246 lines
13 KiB
Python
246 lines
13 KiB
Python
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
|
|
# This file was automatically generated from src/transformers/models/cohere2/modular_cohere2.py.
|
|
# Do NOT edit this file manually as any edits will be overwritten by the generation of
|
|
# the file from the modular. If any change should be done, please apply the change to the
|
|
# modular_cohere2.py file directly. One of our CI enforces this.
|
|
# 🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨🚨
|
|
# coding=utf-8
|
|
# Copyright 2024 Cohere Inc. HuggingFace Inc. team. 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.
|
|
import warnings
|
|
|
|
from ...configuration_utils import PretrainedConfig, layer_type_validation
|
|
from ...modeling_rope_utils import rope_config_validation
|
|
|
|
|
|
class Cohere2Config(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_theta (`float`, *optional*, defaults to 10000.0):
|
|
The base period of the RoPE embeddings.
|
|
rope_scaling (`Dict`, *optional*):
|
|
Dictionary containing the scaling configuration for the RoPE embeddings. NOTE: if you apply new rope type
|
|
and you expect the model to work on longer `max_position_embeddings`, we recommend you to update this value
|
|
accordingly.
|
|
Expected contents:
|
|
`rope_type` (`str`):
|
|
The sub-variant of RoPE to use. Can be one of ['default', 'linear', 'dynamic', 'yarn', 'longrope',
|
|
'llama3'], with 'default' being the original RoPE implementation.
|
|
`factor` (`float`, *optional*):
|
|
Used with all rope types except 'default'. The scaling factor to apply to the RoPE embeddings. In
|
|
most scaling types, a `factor` of x will enable the model to handle sequences of length x *
|
|
original maximum pre-trained length.
|
|
`original_max_position_embeddings` (`int`, *optional*):
|
|
Used with 'dynamic', 'longrope' and 'llama3'. The original max position embeddings used during
|
|
pretraining.
|
|
`attention_factor` (`float`, *optional*):
|
|
Used with 'yarn' and 'longrope'. The scaling factor to be applied on the attention
|
|
computation. If unspecified, it defaults to value recommended by the implementation, using the
|
|
`factor` field to infer the suggested value.
|
|
`beta_fast` (`float`, *optional*):
|
|
Only used with 'yarn'. Parameter to set the boundary for extrapolation (only) in the linear
|
|
ramp function. If unspecified, it defaults to 32.
|
|
`beta_slow` (`float`, *optional*):
|
|
Only used with 'yarn'. Parameter to set the boundary for interpolation (only) in the linear
|
|
ramp function. If unspecified, it defaults to 1.
|
|
`short_factor` (`list[float]`, *optional*):
|
|
Only used with 'longrope'. The scaling factor to be applied to short contexts (<
|
|
`original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
|
|
size divided by the number of attention heads divided by 2
|
|
`long_factor` (`list[float]`, *optional*):
|
|
Only used with 'longrope'. The scaling factor to be applied to long contexts (<
|
|
`original_max_position_embeddings`). Must be a list of numbers with the same length as the hidden
|
|
size divided by the number of attention heads divided by 2
|
|
`low_freq_factor` (`float`, *optional*):
|
|
Only used with 'llama3'. Scaling factor applied to low frequency components of the RoPE
|
|
`high_freq_factor` (`float`, *optional*):
|
|
Only used with 'llama3'. Scaling factor applied to high frequency components of the RoPE
|
|
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.
|
|
sliding_window (`int`, *optional*, defaults to 4096):
|
|
Size of the sliding window attention context.
|
|
layer_types (`list`, *optional*):
|
|
Attention pattern for each layer.
|
|
|
|
```python
|
|
>>> from transformers import Cohere2Model, Cohere2Config
|
|
|
|
>>> # Initializing a Cohere Nextmodel configuration
|
|
>>> configuration = Cohere2Config()
|
|
|
|
>>> # Initializing a model from the Cohere2 configuration
|
|
>>> model = Cohere2Model(configuration) # doctest: +SKIP
|
|
|
|
>>> # Accessing the model configuration
|
|
>>> configuration = model.config # doctest: +SKIP
|
|
```
|
|
"""
|
|
|
|
model_type = "cohere2"
|
|
keys_to_ignore_at_inference = ["past_key_values"]
|
|
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=256000,
|
|
hidden_size=8192,
|
|
intermediate_size=22528,
|
|
logit_scale=0.0625,
|
|
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,
|
|
tie_word_embeddings=True,
|
|
rope_theta=10000.0,
|
|
rope_scaling=None,
|
|
attention_bias=False,
|
|
attention_dropout=0.0,
|
|
sliding_window=4096,
|
|
layer_types=None,
|
|
**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.rope_theta = rope_theta
|
|
self.rope_scaling = rope_scaling
|
|
self.attention_bias = attention_bias
|
|
self.attention_dropout = attention_dropout
|
|
self.sliding_window = sliding_window
|
|
self.layer_types = layer_types
|
|
# Need to specify head_dim in the config so it can be used in the attention forward functions
|
|
self.head_dim = hidden_size // num_attention_heads
|
|
|
|
# Validate the correctness of rotary position embeddings parameters
|
|
rope_config_validation(self)
|
|
|
|
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,
|
|
)
|
|
|
|
# BC -> the pattern used to be a simple int, and it's still present in configs on the Hub
|
|
self._sliding_window_pattern = kwargs.get("sliding_window_pattern", 4)
|
|
|
|
if self.layer_types is None:
|
|
# BC -> the pattern used to be a simple int, and it's still present in configs on the Hub
|
|
self._sliding_window_pattern = getattr(self, "sliding_window_pattern", 4)
|
|
self.layer_types = [
|
|
"sliding_attention" if bool((i + 1) % self._sliding_window_pattern) else "full_attention"
|
|
for i in range(self.num_hidden_layers)
|
|
]
|
|
layer_type_validation(self.layer_types)
|
|
|
|
@property
|
|
def sliding_window_pattern(self):
|
|
warnings.warn(
|
|
"The `sliding_window_pattern` attribute is deprecated and will be removed in v4.55.0.",
|
|
FutureWarning,
|
|
)
|
|
return self._sliding_window_pattern
|
|
|
|
@sliding_window_pattern.setter
|
|
def sliding_window_pattern(self, value):
|
|
self._sliding_window_pattern = value
|
|
|
|
|
|
__all__ = ["Cohere2Config"]
|