mypy

src/torchmetrics/functional/multimodal/clip_score.py

@@ -51,7 +51,9 @@ def _clip_score_update(
             f"Expected the number of images and text examples to be the same but got {len(images)} and {len(text)}"
         )
     device = images[0].device
-    processed_input = processor(text=text, images=[i.cpu() for i in images], return_tensors="pt", padding=True)
+    processed_input = processor(
+        text=text, images=[i.cpu() for i in images], return_tensors="pt", padding=True
+    )  # type: ignore
 
     img_features = model.get_image_features(processed_input["pixel_values"].to(device))
     img_features = img_features / img_features.norm(p=2, dim=-1, keepdim=True)

src/torchmetrics/functional/text/infolm.py

@@ -384,7 +384,7 @@ def _get_batch_distribution(
     for mask_idx in range(seq_len):
         input_ids = batch["input_ids"].clone()
         input_ids[:, mask_idx] = special_tokens_map["mask_token_id"]
-        logits_distribution = model(input_ids, batch["attention_mask"]).logits
+        logits_distribution = model(input_ids, batch["attention_mask"]).logits  # type: ignore
         # [batch_size, seq_len, vocab_size] -> [batch_size, vocab_size]
         logits_distribution = logits_distribution[:, mask_idx, :]
         prob_distribution = F.softmax(logits_distribution / temperature, dim=-1)