src/hyperpod_nemo_adapter/collections/model/nlp/custom_models/modeling_deepseek.py [1246:1253]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    @add_start_docstrings_to_model_forward(DeepseekV3_INPUTS_DOCSTRING)
    def forward(
        self,
        input_ids: torch.LongTensor = None,
        attention_mask: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.LongTensor] = None,
        past_key_values: Optional[List[torch.FloatTensor]] = None,
        inputs_embeds: Optional[torch.FloatTensor] = None,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/hyperpod_nemo_adapter/collections/model/nlp/custom_models/modeling_deepseek.py [1569:1576]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    @add_start_docstrings_to_model_forward(DeepseekV3_INPUTS_DOCSTRING)
    def forward(
        self,
        input_ids: torch.LongTensor = None,
        attention_mask: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.LongTensor] = None,
        past_key_values: Optional[List[torch.FloatTensor]] = None,
        inputs_embeds: Optional[torch.FloatTensor] = None,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



