Update models/visual_analyzer.py

models/visual_analyzer.py

@@ -105,9 +105,13 @@ Respond with just the emotion."""
         """Load the Qwen2-VL model with quantization."""
         with LogTimer(logger, "Loading Qwen2-VL model"):
             try:
+                import os
                 import torch
                 from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
 
+                # Get HuggingFace token from environment (optional - model is open access)
+                hf_token = os.environ.get("HF_TOKEN")
+
                 # Determine device
                 if self.config.device == "cuda" and torch.cuda.is_available():
                     self._device = "cuda"
@@ -120,6 +124,7 @@ Respond with just the emotion."""
                 self.processor = AutoProcessor.from_pretrained(
                     self.config.visual_model_id,
                     trust_remote_code=True,
+                    token=hf_token,
                 )
 
                 # Load model with quantization
@@ -158,6 +163,7 @@ Respond with just the emotion."""
 
                 self.model = Qwen2VLForConditionalGeneration.from_pretrained(
                     self.config.visual_model_id,
+                    token=hf_token,
                     **model_kwargs,
                 )