COMMIT

app.py

@@ -1,64 +1,61 @@
+import numpy as np
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import simple_slice_viewer as ssv
+import SimpleITK as sikt
 import gradio as gr
-from huggingface_hub import InferenceClient
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+device = torch.device('cpu')  # Set to 'cuda' if using a GPU
+dtype = torch.float32  # Data type for model processing
 
+model_name_or_path = 'GoodBaiBai88/M3D-LaMed-Phi-3-4B'
+proj_out_num = 256  # Number of projection outputs required for the image
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+# Load model and tokenizer
+model = AutoModelForCausalLM.from_pretrained(
+    model_name_or_path,
+    torch_dtype=torch.float32,
+    device_map='cpu',
+    trust_remote_code=True
 )
 
+tokenizer = AutoTokenizer.from_pretrained(
+    model_name_or_path,
+    model_max_length=512,
+    padding_side="right",
+    use_fast=False,
+    trust_remote_code=True
+)
 
-if __name__ == "__main__":
-    demo.launch()
+def process_image(image_path, question):
+    # Load the image
+    image_np = np.load(image_path)  # Load the .npy image
+    image_tokens = "<im_patch>" * proj_out_num
+    input_txt = image_tokens + question
+    input_id = tokenizer(input_txt, return_tensors="pt")['input_ids'].to(device=device)
+
+    # Prepare image for model
+    image_pt = torch.from_numpy(image_np).unsqueeze(0).to(dtype=dtype, device=device)
+
+    # Generate model response
+    generation = model.generate(image_pt, input_id, max_new_tokens=256, do_sample=True, top_p=0.9, temperature=1.0)
+    generated_texts = tokenizer.batch_decode(generation, skip_special_tokens=True)
+
+    return generated_texts[0]
+
+# Gradio Interface
+def gradio_interface(image, question):
+    response = process_image(image.name, question)
+    return response
+
+# Gradio App
+gr.Interface(
+    fn=gradio_interface,
+    inputs=[
+        gr.File(label="Upload .npy Image", type="filepath"),  # For uploading .npy image
+        gr.Textbox(label="Enter your question", placeholder="Ask something about the image..."),
+    ],
+    outputs=gr.Textbox(label="Model Response"),
+    title="Medical Image Analysis",
+    description="Upload a .npy image and ask a question to analyze it using the model."
+).launch()