# Copyright 2024 Cohere team. All rights reserved. # # This code is based on EleutherAI's GPT-NeoX library and the GPT-NeoX # and OPT implementations in this library. It has been modified from its # original forms to accommodate minor architectural differences compared # to GPT-NeoX and OPT used by the Meta AI team that trained the model. # # 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. """Cohere model configuration""" from ...configuration_utils import PreTrainedConfig from ...modeling_rope_utils import RopeParameters from ...utils import logging logger = logging.get_logger(__name__) class CohereConfig(PreTrainedConfig): r""" This is the configuration class to store the configuration of a [`CohereModel`]. It is used to instantiate an Cohere 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 [CohereForAI/c4ai-command-r-v01](https://huggingface.co/CohereForAI/c4ai-command-r-v01) model. Args: vocab_size (`int`, *optional*, defaults to 256000): Vocabulary size of the Cohere model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`CohereModel`] hidden_size (`int`, *optional*, defaults to 8192): Dimension of the hidden representations. intermediate_size (`int`, *optional*, defaults to 22528): Dimension of the MLP representations. logit_scale (`float`, *optional*, defaults to 0.0625): The scaling factor for the output logits. num_hidden_layers (`int`, *optional*, defaults to 40): Number of hidden layers in the Transformer decoder. num_attention_heads (`int`, *optional*, defaults to 64): Number of attention heads for each attention layer in the Transformer decoder. num_key_value_heads (`int`, *optional*): 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, check out [this paper](https://huggingface.co/papers/2305.13245). If it is not specified, will default to `num_attention_heads`. hidden_act (`str` or `function`, *optional*, defaults to `"silu"`): The non-linear activation function (function or string) in the decoder. max_position_embeddings (`int`, *optional*, defaults to 8192): 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. layer_norm_eps (`float`, *optional*, defaults to 1e-05): The epsilon used by the layer normalization. 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`. pad_token_id (`int`, *optional*, defaults to 0): Padding token id. bos_token_id (`int`, *optional*, defaults to 5): Beginning of stream token id. eos_token_id (`int`, *optional*, defaults to 255001): End of stream token id. tie_word_embeddings (`bool`, *optional*, defaults to `True`): Whether to tie weight embeddings rope_parameters (`RopeParameters`, *optional*): Dictionary containing the configuration parameters for the RoPE embeddings. The dictionary should contain a value for `rope_theta` and optionally parameters used for scaling in case you want to use RoPE with longer `max_position_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. use_qk_norm (`bool`, *optional*, defaults to `False`): Whether to use query-key normalization in the attention ```python >>> from transformers import CohereModel, CohereConfig >>> # Initializing a Cohere model configuration >>> configuration = CohereConfig() >>> # Initializing a model from the Cohere configuration >>> model = CohereModel(configuration) # doctest: +SKIP >>> # Accessing the model configuration >>> configuration = model.config # doctest: +SKIP ```""" model_type = "cohere" keys_to_ignore_at_inference = ["past_key_values"] default_theta = 500000.0 base_model_tp_plan = { "layers.*.self_attn.q_proj": "colwise", "layers.*.self_attn.k_proj": "colwise", "layers.*.self_attn.v_proj": "colwise", "layers.*.self_attn.o_proj": "rowwise", "layers.*.mlp.gate_proj": "colwise", "layers.*.mlp.up_proj": "colwise", "layers.*.mlp.down_proj": "rowwise", } base_model_pp_plan = { "embed_tokens": (["input_ids"], ["inputs_embeds"]), "layers": (["hidden_states", "attention_mask"], ["hidden_states"]), "norm": (["hidden_states"], ["hidden_states"]), } def __init__( self, vocab_size: int | None = 256000, hidden_size: int | None = 8192, intermediate_size: int | None = 22528, logit_scale: float | None = 0.0625, num_hidden_layers: int | None = 40, num_attention_heads: int | None = 64, num_key_value_heads: int | None = None, hidden_act: str | None = "silu", max_position_embeddings: int | None = 8192, initializer_range: float | None = 0.02, layer_norm_eps: int | None = 1e-5, use_cache: bool | None = True, pad_token_id: int | None = 0, bos_token_id: int | None = 5, eos_token_id: int | None = 255001, tie_word_embeddings: bool | None = True, rope_parameters: RopeParameters | dict[str, RopeParameters] | None = None, attention_bias: bool | None = False, attention_dropout: float | None = 0.0, use_qk_norm: bool | None = False, **kwargs, ): self.vocab_size = vocab_size self.max_position_embeddings = max_position_embeddings self.hidden_size = hidden_size self.logit_scale = logit_scale self.intermediate_size = intermediate_size self.num_hidden_layers = num_hidden_layers self.num_attention_heads = num_attention_heads # for backward compatibility 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.layer_norm_eps = layer_norm_eps self.use_cache = use_cache self.attention_bias = attention_bias self.attention_dropout = attention_dropout self.use_qk_norm = use_qk_norm self.rope_parameters = rope_parameters self.tie_word_embeddings = tie_word_embeddings self.pad_token_id = pad_token_id self.bos_token_id = bos_token_id self.eos_token_id = eos_token_id super().__init__(**kwargs) __all__ = ["CohereConfig"]