Update README.md

README.md

@@ -14,6 +14,7 @@ For a complete overview of the project, including all related models, datasets,
 ```python
 from transformers import MllamaForConditionalGeneration, AutoProcessor
 from peft import PeftModel
+from PIL import Image
 
 # Load base model
 base_model_name = "meta-llama/Llama-3.2-11B-Vision-Instruct" 
@@ -23,6 +24,57 @@ processor = AutoProcessor.from_pretrained(base_model_name)
 # Load LoRA adapter
 adapter_path = "DermaVLM/DermatoLLama-200k"
 model = PeftModel.from_pretrained(model, adapter_path)
+
+# Inference
+image_path = "DERM12345.jpg"
+image = Image.open(image_path).convert("RGB")
+prompt_text = "Describe the image in detail."
+messages = []
+content_list = []
+if image:
+    content_list.append({"type": "image"})
+
+# Add the text part of the prompt
+content_list.append({"type": "text", "text": prompt_text})
+messages.append({"role": "user", "content": content_list})
+
+input_text = processor.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    tokenize=False,
+)
+
+# Prepare final inputs
+inputs = processor(
+    images=image,
+    text=input_text,
+    add_special_tokens=False,
+    return_tensors="pt",
+).to(model.device)
+
+generation_config = {
+    "max_new_tokens": 256,
+    "do_sample": True,
+    "temperature": 0.4,
+    "top_p": 0.95,
+}
+
+input_length = inputs.input_ids.shape[1]
+
+with torch.no_grad():
+    outputs = model.generate(
+        **inputs,
+        **generation_config,
+        pad_token_id=(
+            processor.tokenizer.pad_token_id
+            if processor.tokenizer.pad_token_id is not None
+            else processor.tokenizer.eos_token_id
+        ),
+    )
+    generated_tokens = outputs[0][input_length:]
+    raw_output = processor.decode(generated_tokens, skip_special_tokens=True)
+
+print(raw_output)
 ```
 
 ## Citation