Update README.md

README.md

@@ -102,6 +102,36 @@ generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
 
 ## Training Details
 
+```
+from transformers import ViTImageProcessor, AutoTokenizer, VisionEncoderDecoderModel
+from datasets import load_dataset
+
+image_processor = ViTImageProcessor.from_pretrained("LeroyDyer/Mixtral_AI_Cyber_Q_Vision")
+tokenizer = AutoTokenizer.from_pretrained("LeroyDyer/Mixtral_AI_Cyber_Q_Vision")
+model = VisionEncoderDecoderModel.from_encoder_decoder_pretrained(
+    "LeroyDyer/Mixtral_AI_Cyber_Q_Vision", "LeroyDyer/Mixtral_AI_Cyber_Q_Vision"
+)
+
+model.config.decoder_start_token_id = tokenizer.cls_token_id
+model.config.pad_token_id = tokenizer.pad_token_id
+
+dataset = load_dataset("huggingface/cats-image")
+image = dataset["test"]["image"][0]
+pixel_values = image_processor(image, return_tensors="pt").pixel_values
+
+labels = tokenizer(
+    "an image of two cats chilling on a couch",
+    return_tensors="pt",
+).input_ids
+
+# the forward function automatically creates the correct decoder_input_ids
+loss = model(pixel_values=pixel_values, labels=labels).loss
+
+
+
+```
+
+
 ### Training Data
 
 <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->