Fix doc links (#22274)

docs/source/en/tasks/image_classification.mdx

@@ -403,9 +403,9 @@ Configure the model for training with `compile()`:
 >>> model.compile(optimizer=optimizer, loss=loss)
 ```
 
-To compute the accuracy from the predictions and push your model to the 🤗 Hub, use [Keras callbacks](./main_classes/keras_callbacks).
-Pass your `compute_metrics` function to [KerasMetricCallback](./main_classes/keras_callbacks#transformers.KerasMetricCallback),
-and use the [PushToHubCallback](./main_classes/keras_callbacks#transformers.PushToHubCallback) to upload the model:
+To compute the accuracy from the predictions and push your model to the 🤗 Hub, use [Keras callbacks](../main_classes/keras_callbacks).
+Pass your `compute_metrics` function to [KerasMetricCallback](../main_classes/keras_callbacks#transformers.KerasMetricCallback),
+and use the [PushToHubCallback](../main_classes/keras_callbacks#transformers.PushToHubCallback) to upload the model:
 
 ```py
 >>> from transformers.keras_callbacks import KerasMetricCallback, PushToHubCallback

docs/source/en/tasks/multiple_choice.mdx

@@ -341,7 +341,7 @@ Configure the model for training with [`compile`](https://keras.io/api/models/mo
 >>> model.compile(optimizer=optimizer)
 ```
 
-The last two things to setup before you start training is to compute the accuracy from the predictions, and provide a way to push your model to the Hub. Both are done by using [Keras callbacks](./main_classes/keras_callbacks).
+The last two things to setup before you start training is to compute the accuracy from the predictions, and provide a way to push your model to the Hub. Both are done by using [Keras callbacks](../main_classes/keras_callbacks).
 
 Pass your `compute_metrics` function to [`~transformers.KerasMetricCallback`]:
 

docs/source/en/tasks/semantic_segmentation.mdx

@@ -412,7 +412,7 @@ Convert your datasets to the `tf.data.Dataset` format using the [`~datasets.Data
 ... )
 ```
 
-To compute the accuracy from the predictions and push your model to the 🤗 Hub, use [Keras callbacks](./main_classes/keras_callbacks).
+To compute the accuracy from the predictions and push your model to the 🤗 Hub, use [Keras callbacks](../main_classes/keras_callbacks).
 Pass your `compute_metrics` function to [`KerasMetricCallback`],
 and use the [`PushToHubCallback`] to upload the model:
 

docs/source/en/tasks/sequence_classification.mdx

@@ -267,7 +267,7 @@ Configure the model for training with [`compile`](https://keras.io/api/models/mo
 >>> model.compile(optimizer=optimizer)
 ```
 
-The last two things to setup before you start training is to compute the accuracy from the predictions, and provide a way to push your model to the Hub. Both are done by using [Keras callbacks](./main_classes/keras_callbacks).
+The last two things to setup before you start training is to compute the accuracy from the predictions, and provide a way to push your model to the Hub. Both are done by using [Keras callbacks](../main_classes/keras_callbacks).
 
 Pass your `compute_metrics` function to [`~transformers.KerasMetricCallback`]:
 

docs/source/en/tasks/summarization.mdx

@@ -275,7 +275,7 @@ Configure the model for training with [`compile`](https://keras.io/api/models/mo
 >>> model.compile(optimizer=optimizer)
 ```
 
-The last two things to setup before you start training is to compute the ROUGE score from the predictions, and provide a way to push your model to the Hub. Both are done by using [Keras callbacks](./main_classes/keras_callbacks).
+The last two things to setup before you start training is to compute the ROUGE score from the predictions, and provide a way to push your model to the Hub. Both are done by using [Keras callbacks](../main_classes/keras_callbacks).
 
