update

app_regression.py

@@ -15,10 +15,9 @@ from typing import List
 
 
 processor = AutoProcessor.from_pretrained("Mantis-VL/mantis-8b-idefics2-video-eval-20k-mantis-2epoch_4096_regression")
-model = Idefics2ForSequenceClassification.from_pretrained("Mantis-VL/mantis-8b-idefics2-video-eval-20k-mantis-2epoch_4096_regression", torch_dtype=torch.bfloat16)
-model.eval()
+model = Idefics2ForSequenceClassification.from_pretrained("Mantis-VL/mantis-8b-idefics2-video-eval-20k-mantis-2epoch_4096_regression", torch_dtype=torch.bfloat16).eval()
 
-MAX_NUM_FRAMES = 8
+MAX_NUM_FRAMES = 16
 conv_template = conv_templates["idefics_2"]
 
 with open("./examples/all_subsets.json", 'r') as f:
@@ -92,9 +91,9 @@ def score(prompt:str, images:List[Image.Image]):
     
     flatten_images = [Image.open(x) if isinstance(x, str) else x for x in flatten_images]
     inputs = processor(text=prompt, images=flatten_images, return_tensors="pt")
-    print(processor.tokenizer.decode(inputs["input_ids"][0], skip_special_tokens=False))
     inputs = {k: v.to(model.device) for k, v in inputs.items()}
-    outputs = model(**inputs)
+    with torch.no_grad():
+        outputs = model(**inputs)
     
     logits = outputs.logits
     num_aspects = logits.shape[-1]