Create README.md

README.md

@@ -0,0 +1,69 @@
+---
+library_name: optimum.onnxruntime
+tags:
+- onnx
+- int8
+- quantization
+- embeddings
+- cpu
+pipeline_tag: feature-extraction
+license: apache-2.0
+base_model: ibm-granite/granite-embedding-english-r2
+---
+
+# Granite Embedding English R2 — INT8 (ONNX)
+
+This is the **INT8-quantized ONNX version** of [`ibm-granite/granite-embedding-english-r2`](https://huggingface.co/ibm-granite/granite-embedding-english-r2).  
+It is optimized to run efficiently on **CPU** using [🤗 Optimum](https://huggingface.co/docs/optimum) with ONNX Runtime.
+
+- **Embedding dimension:** 768  
+- **Precision:** INT8 (dynamic quantization)  
+- **Backend:** ONNX Runtime  
+- **Use case:** text embeddings, semantic search, clustering, retrieval  
+
+---
+
+## 📥 Installation
+
+```bash
+pip install -U transformers optimum[onnxruntime]
+````
+
+---
+
+## 🚀 Usage
+
+```python
+from transformers import AutoTokenizer
+from optimum.onnxruntime import ORTModelForFeatureExtraction
+
+repo_id = "yasserrmd/granite-embedding-r2-onnx"
+
+# Load tokenizer + ONNX model
+tokenizer = AutoTokenizer.from_pretrained(repo_id)
+model = ORTModelForFeatureExtraction.from_pretrained(repo_id)
+
+# Encode sentences
+inputs = tokenizer(["Hello world", "مرحباً"], padding=True, return_tensors="pt")
+outputs = model(**inputs)
+
+# Apply mean pooling over tokens
+embeddings = outputs.last_hidden_state.mean(dim=1)
+print(embeddings.shape)  # (2, 768)
+```
+
+---
+
+## ✅ Notes
+
+* Quantization reduces model size and makes inference faster on CPUs while preserving accuracy.
+* Pooling strategy here is **mean pooling**; you can adapt CLS pooling or max pooling as needed.
+* Works seamlessly with **Hugging Face Hub** + `optimum.onnxruntime`.
+
+---
+
+## 📚 References
+
+* [Original Granite Embedding English R2](https://huggingface.co/ibm-granite/granite-embedding-english-r2)
+* [Optimum ONNX Runtime docs](https://huggingface.co/docs/optimum/onnxruntime/usage_guides/models)
+