config.json

@@ -0,0 +1,5 @@
+{
+    "embedding_dimension": 4096,
+    "pooling_mode": "lasttoken",
+    "include_prompt": true
+}

README.md

@@ -1,11 +1,12 @@
 ---
 license: apache-2.0
-library_name: transformers
-pipeline_tag: feature-extraction
+library_name: sentence-transformers
+pipeline_tag: sentence-similarity
 
 base_model:
 - Qwen/Qwen3-VL-8B-Instruct
 tags:
+- sentence-transformers
 - transformers
 - multimodal embedding
 - qwen
@@ -104,6 +105,55 @@ Results on the MMTEB benchmark.
 
 ## Usage
 
+### Sentence Transformers
+
+Install Sentence Transformers with `pip install sentence-transformers`, then use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+
+# Load the model
+model = SentenceTransformer("Qwen/Qwen3-VL-Embedding-8B")
+
+# Text queries
+queries = [
+    "A woman playing with her dog on a beach at sunset.",
+    "Pet owner training dog outdoors near water.",
+    "Woman surfing on waves during a sunny day.",
+    "City skyline view from a high-rise building at night.",
+]
+
+# Documents: text, image, and text+image
+documents = [
+    "A woman shares a joyful moment with her golden retriever on a sun-drenched beach at sunset, as the dog offers its paw in a heartwarming display of companionship and trust.",
+    "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
+    {"text": "A woman shares a joyful moment with her golden retriever on a sun-drenched beach at sunset, as the dog offers its paw in a heartwarming display of companionship and trust.", "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"},
+]
+
+# Encode queries and documents
+query_embeddings = model.encode(queries)
+doc_embeddings = model.encode(documents)
+print(query_embeddings.shape, doc_embeddings.shape)
+# (4, 4096) (3, 4096)
+
+# Compute similarities
+similarities = model.similarity(query_embeddings, doc_embeddings)
+print(similarities)
+# tensor([[0.7438, 0.6556, 0.6244],
+#         [0.4430, 0.3323, 0.3929],
+#         [0.3685, 0.2310, 0.2874],
+#         [0.0602, -0.0162, 0.0167]])
+```
+
+By default, all inputs are wrapped with the `"Represent the user's input."` instruction via a system prompt. You can customize this by passing a different prompt:
+
+```python
+# With a custom prompt
+model.encode(queries, prompt="Retrieve relevant documents for the query.")
+```
+
+### Using transformers
+
 - **requirements**
 ```text
 transformers>=4.57.0

config_sentence_transformers.json

@@ -0,0 +1,11 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.4.0"
+  },
+  "default_prompt_name": "default",
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "default": "Represent the user's input."
+  },
+  "similarity_fn_name": "cosine"
+}

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.base.modules.transformer.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.sentence_transformer.modules.normalize.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,29 @@
+{
+    "transformer_task": "feature-extraction",
+    "modality_config": {
+        "text": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        },
+        "image": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        },
+        "video": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        },
+        "message": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state",
+            "format": "structured"
+        }
+    },
+    "module_output_name": "token_embeddings",
+    "processing_kwargs": {
+        "chat_template": {
+            "add_generation_prompt": true
+        }
+    },
+    "unpad_inputs": false
+}