chore: Fix typo s/exclusivelly/exclusively/ (#28361)

docs/source/en/internal/generation_utils.md

@@ -317,7 +317,7 @@ generation.
 
 ## StoppingCriteria
 
-A [`StoppingCriteria`] can be used to change when to stop generation (other than EOS token). Please note that this is exclusivelly available to our PyTorch implementations.
+A [`StoppingCriteria`] can be used to change when to stop generation (other than EOS token). Please note that this is exclusively available to our PyTorch implementations.
 
 [[autodoc]] StoppingCriteria
     - __call__
@@ -333,7 +333,7 @@ A [`StoppingCriteria`] can be used to change when to stop generation (other than
 
 ## Constraints
 
-A [`Constraint`] can be used to force the generation to include specific tokens or sequences in the output. Please note that this is exclusivelly available to our PyTorch implementations.
+A [`Constraint`] can be used to force the generation to include specific tokens or sequences in the output. Please note that this is exclusively available to our PyTorch implementations.
 
 [[autodoc]] Constraint
 

src/transformers/generation/logits_process.py

@@ -1889,7 +1889,7 @@ class ClassifierFreeGuidanceLogitsProcessor(LogitsProcessor):
 
     <Tip warning={true}>
 
-    This logits processor is exclusivelly compatible with
+    This logits processor is exclusively compatible with
     [MusicGen](https://huggingface.co/docs/transformers/main/en/model_doc/musicgen)
 
     </Tip>
@@ -1948,7 +1948,7 @@ class AlternatingCodebooksLogitsProcessor(LogitsProcessor):
 
     <Tip warning={true}>
 
-    This logits processor is exclusivelly compatible with
+    This logits processor is exclusively compatible with
     [Bark](https://huggingface.co/docs/transformers/en/model_doc/bark)'s fine submodel. See the model documentation
     for examples.
 
@@ -2109,7 +2109,7 @@ class BarkEosPrioritizerLogitsProcessor(LogitsProcessor):
 
     <Tip warning={true}>
 
-    This logits processor is exclusivelly compatible with
+    This logits processor is exclusively compatible with
     [Bark](https://huggingface.co/docs/transformers/en/model_doc/bark). See the model documentation for examples.
 
     </Tip>

src/transformers/models/llama/modeling_llama.py

@@ -1240,7 +1240,7 @@ class LlamaForCausalLM(LlamaPreTrainedModel):
 
             # Keep only the unprocessed tokens:
             # 1 - If the length of the attention_mask exceeds the length of input_ids, then we are in a setting where
-            # some of the inputs are exclusivelly passed as part of the cache (e.g. when passing input_embeds as
+            # some of the inputs are exclusively passed as part of the cache (e.g. when passing input_embeds as
             # input)
             if attention_mask is not None and attention_mask.shape[1] > input_ids.shape[1]:
                 input_ids = input_ids[:, -(attention_mask.shape[1] - past_length) :]

src/transformers/models/llava/modeling_llava.py

@@ -504,7 +504,7 @@ class LlavaForConditionalGeneration(LlavaPreTrainedModel):
 
             # Keep only the unprocessed tokens:
             # 1 - If the length of the attention_mask exceeds the length of input_ids, then we are in a setting where
-            # some of the inputs are exclusivelly passed as part of the cache (e.g. when passing input_embeds as
+            # some of the inputs are exclusively passed as part of the cache (e.g. when passing input_embeds as
             # input)
             if attention_mask is not None and attention_mask.shape[1] > input_ids.shape[1]:
                 input_ids = input_ids[:, -(attention_mask.shape[1] - past_length) :]

src/transformers/models/mistral/modeling_mistral.py

@@ -1207,7 +1207,7 @@ class MistralForCausalLM(MistralPreTrainedModel):
 
             # Keep only the unprocessed tokens:
             # 1 - If the length of the attention_mask exceeds the length of input_ids, then we are in a setting where
-            # some of the inputs are exclusivelly passed as part of the cache (e.g. when passing input_embeds as
+            # some of the inputs are exclusively passed as part of the cache (e.g. when passing input_embeds as
             # input)
             if attention_mask is not None and attention_mask.shape[1] > input_ids.shape[1]:
                 input_ids = input_ids[:, -(attention_mask.shape[1] - past_length) :]

src/transformers/models/mixtral/modeling_mixtral.py

@@ -1387,7 +1387,7 @@ class MixtralForCausalLM(MixtralPreTrainedModel):
 
             # Keep only the unprocessed tokens:
             # 1 - If the length of the attention_mask exceeds the length of input_ids, then we are in a setting where
-            # some of the inputs are exclusivelly passed as part of the cache (e.g. when passing input_embeds as
+            # some of the inputs are exclusively passed as part of the cache (e.g. when passing input_embeds as
             # input)
             if attention_mask is not None and attention_mask.shape[1] > input_ids.shape[1]:
                 input_ids = input_ids[:, -(attention_mask.shape[1] - past_length) :]

src/transformers/models/persimmon/modeling_persimmon.py

@@ -838,7 +838,7 @@ class PersimmonForCausalLM(PersimmonPreTrainedModel):
 
             # Keep only the unprocessed tokens:
             # 1 - If the length of the attention_mask exceeds the length of input_ids, then we are in a setting where
-            # some of the inputs are exclusivelly passed as part of the cache (e.g. when passing input_embeds as
+            # some of the inputs are exclusively passed as part of the cache (e.g. when passing input_embeds as
             # input)
             if attention_mask is not None and attention_mask.shape[1] > input_ids.shape[1]:
                 input_ids = input_ids[:, -(attention_mask.shape[1] - past_length) :]

src/transformers/models/phi/modeling_phi.py

@@ -1095,7 +1095,7 @@ class PhiForCausalLM(PhiPreTrainedModel):
 
             # Keep only the unprocessed tokens:
             # 1 - If the length of the attention_mask exceeds the length of input_ids, then we are in a setting where
-            # some of the inputs are exclusivelly passed as part of the cache (e.g. when passing input_embeds as
+            # some of the inputs are exclusively passed as part of the cache (e.g. when passing input_embeds as
             # input)
             if attention_mask is not None and attention_mask.shape[1] > input_ids.shape[1]:
                 input_ids = input_ids[:, -(attention_mask.shape[1] - past_length) :]

src/transformers/models/vipllava/modeling_vipllava.py

@@ -503,7 +503,7 @@ class VipLlavaForConditionalGeneration(VipLlavaPreTrainedModel):
 
             # Keep only the unprocessed tokens:
             # 1 - If the length of the attention_mask exceeds the length of input_ids, then we are in a setting where
-            # some of the inputs are exclusivelly passed as part of the cache (e.g. when passing input_embeds as
+            # some of the inputs are exclusively passed as part of the cache (e.g. when passing input_embeds as
             # input)
             if attention_mask is not None and attention_mask.shape[1] > input_ids.shape[1]:
                 input_ids = input_ids[:, -(attention_mask.shape[1] - past_length) :]