| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| """ Della model configuration """ |
|
|
| from transformers.configuration_utils import PretrainedConfig |
|
|
|
|
| Della_PRETRAINED_CONFIG_ARCHIVE_MAP = { |
| "Della-226M-base": "https://huggingface.co/IDEA-CCNL/Randeng-DELLA-226M-Chinese/resolve/main/config.json" |
| } |
|
|
|
|
| class DellaModelConfig(PretrainedConfig): |
| r""" |
| This is the configuration class to store the configuration of a [`~DellaModel`]. |
| It is used to instantiate an DellaModel 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 DellaModel [Randeng-DELLA-226M-Chinese](https://huggingface.co/IDEA-CCNL/Randeng-DELLA-226M-Chinese) architecture. |
| |
| 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 30522): |
| Vocabulary size of the Della model. Defines the number of different |
| tokens that can be represented by the |
| `inputs_ids` passed when calling [`~DellaModel`] or |
| [`~TFDellaModel`]. |
| hidden_size (`int`, *optional*, defaults to 768): |
| Dimension of the encoder layers and the pooler layer. |
| num_hidden_layers (`int`, *optional*, defaults to 12): |
| Number of hidden layers in the Transformer encoder. |
| num_attention_heads (`int`, *optional*, defaults to 12): |
| Number of attention heads for each attention layer in the Transformer encoder. |
| intermediate_size (`int`, *optional*, defaults to 3072): |
| Dimension of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder. |
| hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`): |
| The non-linear activation function (function or string) in the encoder and pooler. |
| If string, `"gelu"`, `"relu"`, `"selu"` and `"gelu_new"` are supported. |
| hidden_dropout_prob (`float`, *optional*, defaults to 0.1): |
| The dropout probabilitiy for all fully connected layers in the embeddings, encoder, and pooler. |
| attention_probs_dropout_prob (`float`, *optional*, defaults to 0.1): |
| The dropout ratio for the attention probabilities. |
| max_position_embeddings (`int`, *optional*, defaults to 512): |
| 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). |
| type_vocab_size (`int`, *optional*, defaults to 2): |
| The vocabulary size of the `token_type_ids` passed when calling [`~DellaModel`] or |
| [`~TFDellaModel`]. |
| initializer_range (`float`, *optional*, defaults to 0.02): |
| The standard deviation of the truncated_normal_initializer for initializing all weight matrices. |
| layer_norm_eps (`float`, *optional*, defaults to 1e-12): |
| The epsilon used by the layer 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`. |
| |
| """ |
| model_type = "DellaModel" |
| keys_to_ignore_at_inference = ["past_key_values"] |
| attribute_map = { |
| "hidden_size": "n_embd", |
| "max_position_embeddings": "n_positions", |
| "num_attention_heads": "n_head", |
| "num_hidden_layers": "n_layer", |
| } |
|
|
| def __init__( |
| self, |
| vocab_size=50257, |
| n_positions=1024, |
| n_embd=768, |
| n_layer=12, |
| n_head=12, |
| n_inner=None, |
| activation_function="gelu_new", |
| resid_pdrop=0.1, |
| embd_pdrop=0.1, |
| attn_pdrop=0.1, |
| layer_norm_epsilon=1e-5, |
| initializer_range=0.02, |
| scale_attn_weights=True, |
| use_cache=True, |
| scale_attn_by_inverse_layer_idx=False, |
| reorder_and_upcast_attn=False, |
| bos_token_id=21128, |
| eos_token_id=21129, |
| pad_token_id=0, |
| CVAE=False, |
| latent_dim=256, |
| **kwargs, |
| ): |
| self.vocab_size = vocab_size |
| self.n_positions = n_positions |
| self.n_embd = n_embd |
| self.n_layer = n_layer |
| self.n_head = n_head |
| self.n_inner = n_inner |
| self.activation_function = activation_function |
| self.resid_pdrop = resid_pdrop |
| self.embd_pdrop = embd_pdrop |
| self.attn_pdrop = attn_pdrop |
| self.layer_norm_epsilon = layer_norm_epsilon |
| self.initializer_range = initializer_range |
|
|
| self.scale_attn_weights = scale_attn_weights |
| self.use_cache = use_cache |
| self.scale_attn_by_inverse_layer_idx = scale_attn_by_inverse_layer_idx |
| self.reorder_and_upcast_attn = reorder_and_upcast_attn |
|
|
| self.bos_token_id = bos_token_id |
| self.eos_token_id = eos_token_id |
| self.pad_token_id = pad_token_id |
| self.CVAE = CVAE |
| self.latent_dim = latent_dim |
| super().__init__(bos_token_id=bos_token_id, eos_token_id=eos_token_id, pad_token_id=pad_token_id, **kwargs) |
|
|
