code works

app.py

@@ -13,7 +13,7 @@ try:
     processor = AutoProcessor.from_pretrained("HuggingFaceTB/SmolVLM-Instruct")
     model = AutoModelForVision2Seq.from_pretrained(
         "HuggingFaceTB/SmolVLM-Instruct",
-        torch_dtype=torch.bfloat16 if DEVICE == "cuda" else torch.float32,
+        torch_dtype=torch.bfloat16,
         _attn_implementation="flash_attention_2" if DEVICE == "cuda" else "eager",
     ).to(DEVICE)
 except Exception as e:
@@ -56,23 +56,21 @@ def answer_question(image, question):
     except Exception as e:
         return f"Error: Failed to prepare inputs. {str(e)}"
 
-    # Generate the output
+    # Generate the answer
     try:
-        generated_ids = model.generate(**inputs, max_new_tokens=500)
-        generated_texts = processor.batch_decode(
-            generated_ids, skip_special_tokens=True
-        )
-        return generated_texts[0]
+        outputs = model.generate(**inputs)
+        answer = processor.decode(outputs[0], skip_special_tokens=True)
+        return answer
     except Exception as e:
-        return f"Error: Failed to generate output. {str(e)}"
+        return f"Error: Failed to generate answer. {str(e)}"
 
 
 # Create Gradio interface
 iface = gr.Interface(
     fn=answer_question,
     inputs=[
-        gr.inputs.Image(type="numpy"),
-        gr.inputs.Textbox(lines=2, placeholder="Enter your question here..."),
+        gr.Image(type="numpy"),
+        gr.Textbox(lines=2, placeholder="Enter your question here..."),
     ],
     outputs="text",
     title="Image Question Answering",

demo.ipynb

@@ -0,0 +1,104 @@
+{
+ "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": null,
+   "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"
+     ]
+    },
+    {
+     "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": [
+    "# 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)"
+   ]
+  }
+ ],
+ "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
+}