Merge branch 'main' of https://huggingface.co/jinaai/jina-embeddings-v5-text-small-text-matching

README.md

@@ -26,7 +26,7 @@ library_name: llama.cpp
 
 ### **jina-embeddings-v5-text-small-text-matching**: Text-Matching-Targeted Embedding Distillation
 
-[Blog](https://jina.ai/news/jina-embeddings-v5-text-distilling-4b-quality-into-sub-1b-multilingual-embeddings) | [Elastic Inference Service](https://www.elastic.co/docs/explore-analyze/elastic-inference/eis) | [ArXiv](https://arxiv.org/abs/2602.15547) | [Blog](https://jina.ai/news/jina-embeddings-v5-text-distilling-4b-quality-into-sub-1b-multilingual-embeddings)
+[Elastic Inference Service](https://www.elastic.co/docs/explore-analyze/elastic-inference/eis) | [ArXiv](https://arxiv.org/abs/2602.15547) | [Release Note](https://jina.ai/news/jina-embeddings-v5-text-distilling-4b-quality-into-sub-1b-multilingual-embeddings) | [Blog](https://www.elastic.co/search-labs/blog/jina-embeddings-v5-text)
 
 ### Model Overview
 
@@ -48,18 +48,7 @@ Trained using a novel approach that combines distillation with task-specific con
 | Pooling Strategy | Last-token pooling |
 | Base Model | jinaai/jina-embeddings-v5-text-small |
 
-<p align="center">
-<img src="https://jina-ai-gmbh.ghost.io/content/images/2026/02/v5_mmteb-4.png" alt="MMTEB Multilingual Benchmark" width="500px">
-</p>
-
-<p align="center">
-<img src="https://jina-ai-gmbh.ghost.io/content/images/2026/02/v5_mteb_en-4.png" alt="MTEB English Benchmark" width="500px">
-</p>
-
-<p align="center">
-<img src="https://jina-ai-gmbh.ghost.io/content/images/2026/02/v5_retrieval-4.png" alt="Retrieval Benchmark Results" width="500px">
-</p>
-
+![v5_benchmarks_combined](https://cdn-uploads.huggingface.co/production/uploads/6476ff2699a5ce743ccea3fc/7WjMQChM6XAOI9LhREChg.png)
 
 ### Training and Evaluation
 
@@ -246,6 +235,52 @@ curl -X POST "http://127.0.0.1:8080/v1/embeddings" \
 
 </details>
 
+<details>
+  <summary> via <a href="https://huggingface.co/docs/optimum/index">Optimum (ONNX)</a></summary>
+
+You can run the ONNX-optimized version of the model locally using Hugging Face's `optimum` library. Make sure you have the required dependencies installed (e.g., `pip install optimum[onnxruntime] transformers torch`):
+
+```python
+from optimum.onnxruntime import ORTModelForFeatureExtraction
+from transformers import AutoTokenizer
+import torch
+
+model_id = "jinaai/jina-embeddings-v5-text-small-text-matching"
+
+# 1. Load tokenizer and ONNX model
+# We specify the subfolder 'onnx' where the weights are located
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+model = ORTModelForFeatureExtraction.from_pretrained(
+    model_id,
+    subfolder="onnx",
+    file_name="model.onnx",
+    provider="CPUExecutionProvider",  # Or "CUDAExecutionProvider" for GPU
+    trust_remote_code=True,
+)
+
+# 2. Prepare input
+texts = ["Document: How do I use Jina ONNX models?", "Document: Information about semantic matching."]
+inputs = tokenizer(texts, padding=True, truncation=True, return_tensors="pt")
+
+
+# 4. Inference
+with torch.no_grad():
+    outputs = model(**inputs)
+
+# 5. Pooling (Crucial for Jina-v5)
+# Jina-v5 uses LAST-TOKEN pooling.
+# We take the hidden state of the last non-padding token.
+last_hidden_state = outputs.last_hidden_state
+# Find the indices of the last token (usually the end of the sequence)
+sequence_lengths = inputs.attention_mask.sum(dim=1) - 1
+embeddings = last_hidden_state[torch.arange(last_hidden_state.size(0)), sequence_lengths]
+
+print('embeddings shape:', embeddings.shape)
+print('embeddings:', embeddings)
+```
+
+</details>
+
 ### License
 
 The model is licensed under CC BY-NC 4.0. For commercial use, please [contact us]([email protected]).