configuration_telechat.py

# coding=utf-8
# Copyright 2018 The OpenAI Team Authors and HuggingFace Inc. team.
# Copyright (c) 2018, NVIDIA CORPORATION.  All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
""" TELECHAT configuration"""

from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging



logger = logging.get_logger(__name__)

TELECHAT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
}


class TELECHATConfig(PretrainedConfig):
    """
    xxxxxx
    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 50257):
            Vocabulary size of the GPT-2 model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`GPT2Model`] or [`TFGPT2Model`].
        n_positions (`int`, *optional*, defaults to 1024):
            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).
        n_embd (`int`, *optional*, defaults to 768):
            Dimensionality of the embeddings and hidden states.
        n_layer (`int`, *optional*, defaults to 12):
            Number of hidden layers in the Transformer encoder.
        n_head (`int`, *optional*, defaults to 12):
            Number of attention heads for each attention layer in the Transformer encoder.
        n_inner (`int`, *optional*, defaults to None):
            Dimensionality of the inner feed-forward layers. `None` will set it to 4 times n_embd
        activation_function (`str`, *optional*, defaults to `"gelu"`):
            Activation function, to be selected in the list `["relu", "silu", "gelu", "tanh", "gelu_new"]`.
        resid_pdrop (`float`, *optional*, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        embd_pdrop (`int`, *optional*, defaults to 0.1):
            The dropout ratio for the embeddings.
        attn_pdrop (`float`, *optional*, defaults to 0.1):
            The dropout ratio for the attention.
        layer_norm_epsilon (`float`, *optional*, defaults to 1e-5):
            The epsilon to use in the layer normalization layers.
        initializer_range (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        summary_type (`string`, *optional*, defaults to `"cls_index"`):
            Argument used when doing sequence summary, used in the models [`GPT2DoubleHeadsModel`] and
            [`TFGPT2DoubleHeadsModel`].
            Has to be one of the following options:
                - `"last"`: Take the last token hidden state (like XLNet).
                - `"first"`: Take the first token hidden state (like BERT).
                - `"mean"`: Take the mean of all tokens hidden states.
                - `"cls_index"`: Supply a Tensor of classification token position (like GPT/GPT-2).
                - `"attn"`: Not implemented now, use multi-head attention.
        summary_use_proj (`bool`, *optional*, defaults to `True`):
            Argument used when doing sequence summary, used in the models [`GPT2DoubleHeadsModel`] and
            [`TFGPT2DoubleHeadsModel`].
            Whether or not to add a projection after the vector extraction.
        summary_activation (`str`, *optional*):
            Argument used when doing sequence summary. Used in for the multiple choice head in
            [`GPT2DoubleHeadsModel`].
            Pass `"tanh"` for a tanh activation to the output, any other value will result in no activation.
        summary_proj_to_labels (`bool`, *optional*, defaults to `True`):
            Argument used when doing sequence summary, used in the models [`GPT2DoubleHeadsModel`] and
            [`TFGPT2DoubleHeadsModel`].
            Whether the projection outputs should have `config.num_labels` or `config.hidden_size` classes.
        summary_first_dropout (`float`, *optional*, defaults to 0.1):
            Argument used when doing sequence summary, used in the models [`GPT2DoubleHeadsModel`] and
            [`TFGPT2DoubleHeadsModel`].
            The dropout ratio to be used after the projection and activation.
        scale_attn_weights (`bool`, *optional*, defaults to `True`):
            Scale attention weights by dividing by sqrt(hidden_size)..
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models).
        scale_attn_by_inverse_layer_idx (`bool`, *optional*, defaults to `False`):
            Whether to additionally scale attention weights by `1 / layer_idx + 1`.
        reorder_and_upcast_attn (`bool`, *optional*, defaults to `False`):
            Whether to scale keys (K) prior to computing attention (dot-product) and upcast attention
            dot-product/softmax to float() when training with mixed precision.
    Example:
    ```python
    >>> from transformers import GPT2Config, GPT2Model
    >>> # Initializing a GPT2 configuration
    >>> configuration = GPT2Config()
    >>> # Initializing a model (with random weights) from the configuration
    >>> model = GPT2Model(configuration)
    >>> # Accessing the model configuration
    >>> configuration = model.config
    ```"""

    model_type = "telechat"
    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=80000,
            n_positions=1024,
            n_embd=768,
            n_layer=12,
            n_head=12,
            num_key_value_heads=64,
            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,
            summary_type="cls_index",
            summary_use_proj=True,
            summary_activation=None,
            summary_proj_to_labels=True,
            summary_first_dropout=0.1,
            scale_attn_weights=True,
            use_cache=True,
            bos_token_id=None,
            eos_token_id=None,
            sep_token_id=None,
            pad_token_id=None,
            unk_token_id=None,
            scale_attn_by_inverse_layer_idx=False,
            reorder_and_upcast_attn=False,
            relative_encoding=None,
            rotary_theta=10000,
            rotary_use_xpos=True,
            rotary_xpos_scale_base=512,
            use_mup=False,
            mup_scale_factor=1.0,
            output_mult=1.0,
            input_mult=1.0,
            mup_base_width=256,
            enable_flash_attn=True,
            use_RMSNorm=False,
            add_bias_linear=True,
            **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.num_key_value_heads = num_key_value_heads
        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.summary_type = summary_type
        self.summary_use_proj = summary_use_proj
        self.summary_activation = summary_activation
        self.summary_first_dropout = summary_first_dropout
        self.summary_proj_to_labels = summary_proj_to_labels
        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.relative_encoding = relative_encoding
        self.use_RMSNorm = use_RMSNorm
        self.add_bias_linear = add_bias_linear

        # for rotary
        self.rotary_theta = rotary_theta
        self.rotary_use_xpos = rotary_use_xpos
        self.rotary_xpos_scale_base = rotary_xpos_scale_base

        # for mup
        self.use_mup = use_mup
        self.mup_scale_factor = mup_scale_factor
        self.output_mult = output_mult
        self.input_mult = input_mult
        self.mup_base_width = mup_base_width

        self.bos_token_id = bos_token_id
        self.eos_token_id = eos_token_id
        self.unk_token_id = unk_token_id
        self.sep_token_id = sep_token_id
        self.pad_token_id = pad_token_id

        self.enable_flash_attn = enable_flash_attn

        self.architectures = ["TELECHAT"]
        self.auto_map = {
            "AutoConfig": "configuration_telechat.TELECHATConfig",
            "AutoModel": "modeling_telechat.TELECHAT",
            "AutoModelForCausalLM": "modeling_telechat.TELECHAT"
        }

        
        super().__init__(bos_token_id=bos_token_id, eos_token_id=eos_token_id, sep_token_id = sep_token_id, pad_token_id = pad_token_id, **kwargs)