Fix clippy warnings (#466)

src/lib.rs

@@ -91,7 +91,7 @@
 //! ### Manual installation (recommended)
 //!
 //! 1. Download `libtorch` from <https://pytorch.org/get-started/locally/>. This package requires `v2.2`: if this version is no longer available on the "get started" page,
-//! the file should be accessible by modifying the target link, for example `https://download.pytorch.org/libtorch/cu121/libtorch-cxx11-abi-shared-with-deps-2.2.0%2Bcu121.zip` for a Linux version with CUDA12.
+//!     the file should be accessible by modifying the target link, for example `https://download.pytorch.org/libtorch/cu121/libtorch-cxx11-abi-shared-with-deps-2.2.0%2Bcu121.zip` for a Linux version with CUDA12.
 //! 2. Extract the library to a location of your choice
 //! 3. Set the following environment variables
 //! ##### Linux:

src/models/albert/mod.rs

@@ -16,6 +16,7 @@
 //! - Configuration file expected to have a structure following the [Transformers library](https://github.com/huggingface/transformers)
 //! - Model weights are expected to have a structure and parameter names following the [Transformers library](https://github.com/huggingface/transformers). A conversion using the Python utility scripts is required to convert the `.bin` weights to the `.ot` format.
 //! - `BertTokenizer` using a `vocab.txt` vocabulary
+//!
 //! Pretrained models are available and can be downloaded using RemoteResources.
 //!
 //! ```no_run

src/models/bart/bart_model.rs

@@ -369,7 +369,7 @@ fn _shift_tokens_right(input_ids: &Tensor, pad_token_id: i64) -> Tensor {
 /// It is made of the following blocks:
 /// - `encoder`: `BartEncoder` (transformer) made of a vector of encoding layers
 /// - `decoder`: `BartDecoder` (transformer)  made of a vector of decoding layers with self attention and encoder cross-attention.
-/// caching is implemented for the decoder to avoid recalculating static states (encoder key/values and previously calculated decoder key/values)
+///     caching is implemented for the decoder to avoid recalculating static states (encoder key/values and previously calculated decoder key/values)
 /// - `pad_token_id`: padding token id
 pub struct BartModel {
     pub(crate) encoder: BartEncoder,
@@ -437,7 +437,7 @@ impl BartModel {
     /// * `attention_mask` - Optional attention mask of shape (*batch size*, *source_sequence_length*) for the encoder positions. Positions with a mask with value 0 will be masked.
     /// * `decoder_input_ids` - Optional input tensor of shape (*batch size*, *target_sequence_length*). Must be provided when running in generation mode (e.g. initialized with a BOS token)
     /// * `encoder_outputs` - Optional tuple made of a tensor of shape (*batch size*, *source_sequence_length*, *encoder_hidden_dim*) and optional vectors of tensors of length *num_encoder_layers* with shape (*batch size*, *source_sequence_length*, *hidden_size*).
-    /// These correspond to the encoder last hidden state and optional hidden states/attention weights for encoder layers. When provided, the encoder hidden state will not be recalculated. Useful for generation tasks.
+    ///     These correspond to the encoder last hidden state and optional hidden states/attention weights for encoder layers. When provided, the encoder hidden state will not be recalculated. Useful for generation tasks.
     /// * `decoder_attention_mask` - Optional attention mask of shape (*batch size*, *target_sequence_length*) for the decoder positions. Positions with a mask with value 0 will be masked.
     /// * `train` - boolean flag to turn on/off the dropout layers in the model. Should be set to false for inference.
     ///
@@ -597,7 +597,7 @@ impl BartForConditionalGeneration {
     /// * `input_ids` - Optional input tensor of shape (*batch size*, *source_sequence_length*). Must be provided when not running in generation mode
     /// * `attention_mask` - Optional attention mask of shape (*batch size*, *source_sequence_length*) for the encoder positions. Positions with a mask with value 0 will be masked.
     /// * `encoder_outputs` - Optional tuple made of a tensor of shape (*batch size*, *source_sequence_length*, *encoder_hidden_dim*) and optional vectors of tensors of length *num_encoder_layers* with shape (*batch size*, *source_sequence_length*, *hidden_size*).
-    /// These correspond to the encoder last hidden state and optional hidden states/attention weights for encoder layers. When provided, the encoder hidden state will not be recalculated. Useful for generation tasks.
+    ///     These correspond to the encoder last hidden state and optional hidden states/attention weights for encoder layers. When provided, the encoder hidden state will not be recalculated. Useful for generation tasks.
     /// * `decoder_input_ids` - Optional input tensor of shape (*batch size*, *target_sequence_length*). Must be provided when running in generation mode (e.g. initialized with a BOS token)
     /// * `decoder_attention_mask` - Optional attention mask of shape (*batch size*, *target_sequence_length*) for the decoder positions. Positions with a mask with value 0 will be masked.
     /// * `train` - boolean flag to turn on/off the dropout layers in the model. Should be set to false for inference.
@@ -798,7 +798,7 @@ impl BartForSequenceClassification {
     /// * `input_ids` - Optional input tensor of shape (*batch size*, *source_sequence_length*). Must be provided when not running in generation mode
     /// * `attention_mask` - Optional attention mask of shape (*batch size*, *source_sequence_length*) for the encoder positions. Positions with a mask with value 0 will be masked.
     /// * `encoder_outputs` - Optional tuple made of a tensor of shape (*batch size*, *source_sequence_length*, *encoder_hidden_dim*) and optional vectors of tensors of length *num_encoder_layers* with shape (*batch size*, *source_sequence_length*, *hidden_size*).
-    /// These correspond to the encoder last hidden state and optional hidden states/attention weights for encoder layers. When provided, the encoder hidden state will not be recalculated. Useful for generation tasks.
+    ///     These correspond to the encoder last hidden state and optional hidden states/attention weights for encoder layers. When provided, the encoder hidden state will not be recalculated. Useful for generation tasks.
     /// * `decoder_input_ids` - Optional input tensor of shape (*batch size*, *target_sequence_length*). Must be provided when running in generation mode (e.g. initialized with a BOS token)
     /// * `decoder_attention_mask` - Optional attention mask of shape (*batch size*, *target_sequence_length*) for the decoder positions. Positions with a mask with value 0 will be masked.
     /// * `train` - boolean flag to turn on/off the dropout layers in the model. Should be set to false for inference.

src/models/bart/mod.rs

@@ -11,6 +11,7 @@
 //! - Configuration file expected to have a structure following the [Transformers library](https://github.com/huggingface/transformers)
 //! - Model weights are expected to have a structure and parameter names following the [Transformers library](https://github.com/huggingface/transformers). A conversion using the Python utility scripts is required to convert the `.bin` weights to the `.ot` format.
 //! - `RobertaTokenizer` using a `vocab.txt` vocabulary and `merges.txt` 2-gram merges
+//!
 //! Pretrained models are available and can be downloaded using RemoteResources.
 //!
 //! ```no_run

src/models/bert/mod.rs

@@ -16,6 +16,7 @@
 //! - Configuration file expected to have a structure following the [Transformers library](https://github.com/huggingface/transformers)
 //! - Model weights are expected to have a structure and parameter names following the [Transformers library](https://github.com/huggingface/transformers). A conversion using the Python utility scripts is required to convert the `.bin` weights to the `.ot` format.
 //! - `BertTokenizer` using a `vocab.txt` vocabulary
+//!
 //! Pretrained models are available and can be downloaded using RemoteResources.
 //!
 //! ```no_run

src/models/deberta/mod.rs

@@ -12,6 +12,7 @@
 //! - Configuration file expected to have a structure following the [Transformers library](https://github.com/huggingface/transformers)
 //! - Model weights are expected to have a structure and parameter names following the [Transformers library](https://github.com/huggingface/transformers). A conversion using the Python utility scripts is required to convert the `.bin` weights to the `.ot` format.
 //! - `DebertaTokenizer` using a `vocab.json` vocabulary and `merges.txt` merges file
+//!
 //! Pretrained models for a number of language pairs are available and can be downloaded using RemoteResources.
 //!
 //! ```no_run

src/models/deberta_v2/mod.rs

@@ -12,6 +12,7 @@
 //! - Configuration file expected to have a structure following the [Transformers library](https://github.com/huggingface/transformers)
 //! - Model weights are expected to have a structure and parameter names following the [Transformers library](https://github.com/huggingface/transformers). A conversion using the Python utility scripts is required to convert the `.bin` weights to the `.ot` format.
 //! - `DebertaV2Tokenizer` using a `spiece.model` SentencePiece model file
+//!
 //! Pretrained models for a number of language pairs are available and can be downloaded using RemoteResources.
 //!
 //! ```no_run

src/models/distilbert/mod.rs

@@ -14,6 +14,7 @@
 //! - Configuration file expected to have a structure following the [Transformers library](https://github.com/huggingface/transformers)
 //! - Model weights are expected to have a structure and parameter names following the [Transformers library](https://github.com/huggingface/transformers). A conversion using the Python utility scripts is required to convert the `.bin` weights to the `.ot` format.
 //! - `BertTokenizer` using a `vocab.txt` vocabulary
+//!
 //! Pretrained models are available and can be downloaded using RemoteResources.
 //!
 //! ```no_run

