transformers - 💡(How to fix) Fix return_tensors is silently ignored when text_kwargs is explicitly passed

from transformers import Qwen2VLProcessor

processor = Qwen2VLProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct")

# Works — no text_kwargs dict
out1 = processor(text="hello", return_tensors="pt")
print(type(out1["input_ids"]))  # Tensor ✓

# Silently breaks — flat return_tensors + text_kwargs dict
out2 = processor(text="hello", return_tensors="pt",
                 text_kwargs={"padding": "max_length", "max_length": 32})
print(type(out2["input_ids"]))  # list ✗ — should be Tensor!

# Workaround — put return_tensors inside text_kwargs
out3 = processor(text="hello",
                 text_kwargs={"padding": "max_length", "max_length": 32, "return_tensors": "pt"})
print(type(out3["input_ids"]))  # Tensor ✓

---

<class 'torch.Tensor'>
<class 'list'>
<class 'torch.Tensor'>

---

<class 'torch.Tensor'>
<class 'torch.Tensor'>
<class 'torch.Tensor'>

---

if modality in kwargs:
    kwarg_value = kwargs[modality].pop(modality_key, "__empty__")  # not found → "__empty__"
    # NO fallthrough to elif branch
elif modality_key in kwargs:
    kwarg_value = kwargs.get(modality_key, "__empty__")

---

if modality in kwargs:
    kwarg_value = kwargs[modality].pop(modality_key, "__empty__")
    if kwarg_value != "__empty__" and modality_key in non_modality_kwargs:
        raise ValueError(...)
else:
    kwarg_value = "__empty__"

# Fallback: if not found in modality dict, check flat kwargs
if (isinstance(kwarg_value, str) and kwarg_value == "__empty__") and modality_key in kwargs:
    kwarg_value = kwargs.get(modality_key, "__empty__")

---

processor(text="hello", text_kwargs={"padding": "max_length", "return_tensors": "pt"})