jradchenko/DeciCoder-1b

1from packaging import version2import transformers3if version.parse(transformers.__version__) < version.parse("4.31.0"):4    raise ImportError(5        f"You are using transformers=={transformers.__version__}, but transformers>=4.31.0 is required to use DeciCoder. Please upgrade transformers."6    )7from transformers.models.llama.configuration_llama import LlamaConfig8from transformers.utils import logging9 10 11logger = logging.get_logger(__name__)12 13LLAMA_PRETRAINED_CONFIG_ARCHIVE_MAP = {}14 15 16class LlamaConfig(LlamaConfig):17    r"""18   This is the configuration class to store the configuration of a [`LlamaModel`]. It is used to instantiate an LLaMA19   model according to the specified arguments, defining the model architecture. Instantiating a configuration with the20   defaults will yield a similar configuration to that of the LLaMA-7B.21 22   Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the23   documentation from [`PretrainedConfig`] for more information.24 25 26    Args:27        naive_attention_prefill (`bool`, *optional*, defaults to False):28            Whether to use naive matmul or scaled dot product attention during prefill.29        naive_attention_decode_batched (`bool`, *optional*, defaults to True):30            Whether to use naive matmul or scaled dot product attention during decode for batch_size > 1.31        naive_attention_decode_single (`bool`, *optional*, defaults to False):32            Whether to use naive matmul or scaled dot product attention during decode for batch_size == 1.33       34 35       ```"""36    keys_to_ignore_at_inference = ["past_key_values"]37 38    def __init__(39        self,40        naive_attention_prefill: bool = False,41        naive_attention_decode_batched: bool = True,42        naive_attention_decode_single: bool = False,43        **kwargs,44    ):45        self.naive_attention_prefill = naive_attention_prefill46        self.naive_attention_decode_batched = naive_attention_decode_batched47        self.naive_attention_decode_single = naive_attention_decode_single48 49        super().__init__(**kwargs,)50 51