Upload README.md with huggingface_hub

README.md

@@ -281,7 +281,7 @@ When filtering by parameter scale for lightweight, production-ready edge models
 | 🏅 **#8** | **`CoIR`** | $\le$ 141M (`2M – 141.3M`) | **`0.5343`** | 👉 [CoIR Leaderboard (Rank #8)](https://mteb-leaderboard.hf.space/benchmark/CoIR?minSize=2&maxSize=141.2537544622754) |
 | 🏅 **#9** | **`MTEB(Code, v1)`** | $\le$ 141M (`2M – 141.3M`) | **`0.5475`** | 👉 [MTEB Code Leaderboard (Rank #9)](https://mteb-leaderboard.hf.space/benchmark/MTEB(Code%2C%20v1)?minSize=2&maxSize=141.2537544622754) |
 
----
+### 🌟 Key Benchmark Highlights
 
 ### 🌟 Key Benchmark Highlights *(Sorted by Rank Ascending)*
 
@@ -652,6 +652,75 @@ for doc in matched_docs:
 
 ---
 
+### Example 7: Local Serving with Ollama
+
+Run `code-embed-v2` locally with Ollama (native embed API or OpenAI-compatible endpoint):
+
+```bash
+# 1. Pull & run directly from Hugging Face
+ollama pull hf.co/divakantpandey/code-embed-v2:code-embed-v2-q8_0.gguf
+
+# Or if pulled from the Ollama registry:
+# ollama pull divakantpandey/code-embed-v2
+
+# 2. Generate embeddings via cURL:
+curl http://localhost:11434/api/embed -d '{
+  "model": "divakantpandey/code-embed-v2",
+  "input": "def binary_search(arr, target):"
+}'
+
+# 3. Query via OpenAI-compatible endpoint (/v1/embeddings):
+curl http://localhost:11434/v1/embeddings \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "divakantpandey/code-embed-v2",
+    "input": "def binary_search(arr, target):"
+  }'
+```
+
+---
+
+### Example 8: High-Performance C++ Inference with `llama.cpp`
+
+Use the Q8_0 GGUF quantized weights for standalone C++ embedding generation or an OpenAI-compatible microservice:
+
+```bash
+# Download GGUF weights (135MB)
+wget https://huggingface.co/divakantpandey/code-embed-v2/resolve/main/code-embed-v2-q8_0.gguf
+
+# Start an OpenAI-compatible embedding server:
+llama-server \
+  -m code-embed-v2-q8_0.gguf \
+  --embedding \
+  -c 8192 \
+  --port 8080
+
+# Query with standard OpenAI Python SDK:
+from openai import OpenAI
+
+client = OpenAI(base_url="http://localhost:8080/v1", api_key="not-needed")
+response = client.embeddings.create(
+    model="code-embed-v2",
+    input="def find_max(nums):"
+)
+print("Vector length:", len(response.data[0].embedding))
+```
+
+---
+
+### Example 9: Production Serving with Text Embeddings Inference (TEI)
+
+For enterprise throughput with dynamic batching and token truncation:
+
+```bash
+# Deploy with Hugging Face TEI (Docker)
+docker run --gpus all -p 8080:80 \
+  ghcr.io/huggingface/text-embeddings-inference:1.5 \
+  --model-id divakantpandey/code-embed-v2
+```
+
+---
+
 ## 📜 License & Citation
 
 This project and its model weights are licensed under the **Creative Commons Attribution-NonCommercial 4.0 International License (CC-BY-NC 4.0)**.