rope delta order

Author: ArthurZucker

src/transformers/models/glm4v/modeling_glm4v.py

@@ -1424,6 +1424,8 @@ def forward(
         **kwargs: Unpack[TransformersKwargs],
     ) -> Union[tuple, Glm4vCausalLMOutputWithPast]:
         r"""
+        rope_deltas (`torch.LongTensor` of shape `(batch_size, )`, *optional*):
+            The rope index difference between sequence length and multimodal rope.
         labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
             Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
             config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
@@ -1432,8 +1434,6 @@ def forward(
             The temporal, height and width of feature shape of each image in LLM.
         video_grid_thw (`torch.LongTensor` of shape `(num_videos, 3)`, *optional*):
             The temporal, height and width of feature shape of each video in LLM.
-        rope_deltas (`torch.LongTensor` of shape `(batch_size, )`, *optional*):
-            The rope index difference between sequence length and multimodal rope.
 
         Example: