|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
""" Cohere model configuration""" |
|
|
|
from transformers import PretrainedConfig, AutoConfig |
|
from transformers.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. |
|
|
|
|
|
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. |
|
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 checkout [this |
|
paper](https://arxiv.org/pdf/2305.13245.pdf). 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. |
|
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/main/perf_train_gpu_many#tensor-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). |
|
tie_word_embeddings (`bool`, *optional*, defaults to `False`): |
|
Whether to tie weight embeddings |
|
rope_theta (`float`, *optional*, defaults to 10000.0): |
|
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 CohereModel, CohereConfig |
|
|
|
>>> # Initializing a Cohere model configuration |
|
>>> configuration = CohereConfig() |
|
|
|
>>> # Initializing a model from the Cohere configuration |
|
>>> model = CohereModel(configuration) |
|
|
|
>>> # Accessing the model configuration |
|
>>> configuration = model.config |
|
```""" |
|
|
|
model_type = "cohere" |
|
keys_to_ignore_at_inference = ["past_key_values"] |
|
|
|
def __init__( |
|
self, |
|
vocab_size=256000, |
|
hidden_size=8192, |
|
intermediate_size=22528, |
|
num_hidden_layers=40, |
|
num_attention_heads=64, |
|
num_key_value_heads=None, |
|
hidden_act="silu", |
|
max_position_embeddings=8192, |
|
initializer_range=0.02, |
|
layer_norm_eps=1e-5, |
|
use_cache=True, |
|
pad_token_id=0, |
|
bos_token_id=5, |
|
eos_token_id=255001, |
|
pretraining_tp=1, |
|
tie_word_embeddings=True, |
|
rope_theta=10000.0, |
|
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 |
|
|
|
|
|
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.pretraining_tp = pretraining_tp |
|
self.use_cache = use_cache |
|
self.rope_theta = rope_theta |
|
self.attention_bias = attention_bias |
|
self.attention_dropout = attention_dropout |
|
|
|
super().__init__( |
|
pad_token_id=pad_token_id, |
|
bos_token_id=bos_token_id, |
|
eos_token_id=eos_token_id, |
|
tie_word_embeddings=tie_word_embeddings, |
|
**kwargs, |
|
) |
|
|
|
|
|
|
|
AutoConfig.register("cohere", CohereConfig) |