src/models/electra/mod.rs

@@ -19,6 +19,7 @@
 //! - Configuration file expected to have a structure following the [Transformers library](https://github.com/huggingface/transformers)
 //! - Model weights are expected to have a structure and parameter names following the [Transformers library](https://github.com/huggingface/transformers). A conversion using the Python utility scripts is required to convert the `.bin` weights to the `.ot` format.
 //! - `BertTokenizer` using a `vocab.txt` vocabulary
+//!
 //! Pretrained models are available and can be downloaded using RemoteResources.
 //!
 //! ```no_run

src/models/fnet/mod.rs

@@ -14,6 +14,7 @@
 //! - Configuration file expected to have a structure following the [Transformers library](https://github.com/huggingface/transformers)
 //! - Model weights are expected to have a structure and parameter names following the [Transformers library](https://github.com/huggingface/transformers). A conversion using the Python utility scripts is required to convert the `.bin` weights to the `.ot` format.
 //! - `FNetTokenizer` using a `spiece.model` SentencePiece (BPE) model file
+//!
 //! Pretrained models are available and can be downloaded using RemoteResources.
 //!
 //! ```no_run

src/models/gpt2/mod.rs

@@ -11,6 +11,7 @@
 //! - Configuration file expected to have a structure following the [Transformers library](https://github.com/huggingface/transformers)
 //! - Model weights are expected to have a structure and parameter names following the [Transformers library](https://github.com/huggingface/transformers). A conversion using the Python utility scripts is required to convert the `.bin` weights to the `.ot` format.
 //! - `Gpt2Tokenizer` using a `vocab.txt` vocabulary and `merges.txt` 2-gram merges
+//!
 //! Pretrained models are available and can be downloaded using RemoteResources.
 //!
 //! ```no_run

src/models/longt5/longt5_model.rs

@@ -174,7 +174,7 @@ impl From<&LongT5Config> for T5Config {
 /// It is made of the following blocks:
 /// - `encoder`: `T5Stack` (transformer) made of a vector of encoding layers
 /// - `decoder`: `T5Stack` (transformer)  made of a vector of decoding layers with self attention and encoder cross-attention.
-/// caching is implemented for the decoder to avoid recalculating static states (encoder key/values and previously calculated decoder key/values)
+///     caching is implemented for the decoder to avoid recalculating static states (encoder key/values and previously calculated decoder key/values)
 /// - `embeddings`: `nn::Embedding` Shared embeddings for the encoder and decoder.
 pub struct LongT5Model {
     pub(crate) encoder: LongT5Stack,
@@ -248,7 +248,7 @@ impl LongT5Model {
     /// * `input_ids` - Optional input tensor of shape (*batch size*, *source_sequence_length*). This or `input_embeds` must be provided.
     /// * `attention_mask` - Optional attention mask of shape (*batch size*, *source_sequence_length*) for the encoder positions. Positions with a mask with value 0 will be masked.
     /// * `encoder_outputs` - Optional tuple made of a tensor of shape (*batch size*, *source_sequence_length*, *encoder_hidden_dim*) and optional vectors of tensors of length *num_encoder_layers* with shape (*batch size*, *source_sequence_length*, *hidden_size*).
-    /// These correspond to the encoder last hidden state and optional hidden states/attention weights for encoder layers. When provided, the encoder hidden state will not be recalculated. Useful for generation tasks.
+    ///     These correspond to the encoder last hidden state and optional hidden states/attention weights for encoder layers. When provided, the encoder hidden state will not be recalculated. Useful for generation tasks.
     /// * `decoder_input_ids` - Optional input tensor of shape (*batch size*, *target_sequence_length*). This or `decoder_input_embeds` must be provided.
     /// * `decoder_attention_mask` - Optional attention mask of shape (*batch size*, *target_sequence_length*) for the decoder positions. Positions with a mask with value 0 will be masked.
     /// * `input_embeds` - Optional input tensor of shape (*batch size*, *source_sequence_length*, *embeddings dimension*). This or `input_ids` must be provided.
@@ -436,7 +436,7 @@ impl LongT5ForConditionalGeneration {
     /// * `input_ids` - Optional input tensor of shape (*batch size*, *source_sequence_length*). This or `input_embeds` must be provided.
     /// * `attention_mask` - Optional attention mask of shape (*batch size*, *source_sequence_length*) for the encoder positions. Positions with a mask with value 0 will be masked.
     /// * `encoder_outputs` - Optional tuple made of a tensor of shape (*batch size*, *source_sequence_length*, *encoder_hidden_dim*) and optional vectors of tensors of length *num_encoder_layers* with shape (*batch size*, *source_sequence_length*, *hidden_size*).
-    /// These correspond to the encoder last hidden state and optional hidden states/attention weights for encoder layers. When provided, the encoder hidden state will not be recalculated. Useful for generation tasks.
+    ///     These correspond to the encoder last hidden state and optional hidden states/attention weights for encoder layers. When provided, the encoder hidden state will not be recalculated. Useful for generation tasks.
     /// * `decoder_input_ids` - Optional input tensor of shape (*batch size*, *target_sequence_length*). This or `decoder_input_embeds` must be provided.
     /// * `decoder_attention_mask` - Optional attention mask of shape (*batch size*, *target_sequence_length*) for the decoder positions. Positions with a mask with value 0 will be masked.
     /// * `input_embeds` - Optional input tensor of shape (*batch size*, *source_sequence_length*, *embeddings dimension*). This or `input_ids` must be provided.

