Integrate with Sentence Transformers v5.4

1_LogitScore/config.json

@@ -0,0 +1,4 @@
+{
+    "true_token_id": 9693,
+    "false_token_id": 2152
+}

README.md

@@ -2,10 +2,10 @@
 license: apache-2.0
 library_name: transformers
 pipeline_tag: text-ranking
-
 base_model:
 - Qwen/Qwen3-VL-8B-Instruct
 tags:
+- sentence-transformers
 - transformers
 - multimodal rerank
 - text rerank
@@ -68,6 +68,51 @@ We utilize retrieval task datasets from various subtasks of [MMEB-v2](https://hu
 
 ## Usage
 
+### Using Sentence Transformers
+
+Install Sentence Transformers:
+```bash
+pip install sentence_transformers
+```
+
+```python
+from sentence_transformers import CrossEncoder
+
+model = CrossEncoder("Qwen/Qwen3-VL-Reranker-8B")
+
+query = "A woman playing with her dog on a beach at sunset."
+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",
+    },
+]
+
+prompt = "Retrieve images or text relevant to the user's query."
+pairs = [(query, doc) for doc in documents]
+scores = model.predict(pairs, prompt=prompt)
+print(scores)
+# [1.3125, 0.25, 0.4375]
+
+rankings = model.rank(query, documents, prompt=prompt)
+print(rankings)
+# [{'corpus_id': 0, 'score': 1.3125}, {'corpus_id': 2, 'score': 0.4375}, {'corpus_id': 1, 'score': 0.25}]
+```
+
+You can map scores to 0...1 with a sigmoid activation:
+
+```python
+scores = model.predict(pairs, activation_fn=torch.nn.Sigmoid(), prompt=prompt)
+print(scores)
+# [0.7891, 0.5625, 0.6094]
+```
+
+The default prompt is `"query"` with instruction `"Retrieve text relevant to the user's query."`. You can customize the instruction for your use case via the `prompt` parameter as shown above.
+
+### Using Transformers
+
 - **requirements**
 ```text
 transformers>=4.57.0
@@ -75,8 +120,6 @@ qwen-vl-utils>=0.0.14
 torch==2.8.0
 ```
 
-### Basic Usage Example
-
 ```python
 from scripts.qwen3_vl_reranker import Qwen3VLReranker
 
@@ -105,7 +148,7 @@ print(scores)
 # [0.7838293313980103, 0.585621178150177, 0.6147719025611877]
 ```
 
-### vLLM Basic Usage Example
+### Using vLLM
 ```python
 import argparse
 import os

additional_chat_templates/reranker.jinja

@@ -0,0 +1,52 @@
+{%- set default_instruction = "Given a search query, retrieve relevant candidates that answer the query." -%}
+{%- set ns = namespace(instruction="", found_instruction=false) -%}
+{%- for message in messages -%}
+    {%- if message.role == "system" -%}
+        {%- if message.content is string -%}
+            {%- set ns.instruction = message.content -%}
+        {%- else -%}
+            {%- for content in message.content -%}
+                {%- if 'text' in content -%}
+                    {%- set ns.instruction = ns.instruction + content.text -%}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+        {%- set ns.found_instruction = true -%}
+    {%- endif -%}
+{%- endfor -%}
+{%- if not ns.found_instruction -%}
+    {%- set ns.instruction = default_instruction -%}
+{%- endif -%}
+{%- set image_count = namespace(value=0) -%}
+{%- set video_count = namespace(value=0) -%}
+{%- macro render_multimodal(message) -%}
+    {%- if message.content is string -%}
+        {{- message.content -}}
+    {%- else -%}
+        {%- for content in message.content -%}
+            {%- if content.type == 'image' or 'image' in content or 'image_url' in content -%}
+                {%- set image_count.value = image_count.value + 1 -%}
+                {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                <|vision_start|><|image_pad|><|vision_end|>
+            {%- elif content.type == 'video' or 'video' in content -%}
+                {%- set video_count.value = video_count.value + 1 -%}
+                {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                <|vision_start|><|video_pad|><|vision_end|>
+            {%- elif 'text' in content -%}
+                {{- content.text -}}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- endif -%}
+{%- endmacro -%}
+{{- '<|im_start|>system\nJudge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be "yes" or "no".<|im_end|>\n<|im_start|>user\n<Instruct>: ' + ns.instruction + '<Query>:' -}}
+{%- for message in messages if message.role == "query" -%}
+    {{- render_multimodal(message) -}}
+{%- endfor -%}
+{{- '\n<Document>:' -}}
+{%- for message in messages if message.role == "document" -%}
+    {{- render_multimodal(message) -}}
+{%- endfor -%}
+{{- '<|im_end|>\n' -}}
+{%- if add_generation_prompt -%}
+    {{- '<|im_start|>assistant\n' -}}
+{%- endif -%}

config_sentence_transformers.json

@@ -0,0 +1,12 @@
+{
+  "__version__": {
+    "pytorch": "2.10.0+cu128",
+    "sentence_transformers": "5.4.0"
+  },
+  "activation_fn": "torch.nn.modules.linear.Identity",
+  "default_prompt_name": "query",
+  "model_type": "CrossEncoder",
+  "prompts": {
+    "query": "Retrieve text relevant to the user's query."
+  }
+}

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.base.modules.transformer.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_CausalScoreHead",
+    "type": "sentence_transformers.cross_encoder.modules.logit_score.LogitScore"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,30 @@
+{
+    "transformer_task": "any-to-any",
+    "modality_config": {
+        "text": {
+            "method": "forward",
+            "method_output_name": "logits"
+        },
+        "image": {
+            "method": "forward",
+            "method_output_name": "logits"
+        },
+        "video": {
+            "method": "forward",
+            "method_output_name": "logits"
+        },
+        "message": {
+            "method": "forward",
+            "method_output_name": "logits",
+            "format": "structured"
+        }
+    },
+    "module_output_name": "causal_logits",
+    "unpad_inputs": false,
+    "processing_kwargs": {
+        "chat_template": {
+            "chat_template": "reranker",
+            "add_generation_prompt": true
+        }
+    }
+}