updated app.py

app.py

@@ -27,7 +27,7 @@ def answer_question(image, question):
     if image is None:
         return "Error: Please upload an image."
 
-    # Convert NumPy array to PIL Image if necessary
+    # Convert NumPy array to PIL Image
     try:
         if isinstance(image, np.ndarray):
             image = Image.fromarray(image)
@@ -49,14 +49,14 @@ def answer_question(image, question):
         },
     ]
 
-    # Apply chat template (this assumes the processor has a chat-based input format)
+    # Apply chat template and prepare inputs
     try:
         prompt = processor.apply_chat_template(messages, add_generation_prompt=True)
         inputs = processor(text=prompt, images=[image], return_tensors="pt").to(DEVICE)
     except Exception as e:
         return f"Error: Failed to prepare inputs. {str(e)}"
 
-    # Generate the answer
+    # Generate answer
     try:
         outputs = model.generate(**inputs, max_new_tokens=400)
         answer = processor.decode(outputs[0], skip_special_tokens=True)

demo.ipynb

@@ -1,134 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/home/kask/miniconda3/envs/innovatie-week/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
-      "  from .autonotebook import tqdm as notebook_tqdm\n"
-     ]
-    }
-   ],
-   "source": [
-    "from transformers import AutoProcessor, AutoModelForVision2Seq\n",
-    "from transformers.image_utils import load_image\n",
-    "import numpy as np\n",
-    "import gradio as gr\n",
-    "import torch\n",
-    "from PIL import Image"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "cpu\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Set the device (GPU or CPU)\n",
-    "DEVICE = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
-    "print(DEVICE)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Some kwargs in processor config are unused and will not have any effect: image_seq_len. \n"
-     ]
-    }
-   ],
-   "source": [
-    "# Initialize processor and model\n",
-    "try:\n",
-    "    processor = AutoProcessor.from_pretrained(\"HuggingFaceTB/SmolVLM-Instruct\")\n",
-    "    model = AutoModelForVision2Seq.from_pretrained(\n",
-    "    \"HuggingFaceTB/SmolVLM-Instruct\",\n",
-    "    torch_dtype=torch.bfloat16,\n",
-    "    _attn_implementation=\"flash_attention_2\" if DEVICE == \"cuda\" else \"eager\",).to(DEVICE)\n",
-    "except Exception as e:\n",
-    "    print(f\"Error loading model or processor: {str(e)}\")\n",
-    "    exit(1)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/home/kask/miniconda3/envs/innovatie-week/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
-      "  from .autonotebook import tqdm as notebook_tqdm\n",
-      "Some kwargs in processor config are unused and will not have any effect: image_seq_len. \n"
-     ]
-    },
-    {
-     "ename": "",
-     "evalue": "",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[1;31mThe Kernel crashed while executing code in the current cell or a previous cell. \n",
-      "\u001b[1;31mPlease review the code in the cell(s) to identify a possible cause of the failure. \n",
-      "\u001b[1;31mClick <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a> for more info. \n",
-      "\u001b[1;31mView Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
-     ]
-    }
-   ],
-   "source": [
-    "from transformers import AutoProcessor, AutoModelForVision2Seq\n",
-    "import tqdm as notebook_tqdm\n",
-    "\n",
-    "# Define the model name\n",
-    "model_name = \"HuggingFaceTB/SmolVLM-Instruct\"\n",
-    "\n",
-    "# Download and save the processor and model locally\n",
-    "processor = AutoProcessor.from_pretrained(model_name)\n",
-    "processor.save_pretrained(\"./local_model\")\n",
-    "\n",
-    "model = AutoModelForVision2Seq.from_pretrained(model_name)\n",
-    "model.save_pretrained(\"./local_model\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "innovatie-week",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}