 Pass your `compute_metrics` function to [`~transformers.KerasMetricCallback`]:
 
@@ -354,7 +354,7 @@ Tokenize the text and return the `input_ids` as PyTorch tensors:
 >>> inputs = tokenizer(text, return_tensors="pt").input_ids
 ```
 
-Use the [`~transformers.generation_utils.GenerationMixin.generate`] method to create the summarization. For more details about the different text generation strategies and parameters for controlling generation, check out the [Text Generation](./main_classes/text_generation) API.
+Use the [`~transformers.generation_utils.GenerationMixin.generate`] method to create the summarization. For more details about the different text generation strategies and parameters for controlling generation, check out the [Text Generation](../main_classes/text_generation) API.
 
 ```py
 >>> from transformers import AutoModelForSeq2SeqLM
@@ -380,7 +380,7 @@ Tokenize the text and return the `input_ids` as TensorFlow tensors:
 >>> inputs = tokenizer(text, return_tensors="tf").input_ids
 ```
 
-Use the [`~transformers.generation_tf_utils.TFGenerationMixin.generate`] method to create the summarization. For more details about the different text generation strategies and parameters for controlling generation, check out the [Text Generation](./main_classes/text_generation) API.
+Use the [`~transformers.generation_tf_utils.TFGenerationMixin.generate`] method to create the summarization. For more details about the different text generation strategies and parameters for controlling generation, check out the [Text Generation](../main_classes/text_generation) API.
 
 ```py
 >>> from transformers import TFAutoModelForSeq2SeqLM

docs/source/en/tasks/token_classification.mdx

@@ -369,7 +369,7 @@ Configure the model for training with [`compile`](https://keras.io/api/models/mo
 >>> model.compile(optimizer=optimizer)
 ```
 
-The last two things to setup before you start training is to compute the seqeval scores from the predictions, and provide a way to push your model to the Hub. Both are done by using [Keras callbacks](./main_classes/keras_callbacks).
+The last two things to setup before you start training is to compute the seqeval scores from the predictions, and provide a way to push your model to the Hub. Both are done by using [Keras callbacks](../main_classes/keras_callbacks).
 
 Pass your `compute_metrics` function to [`~transformers.KerasMetricCallback`]:
 

docs/source/en/tasks/translation.mdx

@@ -284,7 +284,7 @@ Configure the model for training with [`compile`](https://keras.io/api/models/mo
 >>> model.compile(optimizer=optimizer)
 ```
 
-The last two things to setup before you start training is to compute the SacreBLEU metric from the predictions, and provide a way to push your model to the Hub. Both are done by using [Keras callbacks](./main_classes/keras_callbacks).
+The last two things to setup before you start training is to compute the SacreBLEU metric from the predictions, and provide a way to push your model to the Hub. Both are done by using [Keras callbacks](../main_classes/keras_callbacks).
 
 Pass your `compute_metrics` function to [`~transformers.KerasMetricCallback`]:
 
@@ -362,7 +362,7 @@ Tokenize the text and return the `input_ids` as PyTorch tensors:
 >>> inputs = tokenizer(text, return_tensors="pt").input_ids
 ```
 
-Use the [`~transformers.generation_utils.GenerationMixin.generate`] method to create the translation. For more details about the different text generation strategies and parameters for controlling generation, check out the [Text Generation](./main_classes/text_generation) API.
+Use the [`~transformers.generation_utils.GenerationMixin.generate`] method to create the translation. For more details about the different text generation strategies and parameters for controlling generation, check out the [Text Generation](../main_classes/text_generation) API.
 
 ```py
 >>> from transformers import AutoModelForSeq2SeqLM
@@ -388,7 +388,7 @@ Tokenize the text and return the `input_ids` as TensorFlow tensors:
 >>> inputs = tokenizer(text, return_tensors="tf").input_ids
 ```
 
-Use the [`~transformers.generation_tf_utils.TFGenerationMixin.generate`] method to create the translation. For more details about the different text generation strategies and parameters for controlling generation, check out the [Text Generation](./main_classes/text_generation) API.
+Use the [`~transformers.generation_tf_utils.TFGenerationMixin.generate`] method to create the translation. For more details about the different text generation strategies and parameters for controlling generation, check out the [Text Generation](../main_classes/text_generation) API.
 
 ```py
 >>> from transformers import TFAutoModelForSeq2SeqLM