fix: compatibility patches for newer transformers (4.50+ / 5.x)

configuration_florence2.py

@@ -262,7 +262,7 @@ class Florence2LanguageConfig(PretrainedConfig):
         )
 
         # ensure backward compatibility for BART CNN models
-        if self.forced_bos_token_id is None and kwargs.get("force_bos_token_to_be_generated", False):
+        if getattr(self, "forced_bos_token_id", None) is None and kwargs.get("force_bos_token_to_be_generated", False):
             self.forced_bos_token_id = self.bos_token_id
             warnings.warn(
                 f"Please make sure the config includes `forced_bos_token_id={self.bos_token_id}` in future versions. "

modeling_florence2.py

@@ -554,7 +554,13 @@ class DaViT(nn.Module):
         assert self.num_stages == len(self.num_heads) == len(self.num_groups)
 
         num_stages = len(embed_dims)
-        dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths)*2)]
+        _n_dpr = sum(depths) * 2
+        if _n_dpr == 0:
+            dpr = []
+        elif _n_dpr == 1:
+            dpr = [0.0]
+        else:
+            dpr = [drop_path_rate * i / (_n_dpr - 1) for i in range(_n_dpr)]
 
         depth_offset = 0
         convs = []
@@ -2331,21 +2337,8 @@ class Florence2PreTrainedModel(PreTrainedModel):
     supports_gradient_checkpointing = True
     _skip_keys_device_placement = "past_key_values"
 
-    @property
-    def _supports_flash_attn_2(self):
-        """
-        Retrieve language_model's attribute to check whether the model supports
-        Flash Attention 2 or not.
-        """
-        return self.language_model._supports_flash_attn_2
-
-    @property
-    def _supports_sdpa(self):
-        """
-        Retrieve language_model's attribute to check whether the model supports
-        SDPA or not.
-        """
-        return self.language_model._supports_sdpa
+    _supports_flash_attn_2 = False
+    _supports_sdpa = True
 
 
 FLORENCE2_INPUTS_DOCSTRING = r"""

processing_florence2.py

@@ -84,7 +84,7 @@ class Florence2Processor(ProcessorMixin):
 
         tokens_to_add = {
                 'additional_special_tokens': \
-                    tokenizer.additional_special_tokens + \
+                    list(getattr(tokenizer, 'additional_special_tokens', []) or []) + \
                     ['<od>', '</od>', '<ocr>', '</ocr>'] + \
                     [f'<loc_{x}>' for x in range(1000)] + \
                     ['<cap>', '</cap>', '<ncap>', '</ncap>','<dcap>', '</dcap>', '<grounding>', '</grounding>', '<seg>', '</seg>', '<sep>', '<region_cap>', '</region_cap>', '<region_to_desciption>', '</region_to_desciption>', '<proposal>', '</proposal>', '<poly>', '</poly>', '<and>']