Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)` attention_mas

Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)` attention_mas

Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)` attention_mas

Apply LlamaRMSNorm to the input hidden states. Args: hidden_states (torch.Tensor): Input hidden states. R

Forward pass of the LlamaRotaryEmbedding module. Args: x (torch.Tensor): Input tensor of shape [bs, num_attention_he

Forward pass of the MLP. Args: x: Input tensor. Returns: torch.Tensor: Output tensor.

Forward pass for the LlamaDecoderLayer. Args: hidden_states (torch.FloatTensor): Input tensor of shape `(batch, seq_

r""" Args: labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): Labels for computi

r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for computing the sequence classification/regressi

Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)` attention_mas

r""" Args: labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): Labels for computing

r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for computing the sequence classification/regression

Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)` attention_mask (

r""" Args: labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): Labels for computing

r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for computing the sequence classification/regression

r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for computing the sequence classification/regression

Args: hidden_states (`torch.FloatTensor`): input to the layer of shape `(batch, seq_len, embed_dim)` attention_mas

Apply LlamaRMSNorm to the input hidden states. Args: hidden_states (torch.Tensor): Input hidden states. Returns

Forward pass of the LlamaRotaryEmbedding module. Args: x (torch.Tensor): Input tensor of shape [bs, num_attention_heads,

Forward pass of the MLP. Args: x: Input tensor. Returns: torch.Tensor: Output tensor.

Forward pass for the LlamaDecoderLayer. Args: hidden_states (torch.FloatTensor): Input tensor of shape `(batch, seq_len,

r""" Args: labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): Labels for computing

r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for computing the sequence classification/regression

r""" labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*): Labels for computing the masked language mo

r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for computing the sequence classification/regression

r""" labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*): Labels for computing the sequence classification/regression