bumpt transformers and fix examples

app.py

@@ -37,21 +37,43 @@ class LOperatorDemo:
             if not HF_TOKEN:
                 return "❌ HF_TOKEN not found. Please set HF_TOKEN in Spaces secrets."
             
-            # Load processor with token
-            self.processor = AutoProcessor.from_pretrained(
-                MODEL_ID, 
-                trust_remote_code=True,
-                token=HF_TOKEN
-            )
-            
-            # Load model with token
-            self.model = AutoModelForImageTextToText.from_pretrained(
-                MODEL_ID,
-                torch_dtype=torch.bfloat16 if DEVICE == "cuda" else torch.float32,
-                trust_remote_code=True,
-                device_map="auto" if DEVICE == "cuda" else None,
-                token=HF_TOKEN
-            )
+            try:
+                # Try loading with standard approach
+                self.processor = AutoProcessor.from_pretrained(
+                    MODEL_ID, 
+                    trust_remote_code=True,
+                    token=HF_TOKEN
+                )
+                
+                self.model = AutoModelForImageTextToText.from_pretrained(
+                    MODEL_ID,
+                    torch_dtype=torch.bfloat16 if DEVICE == "cuda" else torch.float32,
+                    trust_remote_code=True,
+                    device_map="auto" if DEVICE == "cuda" else None,
+                    token=HF_TOKEN
+                )
+                
+            except Exception as e:
+                logger.warning(f"Standard loading failed: {str(e)}")
+                logger.info("Attempting fallback loading approach...")
+                
+                # Fallback: try loading with explicit model type
+                self.processor = AutoProcessor.from_pretrained(
+                    MODEL_ID, 
+                    trust_remote_code=True,
+                    token=HF_TOKEN,
+                    revision="main"
+                )
+                
+                self.model = AutoModelForImageTextToText.from_pretrained(
+                    MODEL_ID,
+                    torch_dtype=torch.bfloat16 if DEVICE == "cuda" else torch.float32,
+                    trust_remote_code=True,
+                    device_map="auto" if DEVICE == "cuda" else None,
+                    token=HF_TOKEN,
+                    revision="main",
+                    ignore_mismatched_sizes=True
+                )
             
             if DEVICE == "cpu":
                 self.model = self.model.to(DEVICE)
@@ -62,7 +84,7 @@ class LOperatorDemo:
             
         except Exception as e:
             logger.error(f"Error loading model: {str(e)}")
-            return f"❌ Error loading model: {str(e)}"
+            return f"❌ Error loading model: {str(e)} - This may be a custom model requiring special handling"
     
     @spaces.GPU(duration=120)  # 2 minutes for action generation
     def generate_action(self, image: Image.Image, goal: str, instruction: str) -> str:
@@ -193,7 +215,7 @@ def load_example_episodes():
         with open("extracted_episodes_duckdb/episode_13/metadata.json", "r") as f:
             episode_13 = json.load(f)
         
-        # Load episode 53
+        # Load episode 53  
         with open("extracted_episodes_duckdb/episode_53/metadata.json", "r") as f:
             episode_53 = json.load(f)
         
@@ -201,19 +223,19 @@ def load_example_episodes():
         with open("extracted_episodes_duckdb/episode_73/metadata.json", "r") as f:
             episode_73 = json.load(f)
         
-        # Create examples
+        # Create examples with simple identifiers
         examples = [
             [
                 "extracted_episodes_duckdb/episode_13/screenshots/screenshot_1.png",
-                f"Goal: {episode_13['goal']}\nStep: {episode_13['step_instructions'][0]}"
+                "Episode 13: Navigate app interface"
             ],
             [
-                "extracted_episodes_duckdb/episode_53/screenshots/screenshot_1.png",
-                f"Goal: {episode_53['goal']}\nStep: {episode_53['step_instructions'][0]}"
+                "extracted_episodes_duckdb/episode_53/screenshots/screenshot_1.png", 
+                "Episode 53: App interaction example"
             ],
             [
                 "extracted_episodes_duckdb/episode_73/screenshots/screenshot_1.png",
-                f"Goal: {episode_73['goal']}\nStep: {episode_73['step_instructions'][0]}"
+                "Episode 73: Device control task"
             ]
         ]
         

requirements.txt

@@ -1,6 +1,6 @@
 gradio>=4.0.0
 torch>=2.0.0
-transformers>=4.35.0
+transformers>=4.55.0
 Pillow>=10.0.0
 accelerate>=0.20.0
 huggingface-hub>=0.17.0