From 4ab5fb8941a38d172b3883c152c34ae2a0b83a68 Mon Sep 17 00:00:00 2001
From: hugo-syn <61210734+hugo-syn@users.noreply.github.com>
Date: Fri, 5 Jan 2024 22:19:15 +0100
Subject: [PATCH] chore: Fix typo s/exclusivelly/exclusively/ (#28361)
---
docs/source/en/internal/generation_utils.md | 4 ++--
src/transformers/generation/logits_process.py | 6 +++---
src/transformers/models/llama/modeling_llama.py | 2 +-
src/transformers/models/llava/modeling_llava.py | 2 +-
src/transformers/models/mistral/modeling_mistral.py | 2 +-
src/transformers/models/mixtral/modeling_mixtral.py | 2 +-
src/transformers/models/persimmon/modeling_persimmon.py | 2 +-
src/transformers/models/phi/modeling_phi.py | 2 +-
src/transformers/models/vipllava/modeling_vipllava.py | 2 +-
9 files changed, 12 insertions(+), 12 deletions(-)
diff --git a/docs/source/en/internal/generation_utils.md b/docs/source/en/internal/generation_utils.md
index 40969f227e..ce7fcc5319 100644
--- a/docs/source/en/internal/generation_utils.md
+++ b/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
diff --git a/src/transformers/generation/logits_process.py b/src/transformers/generation/logits_process.py
index 4b9b91cd80..dea6f44c3a 100644
--- a/src/transformers/generation/logits_process.py
+++ b/src/transformers/generation/logits_process.py
@@ -1889,7 +1889,7 @@ class ClassifierFreeGuidanceLogitsProcessor(LogitsProcessor):
- 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)
@@ -1948,7 +1948,7 @@ class AlternatingCodebooksLogitsProcessor(LogitsProcessor):
- 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):
- 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.
diff --git a/src/transformers/models/llama/modeling_llama.py b/src/transformers/models/llama/modeling_llama.py
index 5f54fea8c4..8d8b012979 100644
--- a/src/transformers/models/llama/modeling_llama.py
+++ b/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) :]
diff --git a/src/transformers/models/llava/modeling_llava.py b/src/transformers/models/llava/modeling_llava.py
index 54f700bbd7..e8f925938a 100644
--- a/src/transformers/models/llava/modeling_llava.py
+++ b/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) :]
diff --git a/src/transformers/models/mistral/modeling_mistral.py b/src/transformers/models/mistral/modeling_mistral.py
index c8b5c21177..5b21b64f69 100644
--- a/src/transformers/models/mistral/modeling_mistral.py
+++ b/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) :]
diff --git a/src/transformers/models/mixtral/modeling_mixtral.py b/src/transformers/models/mixtral/modeling_mixtral.py
index a32b9b1457..71eb897441 100644
--- a/src/transformers/models/mixtral/modeling_mixtral.py
+++ b/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) :]
diff --git a/src/transformers/models/persimmon/modeling_persimmon.py b/src/transformers/models/persimmon/modeling_persimmon.py
index 92a528b17d..4bffbae38e 100644
--- a/src/transformers/models/persimmon/modeling_persimmon.py
+++ b/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) :]
diff --git a/src/transformers/models/phi/modeling_phi.py b/src/transformers/models/phi/modeling_phi.py
index 7e4235f4f6..be568c62c7 100644
--- a/src/transformers/models/phi/modeling_phi.py
+++ b/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) :]
diff --git a/src/transformers/models/vipllava/modeling_vipllava.py b/src/transformers/models/vipllava/modeling_vipllava.py
index 8aa74857af..c1aa948580 100644
--- a/src/transformers/models/vipllava/modeling_vipllava.py
+++ b/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) :]