| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| """ BERT model configuration""" |
|
|
| from transformers import PretrainedConfig |
|
|
|
|
| class JinaBertConfig(PretrainedConfig): |
| r""" |
| This is the configuration class to store the configuration of a [`BertModel`] or a [`TFBertModel`]. It is used to |
| instantiate a 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 BERT |
| [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) 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 BERT model. Defines the number of different tokens that can be represented by the |
| `inputs_ids` passed when calling [`BertModel`] or [`TFBertModel`]. |
| hidden_size (`int`, *optional*, defaults to 768): |
| Dimensionality 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): |
| 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. |
| type_vocab_size (`int`, *optional*, defaults to 2): |
| The vocabulary size of the `token_type_ids` passed when calling [`BertModel`] or [`TFBertModel`]. |
| 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. |
| window_size (`tuple`, *optional*, defaults to `(-1, -1)`): If not the default, use local attention |
| """ |
|
|
| model_type = "bert" |
|
|
| def __init__( |
| self, |
| vocab_size=30522, |
| hidden_size=768, |
| num_hidden_layers=12, |
| num_attention_heads=12, |
| intermediate_size=3072, |
| hidden_act="gelu", |
| hidden_dropout_prob=0.1, |
| attention_probs_dropout_prob=0.1, |
| type_vocab_size=2, |
| initializer_range=0.02, |
| layer_norm_eps=1e-12, |
| pad_token_id=0, |
| window_size=(-1, -1), |
| dense_seq_output=False, |
| mlp_type='mlp', |
| mlp_checkpoint_lvl=0, |
| last_layer_subset=False, |
| fused_dropout_add_ln=False, |
| fused_bias_fc=False, |
| pad_vocab_size_multiple=1, |
| use_flash_attn=True, |
| use_qk_norm=True, |
| emb_pooler=None, |
| classifier_dropout=None, |
| num_loras=5, |
| **kwargs, |
| ): |
| assert 'position_embedding_type' not in kwargs |
| assert 'max_position_embeddings' not in kwargs |
| super().__init__(pad_token_id=pad_token_id, **kwargs) |
|
|
| if mlp_type == 'fused_mlp' and hidden_act not in ["gelu_new", "gelu_fast", "gelu_pytorch_tanh"]: |
| raise ValueError('Fused MLP only supports approximate gelu') |
|
|
| 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.type_vocab_size = type_vocab_size |
| self.initializer_range = initializer_range |
| self.layer_norm_eps = layer_norm_eps |
| self.window_size = window_size |
| self.dense_seq_output = dense_seq_output |
| self.mlp_type= mlp_type |
| self.mlp_checkpoint_lvl = mlp_checkpoint_lvl |
| self.last_layer_subset = last_layer_subset |
| self.fused_dropout_add_ln = fused_dropout_add_ln |
| self.fused_bias_fc = fused_bias_fc |
| self.pad_vocab_size_multiple = pad_vocab_size_multiple |
| self.use_flash_attn = use_flash_attn |
| self.use_qk_norm = use_qk_norm |
| self.emb_pooler = emb_pooler |
| self.classifier_dropout = classifier_dropout |
| self.num_loras = num_loras |