src/models/m2m_100/m2m_100_model.rs

@@ -126,7 +126,7 @@ fn _shift_tokens_right(
 /// It is made of the following blocks:
 /// - `encoder`: `M2M100Encoder` (transformer) made of a vector of encoding layers
 /// - `decoder`: `M2M100Decoder` (transformer)  made of a vector of decoding layers with self attention and encoder cross-attention.
-/// caching is implemented for the decoder to avoid recalculating static states (encoder key/values and previously calculated decoder key/values)
+///     caching is implemented for the decoder to avoid recalculating static states (encoder key/values and previously calculated decoder key/values)
 /// - `pad_token_id`: padding token id
 pub struct M2M100Model {
     pub(crate) encoder: M2M100Encoder,
@@ -197,7 +197,7 @@ impl M2M100Model {
     /// * `attention_mask` - Optional attention mask of shape (*batch size*, *source_sequence_length*) for the encoder positions. Positions with a mask with value 0 will be masked.
     /// * `decoder_input_ids` - Optional input tensor of shape (*batch size*, *target_sequence_length*). Must be provided when running in generation mode (e.g. initialized with a BOS token)
     /// * `encoder_outputs` - Optional tuple made of a tensor of shape (*batch size*, *source_sequence_length*, *encoder_hidden_dim*) and optional vectors of tensors of length *num_encoder_layers* with shape (*batch size*, *source_sequence_length*, *hidden_size*).
-    /// These correspond to the encoder last hidden state and optional hidden states/attention weights for encoder layers. When provided, the encoder hidden state will not be recalculated. Useful for generation tasks.
+    ///     These correspond to the encoder last hidden state and optional hidden states/attention weights for encoder layers. When provided, the encoder hidden state will not be recalculated. Useful for generation tasks.
     /// * `decoder_attention_mask` - Optional attention mask of shape (*batch size*, *target_sequence_length*) for the decoder positions. Positions with a mask with value 0 will be masked.
     /// * `train` - boolean flag to turn on/off the dropout layers in the model. Should be set to false for inference.
     ///
@@ -365,7 +365,7 @@ impl M2M100ForConditionalGeneration {
     /// * `input_ids` - Optional input tensor of shape (*batch size*, *source_sequence_length*). Must be provided when not running in generation mode
     /// * `attention_mask` - Optional attention mask of shape (*batch size*, *source_sequence_length*) for the encoder positions. Positions with a mask with value 0 will be masked.
     /// * `encoder_outputs` - Optional tuple made of a tensor of shape (*batch size*, *source_sequence_length*, *encoder_hidden_dim*) and optional vectors of tensors of length *num_encoder_layers* with shape (*batch size*, *source_sequence_length*, *hidden_size*).
-    /// These correspond to the encoder last hidden state and optional hidden states/attention weights for encoder layers. When provided, the encoder hidden state will not be recalculated. Useful for generation tasks.
+    ///     These correspond to the encoder last hidden state and optional hidden states/attention weights for encoder layers. When provided, the encoder hidden state will not be recalculated. Useful for generation tasks.
     /// * `decoder_input_ids` - Optional input tensor of shape (*batch size*, *target_sequence_length*). Must be provided when running in generation mode (e.g. initialized with a BOS token)
     /// * `decoder_attention_mask` - Optional attention mask of shape (*batch size*, *target_sequence_length*) for the decoder positions. Positions with a mask with value 0 will be masked.
     /// * `train` - boolean flag to turn on/off the dropout layers in the model. Should be set to false for inference.

src/models/m2m_100/mod.rs

@@ -12,6 +12,7 @@
 //! - Configuration file expected to have a structure following the [Transformers library](https://github.com/huggingface/transformers)
 //! - Model weights are expected to have a structure and parameter names following the [Transformers library](https://github.com/huggingface/transformers). A conversion using the Python utility scripts is required to convert the `.bin` weights to the `.ot` format.
 //! - `M2M100Tokenizer` using a `config.json` vocabulary and a `spiece.model` SentencePiece BPE model
+//!
 //! Pretrained models are available and can be downloaded using RemoteResources.
 //!
 //! ```no_run