configuration_aura.py

from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging

logger = logging.get_logger(__name__)

class LlamaConfig(PretrainedConfig):
    model_type = "llama"
    keys_to_ignore_at_inference = ["past_key_values"]

    def __init__(
            self,
            vocab_size=32000,
            hidden_size=4096,
            intermediate_size=11008,
            num_hidden_layers=32,
            num_attention_heads=32,
            num_key_value_heads=None,
            hidden_act="silu",
            max_position_embeddings=2048,
            initializer_range=0.02,
            rms_norm_eps=1e-6,
            use_cache=True,
            pad_token_id=None,
            bos_token_id=1,
            eos_token_id=2,
            pretraining_tp=1,
            tie_word_embeddings=False,
            rope_theta=10000.0,
            rope_scaling=None,
            attention_bias=False,
            attention_dropout=0.0,
            **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.pretraining_tp = pretraining_tp
        self.use_cache = use_cache
        self.rope_theta = rope_theta
        self.rope_scaling = rope_scaling
        self._rope_scaling_validation()
        self.attention_bias = attention_bias
        self.attention_dropout = attention_dropout

        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,
        )

    def _rope_scaling_validation(self):
        """
        Validate the `rope_scaling` configuration.
        """
        if self.rope_scaling is None:
            return

        if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 2:
            raise ValueError(
                "`rope_scaling` must be a dictionary with two fields, `type` and `factor`, " f"got {self.rope_scaling}"
            )
        rope_scaling_type = self.rope_scaling.get("type", None)
        rope_scaling_factor = self.rope_scaling.get("factor", None)
        if rope_scaling_type is None or rope_scaling_type not in ["linear", "dynamic"]:
            raise ValueError(
                f"`rope_scaling`'s type field must be one of ['linear', 'dynamic'], got {rope_scaling_type}"
            )
        if rope_scaling_factor is None or not isinstance(rope_scaling_factor, float) or rope_scaling_factor <= 1.0:
            raise ValueError(f"`rope_scaling`'s factor field must be a float > 1, got {rope_scaling_factor}")


from typing import Union
from transformers import PretrainedConfig
import os


class SigLipVisionConfig(PretrainedConfig):
    model_type = "siglip_vision_model"

    def __init__(
            self,
            hidden_size=1152,
            image_mean=(0.5, 0.5, 0.5),
            intermediate_size=4304,
            num_hidden_layers=27,
            num_attention_heads=16,
            num_channels=3,
            image_size=384,
            patch_size=14,
            hidden_act="gelu_pytorch_tanh",
            layer_norm_eps=1e-6,
            attention_dropout=0.0,
            **kwargs,
    ):
        super().__init__(**kwargs)

        self.hidden_size = hidden_size
        self.intermediate_size = intermediate_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.num_channels = num_channels
        self.patch_size = patch_size
        self.image_size = image_size
        self.attention_dropout = attention_dropout
        self.layer_norm_eps = layer_norm_eps
        self.hidden_act = hidden_act
        self.image_mean = image_mean

    @classmethod
    def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> "PretrainedConfig":
        cls._set_token_in_kwargs(kwargs)

        config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)

        # get the vision config dict if we are loading from SigLipConfig
        if config_dict.get("model_type") == "siglip":
            config_dict = config_dict["vision_config"]

        if "model_type" in config_dict and hasattr(cls, "model_type") and config_dict["model_type"] != cls.model_type:
            logger.warning(
                f"You are using a model of type {config_dict['model_type']} to instantiate a model of type "
                f"{cls.model_type}. This is not supported for all configurations of models and can yield errors."
            )

        return cls.from_dict(config_dict, **kwargs)


class AuraConfig(LlamaConfig):
    model_type = "aura"