Update app.py

app.py

@@ -4,17 +4,19 @@ import torch
 MODEL_NAME = "RPW/NIH-1.2_Llama-3.2-11B-Vision-Instruct"
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
+instruction = "You are an expert radiographer. Describe accurately what you see in this image."
+
 # Load the tokenizer and model
 tokenizer = RobertaTokenizer.from_pretrained(MODEL_NAME)
 model = RobertaForSequenceClassification.from_pretrained(MODEL_NAME).to(device)
 
-# Example usage: Tokenizing some input text
-input_text = "Describe this image."
-inputs = tokenizer(input_text, return_tensors="pt").to(device)
-
-# Generating output
-outputs = model(**inputs)
-logits = outputs.logits
+input_text = tokenizer.apply_chat_template(messages, add_generation_prompt=True)
+inputs = tokenizer(
+    image,
+    input_text,
+    add_special_tokens=False,
+    return_tensors="pt").to("cuda")
 
-# ใช้ softmax หรือการแปลงค่าอื่นๆ ถ้าต้องการผลลัพธ์ที่เหมาะสมกับการ classification
-print(logits)
+text_streamer = TextStreamer(tokenizer, skip_prompt=True)
+_ = model.generate(**inputs, streamer=text_streamer, max_new_tokens=128,
+                   use_cache=True, temperature=1.5, min_p=0.1)