| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| """RetrievaBERT model configuration""" |
|
|
| from transformers.configuration_utils import PretrainedConfig |
| from transformers.utils import logging |
|
|
|
|
| logger = logging.get_logger(__name__) |
|
|
|
|
| class RetrievaBertConfig(PretrainedConfig): |
| r""" |
| This is the configuration class to store the configuration of a [`RetrievaBertModel`]. It is used to instantiate a |
| RETRIEVA_BERT 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 RETRIEVA_BERT |
| [nvidia/megatron-bert-uncased-345m](https://huggingface.co/nvidia/megatron-bert-uncased-345m) 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 29056): |
| Vocabulary size of the RETRIEVA_BERT model. Defines the number of different tokens that can be represented |
| by the `inputs_ids` passed when calling [`RetrievaBertModel`]. |
| hidden_size (`int`, *optional*, defaults to 1024): |
| Dimensionality of the encoder layers and the pooler layer. |
| num_hidden_layers (`int`, *optional*, defaults to 24): |
| Number of hidden layers in the Transformer encoder. |
| num_attention_heads (`int`, *optional*, defaults to 16): |
| Number of attention heads for each attention layer in the Transformer encoder. |
| intermediate_size (`int`, *optional*, defaults to 4096): |
| Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder. |
| hidden_act (`str` or `Callable`, *optional*, defaults to `"gelu"`): |
| The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, |
| `"relu"`, `"silu"` and `"gelu_new"` are supported. |
| hidden_dropout_prob (`float`, *optional*, defaults to 0.1): |
| The dropout probability 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 [`RetrievaBertModel`]. |
| If set 0, `token_type_ids` is not used. |
| 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. |
| position_embedding_type (`str`, *optional*, defaults to `"absolute"`): |
| Type of position embedding. Choose one of `"absolute"`, `"rope"`. For |
| positional embeddings use `"absolute"`. |
| is_decoder (`bool`, *optional*, defaults to `False`): |
| Whether the model is used as a decoder or not. If `False`, the model is used as an encoder. |
| 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`. |
| |
| Examples: |
| |
| ```python |
| >>> from models import RetrievaBertConfig, RetrievaBertModel |
| |
| >>> # Initializing a RETRIEVA_BERT google-bert/bert-base-uncased style configuration |
| >>> configuration = RetrievaBertConfig() |
| |
| >>> # Initializing a model (with random weights) from the google-bert/bert-base-uncased style configuration |
| >>> model = RetrievaBertModel(configuration) |
| |
| >>> # Accessing the model configuration |
| >>> configuration = model.config |
| ```""" |
|
|
| model_type = "retrieva-bert" |
|
|
| def __init__( |
| self, |
| vocab_size=29056, |
| hidden_size=1024, |
| num_hidden_layers=24, |
| num_attention_heads=16, |
| intermediate_size=4096, |
| hidden_act="silu", |
| hidden_dropout_prob=0.1, |
| attention_probs_dropout_prob=0.1, |
| max_position_embeddings=512, |
| type_vocab_size=0, |
| initializer_range=0.02, |
| layer_norm_eps=1e-12, |
| pad_token_id=0, |
| position_embedding_type="absolute", |
| use_cache=True, |
| rope_theta=10000.0, |
| rotary_percent=1.0, |
| mlp_bias=False, |
| num_key_value_heads=None, |
| lm_head_hidden_act="gelu", |
| **kwargs, |
| ): |
| super().__init__(pad_token_id=pad_token_id, **kwargs) |
|
|
| self.vocab_size = vocab_size |
| self.hidden_size = hidden_size |
| self.num_hidden_layers = num_hidden_layers |
| self.num_attention_heads = num_attention_heads |
| self.hidden_act = hidden_act |
| self.intermediate_size = intermediate_size |
| self.hidden_dropout_prob = hidden_dropout_prob |
| self.attention_probs_dropout_prob = attention_probs_dropout_prob |
| self.max_position_embeddings = max_position_embeddings |
| self.type_vocab_size = type_vocab_size |
| self.initializer_range = initializer_range |
| self.layer_norm_eps = layer_norm_eps |
| self.position_embedding_type = position_embedding_type |
| self.use_cache = use_cache |
| self.rope_theta = rope_theta |
| self.rotary_percent = rotary_percent |
| self.mlp_bias = mlp_bias |
|
|
| if num_key_value_heads is None: |
| num_key_value_heads = num_attention_heads |
| self.num_key_value_heads = num_key_value_heads |
| self.lm_head_hidden_act = lm_head_hidden_act |
|
|
