Added transformers usage example

README.md

@@ -24,4 +24,49 @@ Model checkpoint is saved in [compressed_tensors](https://github.com/neuralmagic
 * To use the model in `transformers` update the package to stable release of Mistral-3
   
   `pip install git+https://github.com/huggingface/[email protected]`
-* To use the model in `vLLM` update the package to version `vllm>=0.8.0`.
+* To use the model in `vLLM` update the package to version `vllm>=0.8.0`.
+
+And example of inference via transformers is provided below:
+
+# pip install accelerate
+
+from transformers import AutoProcessor, AutoModelForImageTextToText
+from PIL import Image
+import requests
+import torch
+
+model_id = "ISTA-DASLab/Mistral-Small-3.1-24B-Instruct-2503-GPTQ-4b-128g"
+
+model = AutoModelForImageTextToText.from_pretrained(
+    model_id, device_map="auto"
+).eval()
+
+processor = AutoProcessor.from_pretrained(model_id)
+
+messages = [
+    {
+        "role": "system",
+        "content": [{"type": "text", "text": "You are a helpful assistant."}]
+    },
+    {
+        "role": "user",
+        "content": [
+            {"type": "image", "image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg"},
+            {"type": "text", "text": "Describe this image in detail."}
+        ]
+    }
+]
+
+inputs = processor.apply_chat_template(
+    messages, add_generation_prompt=True, tokenize=True,
+    return_dict=True, return_tensors="pt"
+).to(model.device, dtype=torch.bfloat16)
+
+input_len = inputs["input_ids"].shape[-1]
+
+with torch.inference_mode():
+    generation = model.generate(**inputs, max_new_tokens=100, do_sample=False)
+    generation = generation[0][input_len:]
+
+decoded = processor.decode(generation, skip_special_tokens=True)
+print(decoded)