| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| """PLM model configuration""" |
| from transformers.configuration_utils import PretrainedConfig |
| from transformers.utils import logging |
|
|
|
|
| logger = logging.get_logger(__name__) |
|
|
|
|
| class PLMConfig(PretrainedConfig): |
| r""" |
| This is the configuration class to store the configuration of a [`PLMModel`]. It is used to instantiate a |
| PLM model according to the specified arguments, defining the model architecture. |
| |
| Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the |
| documentation from [`PretrainedConfig`] for more information. Instantiating a configuration with the |
| defaults will yield a similar configuration to that of the PLM model. |
| |
| |
| Args: |
| vocab_size (`int`, *optional*, defaults to 151936): |
| Vocabulary size of the PLM model. Defines the number of different tokens that can be represented by the |
| `inputs_ids` passed when calling [`PLMModel`] |
| hidden_size (`int`, *optional*, defaults to 4096): |
| Dimension of the hidden representations. |
| intermediate_size (`int`, *optional*, defaults to 8192): |
| Dimension of the MLP representations. |
| num_hidden_layers (`int`, *optional*, defaults to 32): |
| 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. |
| num_key_value_heads (`int`, *optional*, defaults to 16): |
| This is the number of key_value heads that should be used to implement Grouped Query Attention. If |
| `num_key_value_heads=num_attention_heads`, the model will use Multi Head Attention (MHA), if |
| `num_key_value_heads=1` the model will use Multi Query Attention (MQA) otherwise GQA is used. When |
| converting a multi-head checkpoint to a GQA checkpoint, each group key and value head should be constructed |
| by meanpooling all the original heads within that group. For more details checkout [this |
| paper](https://arxiv.org/pdf/2305.13245.pdf). If it is not specified, will default to `32`. |
| hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): |
| The non-linear activation function (function or string) in the decoder. |
| pretraining_tp (`int`, *optional*, defaults to 1): |
| Experimental feature. Tensor parallelism rank used during pretraining. Please refer to [this |
| document](https://huggingface.co/docs/transformers/parallelism) to understand more about it. This value is |
| necessary to ensure exact reproducibility of the pretraining results. Please refer to [this |
| issue](https://github.com/pytorch/pytorch/issues/76232). |
| max_position_embeddings (`int`, *optional*, defaults to 4096): |
| The maximum sequence length that this model might ever be used with. |
| initializer_range (`float`, *optional*, defaults to 0.02): |
| The standard deviation of the truncated_normal_initializer for initializing all weight matrices. |
| rms_norm_eps (`float`, *optional*, defaults to 1e-06): |
| The epsilon used by the rms 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`. |
| tie_word_embeddings (`bool`, *optional*, defaults to `True`): |
| Whether the model's input and output word embeddings should be tied. |
| rope_scaling (`Dict`, *optional*): |
| Dictionary containing the scaling configuration for the RoPE embeddings. Currently supports normal rope. |
| rope_theta (`float`, *optional*, defaults to 100000.0): |
| The base period of the RoPE embeddings. |
| attention_bias (`bool`, defaults to `False`, *optional*, defaults to `False`): |
| Whether to use a bias in the query, key, value and output projection layers during self-attention. |
| attention_dropout (`float`, *optional*, defaults to 0.0): |
| The dropout ratio for the attention probabilities. |
| |
| ```python |
| >>> from transformers import PLMModel, PLMConfig |
| |
| >>> # Initializing a PLM style configuration |
| >>> configuration = PLMConfig() |
| |
| >>> # Initializing a model from the PLM style configuration |
| >>> model = PLMModel(configuration) |
| |
| >>> # Accessing the model configuration |
| >>> configuration = model.config |
| ```""" |
|
|
| model_type = "plm" |
| keys_to_ignore_at_inference = ["past_key_values"] |
|
|
| def __init__( |
| self, |
| vocab_size=151936, |
| hidden_size=2048, |
| intermediate_size=8192, |
| num_hidden_layers=32, |
| num_attention_heads=16, |
| num_key_value_heads=16, |
| kv_lora_rank = 512, |
| q_lora_rank = None, |
| qk_rope_head_dim = 64, |
| v_head_dim = 128, |
| qk_nope_head_dim = 128, |
| hidden_act="relu2", |
| max_position_embeddings=4096, |
| initializer_range=0.02, |
| rms_norm_eps=1e-6, |
| use_cache=True, |
| pretraining_tp=1, |
| tie_word_embeddings=True, |
| rope_theta=100000.0, |
| 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 |
| self.kv_lora_rank = kv_lora_rank |
| self.q_lora_rank = q_lora_rank |
| self.qk_rope_head_dim = qk_rope_head_dim |
| self.v_head_dim = v_head_dim |
| self.qk_nope_head_dim = qk_nope_head_dim |
| |
| 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.attention_bias = attention_bias |
| self.attention_dropout = attention_dropout |
|
|
| super().__init__( |
| tie_word_embeddings=tie_word_embeddings, |
| **kwargs, |
| ) |
