【Python】科研代码学习：十五 configuration，tokenization 的代码细节：Llama 为例

【Python】科研代码学习：十五 tokenizer的代码细节：Llama_Tokenization 为例

前言

LlamaConfig：网络参数配置

class LlamaConfig(PretrainedConfig):

    Args:
        vocab_size (`int`, *optional*, defaults to 32000):
            Vocabulary size of the LLaMA model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`LlamaModel`]
        hidden_size (`int`, *optional*, defaults to 4096):
            Dimension of the hidden representations.
        intermediate_size (`int`, *optional*, defaults to 11008):
            Dimension of the MLP representations.
        num_hidden_layers (`int`, *optional*, defaults to 32):
            Number of hidden layers in the Transformer encoder.
        num_attention_heads (`int`, *optional*, defaults to 32):
            Number of attention heads for each attention layer in the Transformer encoder.
        hidden_act (`str` or `function`, *optional*, defaults to `"silu"`):
            The non-linear activation function (function or string) in the decoder.
        max_position_embeddings (`int`, *optional*, defaults to 2048):
            The maximum sequence length that this model might ever be used with. Typically set this to something large
            just in case (e.g., 512 or 1024 or 2048).
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        rms_norm_eps (`float`, *optional*, defaults to 1e-12):
            The epsilon used by the rms normalization layers.
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models). Only
            relevant if `config.is_decoder=True`.
        tie_word_embeddings(`bool`, *optional*, defaults to `False`):
            Whether to tie weight embeddings
        Example:

    ```python
    >>> from transformers import LlamaModel, LlamaConfig

    >>> # Initializing a LLaMA llama-7b style configuration
    >>> configuration = LlamaConfig()

    >>> # Initializing a model from the llama-7b style configuration
    >>> model = LlamaModel(configuration)

    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""

pad_token_id=0
bos_token_id=1
eos_token_id=2

LlamaTokenizer：分词工具

VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model"}

PRETRAINED_VOCAB_FILES_MAP = {
    "vocab_file": {
        "hf-internal-testing/llama-tokenizer": "https://huggingface.co/hf-internal-testing/llama-tokenizer/resolve/main/tokenizer.model",
    },
    "tokenizer_file": {
        "hf-internal-testing/llama-tokenizer": "https://huggingface.co/hf-internal-testing/llama-tokenizer/resolve/main/tokenizer_config.json",
    },
}
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
    "hf-internal-testing/llama-tokenizer": 2048,
}

class LlamaTokenizer(PreTrainedTokenizer):
    """
    Construct a Llama tokenizer. Based on byte-level Byte-Pair-Encoding.

    Args:
        vocab_file (`str`):
            Path to the vocabulary file.
    """

    vocab_files_names = VOCAB_FILES_NAMES
    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
    model_input_names = ["input_ids", "attention_mask"]

bos_token = AddedToken(bos_token, lstrip=False, rstrip=False) if isinstance(bos_token, str) else bos_token
eos_token = AddedToken(eos_token, lstrip=False, rstrip=False) if isinstance(eos_token, str) else eos_token
unk_token = AddedToken(unk_token, lstrip=False, rstrip=False) if isinstance(unk_token, str) else unk_token
pad_token = AddedToken(pad_token, lstrip=False, rstrip=False) if isinstance(pad_token, str) else pad_token

self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
self.sp_model.Load(vocab_file)

@property
def vocab_size(self):
    """Returns vocab size"""
    return self.sp_model.get_piece_size()

def get_vocab(self):
    """Returns vocab as a dict"""
    vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
    vocab.update(self.added_tokens_encoder)
    return vocab