|
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
|
|
|
|
| import os |
| import math |
| from typing import Optional, Union |
|
|
| from transformers import PretrainedConfig |
| from transformers.utils import logging |
|
|
| logger = logging.get_logger(__name__) |
|
|
|
|
| class PhiConfig(PretrainedConfig): |
| """Phi configuration.""" |
|
|
| model_type = "phi-msft" |
| attribute_map = { |
| "max_position_embeddings": "n_positions", |
| "hidden_size": "n_embd", |
| "num_attention_heads": "n_head", |
| "num_hidden_layers": "n_layer", |
| } |
|
|
| def __init__( |
| self, |
| vocab_size: int = 50304, |
| n_positions: int = 2048, |
| n_embd: int = 1024, |
| n_layer: int = 20, |
| n_inner: Optional[int] = None, |
| n_head: int = 16, |
| n_head_kv: Optional[int] = None, |
| rotary_dim: Optional[int] = 32, |
| activation_function: Optional[str] = "gelu_new", |
| flash_attn: bool = False, |
| flash_rotary: bool = False, |
| fused_dense: bool = False, |
| attn_pdrop: float = 0.0, |
| embd_pdrop: float = 0.0, |
| resid_pdrop: float = 0.0, |
| layer_norm_epsilon: float = 1e-5, |
| initializer_range: float = 0.02, |
| tie_word_embeddings: bool = False, |
| pad_vocab_size_multiple: int = 64, |
| **kwargs |
| ) -> None: |
| self.vocab_size = int(math.ceil(vocab_size / pad_vocab_size_multiple) * pad_vocab_size_multiple) |
| self.n_positions = n_positions |
| self.n_embd = n_embd |
| self.n_layer = n_layer |
| self.n_inner = n_inner |
| self.n_head = n_head |
| self.n_head_kv = n_head_kv |
| self.rotary_dim = min(rotary_dim, n_embd // n_head) |
| self.activation_function = activation_function |
| self.flash_attn = flash_attn |
| self.flash_rotary = flash_rotary |
| self.fused_dense = fused_dense |
| self.attn_pdrop = attn_pdrop |
| self.embd_pdrop = embd_pdrop |
| self.resid_pdrop = resid_pdrop |
| self.layer_norm_epsilon = layer_norm_epsilon |
| self.initializer_range = initializer_range |
|
|
| super().__init__(tie_word_embeddings=tie_word_embeddings, **kwargs) |
|
|
|
|
|
|
| class SiglipVisionConfig(PretrainedConfig): |
|
|
| model_type = "siglip_vision_model" |
|
|
| def __init__( |
| self, |
| hidden_size=768, |
| intermediate_size=3072, |
| num_hidden_layers=12, |
| num_attention_heads=12, |
| num_channels=3, |
| image_size=224, |
| patch_size=16, |
| 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 |
|
|
| @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) |
|
|
| |
| 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 ImpConfig(PhiConfig): |
| model_type = "imp" |
|
|
| def __init__(self, **kwargs): |
| super().__init__(**kwargs) |
| self.image_token_index = getattr(self, "image_token_index", 50296) |
| self.image_token = getattr(self, "image_token", "<image>") |
|
|
| if not hasattr(self, "vision_tower_config") and hasattr(self, "mm_vision_tower"): |
| vision_tower_config = SiglipVisionConfig.from_pretrained(self.mm_vision_tower) |
| self.vision_tower_config = vision_tower_config.to_diff_dict() |
| |
| @property |
| def vision_tower_cfg(self): |
| cfg = SiglipVisionConfig.from_dict(self.vision_tower_config) |
| |
| |
| cfg.mm_vision_select_layer = self.mm_vision_select_layer |
| cfg.mm_vision_tower = self.mm_vision_tower |
| return cfg |
|
|
