mindformers.models.llama.LlamaModel¶
- class mindformers.models.llama.LlamaModel(config: Optional[LlamaConfig] = None)[源代码]¶
Transformer decoder consisting of config.num_hidden_layers layers. Each layer is a [LlamaDecoderLayer] Args:
config(LlamaConfig): the config of network
- Inputs:
input_ids: the tokenized inputs with datatype int32
- Returns:
output: Tensor, the output of llama decoderlayer