Delete configuration_yi.py

configuration_yi.py

@@ -1,121 +0,0 @@
-""" Yi model configuration"""
-from transformers.configuration_utils import PretrainedConfig
-from transformers.utils import logging
-
-logger = logging.get_logger(__name__)
-
-Yi_PRETRAINED_CONFIG_ARCHIVE_MAP = {}
-
-
-class YiConfig(PretrainedConfig):
-    r"""
-    This is the configuration class to store the configuration of a [`YiModel`]. It is used to instantiate an Yi
-    model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
-    defaults will yield a similar configuration to that of the Yi model.
-
-    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
-    documentation from [`PretrainedConfig`] for more information.
-
-
-    Args:
-        vocab_size (`int`, *optional*, defaults to 64000):
-            Vocabulary size of the Yi model. Defines the number of different tokens that can be represented by the
-            `inputs_ids` passed when calling [`YiModel`]
-        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.
-        num_key_value_heads (`int`, *optional*):
-            This is the number of key_value heads that should be used to implement Grouped Query Attention. If
-            `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if
-            `num_key_value_heads=1 the model will use Multi Query Attention (MQA) otherwise GQA is used. When
-            converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed
-            by meanpooling all the original heads within that group. For more details checkout [this
-            paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to
-            `num_attention_heads`.
-        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 4096):
-            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 or 4096).
-        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-5):
-            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
-        output_attentions (`bool`, *optional*, defaults to `False`):
-            Whether or not to output attentions.
-        rope_theta (`float`, *optional*, defaults to 5000000.0):
-            The base period of the RoPE embeddings.
-        Example:
-
-    ```python
-    >>> from transformers import YiModel, YiConfig
-
-    >>> # Initializing a Yi style configuration
-    >>> configuration = YiConfig()
-
-    >>> # Initializing a model from the Yi style configuration
-    >>> model = YiModel(configuration)
-
-    >>> # Accessing the model configuration
-    >>> configuration = model.config
-    ```"""
-    model_type = "Yi"
-    keys_to_ignore_at_inference = ["past_key_values"]
-
-    def __init__(
-        self,
-        vocab_size=64000,
-        hidden_size=4096,
-        intermediate_size=11008,
-        num_hidden_layers=32,
-        num_attention_heads=32,
-        num_key_value_heads=4,
-        hidden_act="silu",
-        max_position_embeddings=4096,
-        initializer_range=0.02,
-        rms_norm_eps=1e-5,
-        use_cache=True,
-        pad_token_id=0,
-        bos_token_id=1,
-        eos_token_id=2,
-        tie_word_embeddings=False,
-        output_attentions=False,
-        rope_theta=5000000.0,
-        **kwargs,
-    ):
-        self.vocab_size = vocab_size
-        self.max_position_embeddings = max_position_embeddings
-        self.hidden_size = hidden_size
-        self.intermediate_size = intermediate_size
-        self.num_hidden_layers = num_hidden_layers
-        self.num_attention_heads = num_attention_heads
-
-        # for backward compatibility
-        if num_key_value_heads is None:
-            num_key_value_heads = num_attention_heads
-
-        self.num_key_value_heads = num_key_value_heads
-        self.hidden_act = hidden_act
-        self.initializer_range = initializer_range
-        self.rms_norm_eps = rms_norm_eps
-        self.use_cache = use_cache
-        self.output_attentions = output_attentions
-        self.rope_theta = rope_theta
-
-        super().__init__(
-            pad_token_id=pad_token_id,
-            bos_token_id=bos_token_id,
-            eos_token_id=eos_token_id,
-            tie_word_embeddings=tie_word_embeddings,
-            **kwargs,
-        )