[bugfix]: preserve tokenizer_kwargs customizations across update_model_arch

TextEncoderArchConfig.__post_init__ rebuilt tokenizer_kwargs from scratch, and
TextEncoderLoader.load -> update_model_arch re-runs __post_init__, silently
wiping customizations applied by pipeline configs (kandinsky5/gen3c/longcat
set 'padding'; multi-prompt kandinsky5 runs then crash on ragged sequences).
Merge defaults under existing keys instead of rebuilding.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

fastvideo/configs/models/encoders/base.py

@@ -43,11 +43,16 @@ class TextEncoderArchConfig(EncoderArchConfig):
     require_processor: bool = False
 
     def __post_init__(self) -> None:
-        self.tokenizer_kwargs = {
+        # update_model_arch re-runs __post_init__ after pipeline configs may
+        # have customized tokenizer_kwargs (e.g. kandinsky5/gen3c/longcat set
+        # "padding"); rebuilding the dict here would silently wipe those
+        # customizations, so only fill in defaults for keys not already set.
+        defaults = {
             "truncation": True,
             "max_length": self.text_len,
             "return_tensors": "pt",
         }
+        self.tokenizer_kwargs = defaults | self.tokenizer_kwargs
 
 
 @dataclass