Qwen2 VL 2B Instruct OpenVINO INT4

--- license: apache-2.0 language: - en pipeline_tag: image-to-text tags: - openvino - nncf - qwen2-vl - vision-language - edge-ai - celeste-imperia --- # Celeste Imperia | Qwen2-VL-2B (OpenVINO INT4 Gold)   [](https://razorpay.me/@huggingface) **The specialized vision-reasoning engine for edge hardware.** This is a hardware-optimized port of Alibaba's **Qwen2-VL-2B-Instruct**, forged using Intel's **NNCF (Neural Network Compression Framework)** for ultra-low latency execution on CPUs, GPUs, and NPUs. --- ## 🐍 For Python Users (Optimum Intel) To achieve the highest throughput on Intel or ARM64 hardware, use the `optimum-intel` library with the OpenVINO backend. ```python from optimum.intel import OVModelForVisualCausalLM from transformers import AutoProcessor from PIL import Image import requests model_id = "CelesteImperia/Qwen2-VL-2B-Instruct-OpenVINO-INT4" # Load optimized model on CPU/GPU/NPU model = OVModelForVisualCausalLM.from_pretrained(model_id, device="CPU") processor = AutoProcessor.from_pretrained(model_id) # Example: Simple Image Description url = "[https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/ai2d-demo.png](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/ai2d-demo.png)" image = Image.open(requests.get(url, stream=True).raw) inputs = processor(text=["Describe this image."], images=[image], return_tensors="pt") output = model.generate(**inputs, max_new_tokens=128) print(processor.decode(output[0], skip_special_tokens=True)) ``` --- ## 💻 For C# / .NET Users (OpenVINO .NET SDK) As a Senior .NET developer, I have validated this vision-language model for native C# integration. This is ideal for building high-speed OCR or automated surveillance tools directly in the Windows/Intel ecosystem. ```csharp using OpenVinoSharp; using System; // 1. Initialize OpenVINO Core for Vision Core core = new Core(); // 2. Load the Optimized Qwen2-VL INT4 Model (.xml / .bin) Model model = core.read_model("qwen2_vl_int4.xml"); CompiledModel compiledModel = core.compile_model(model, "CPU"); Console.WriteLine("👁️ Qwen2-VL Vision Engine Initialized on .NET"); // [Inference l...

Source context: 62 downloads · 0 likes · Pipeline image-to-text · Repo CelesteImperia/Qwen2-VL-2B-Instruct-OpenVINO-INT4