|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
""" InternLM2 model configuration""" |
|
|
|
from transformers.configuration_utils import PretrainedConfig |
|
from transformers.utils import logging |
|
|
|
logger = logging.get_logger(__name__) |
|
|
|
INTERNLM2_PRETRAINED_CONFIG_ARCHIVE_MAP = {} |
|
|
|
|
|
|
|
class InternLM2Config(PretrainedConfig): |
|
r""" |
|
This is the configuration class to store the configuration of a [`InternLM2Model`]. It is used to instantiate |
|
an InternLM2 model according to the specified arguments, defining the model architecture. Instantiating a |
|
configuration with the defaults will yield a similar configuration to that of the InternLM2-7B. |
|
|
|
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 32000): |
|
Vocabulary size of the InternLM2 model. Defines the number of different tokens that can be represented |
|
by the `inputs_ids` passed when calling [`InternLM2Model`] |
|
hidden_size (`int`, *optional*, defaults to 4096): |
|
Dimension of the hidden representations. |
|
intermediate_size (`int`, *optional*, defaults to 11008): |
|
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 32): |
|
Number of attention heads for each attention layer in the Transformer encoder. |
|
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 2048): |
|
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). |
|
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-12): |
|
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 `False`): |
|
Whether to tie weight embeddings |
|
Example: |
|
|
|
""" |
|
model_type = "internlm2" |
|
_auto_class = "AutoConfig" |
|
|
|
def __init__( |
|
self, |
|
vocab_size=103168, |
|
hidden_size=4096, |
|
intermediate_size=11008, |
|
num_hidden_layers=32, |
|
num_attention_heads=32, |
|
num_key_value_heads=None, |
|
hidden_act="silu", |
|
max_position_embeddings=2048, |
|
initializer_range=0.02, |
|
rms_norm_eps=1e-6, |
|
use_cache=True, |
|
pad_token_id=0, |
|
bos_token_id=1, |
|
eos_token_id=2, |
|
tie_word_embeddings=False, |
|
bias=True, |
|
rope_theta=10000, |
|
rope_scaling=None, |
|
attn_implementation="eager", |
|
**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.bias = bias |
|
|
|
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.use_cache = use_cache |
|
self.rope_theta = rope_theta |
|
self.rope_scaling = rope_scaling |
|
self._rope_scaling_validation() |
|
|
|
self.attn_implementation = attn_implementation |
|
if self.attn_implementation is None: |
|
self.attn_implementation = "eager" |
|
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, |
|
) |
|
|
|
def _rope_scaling_validation(self): |
|
""" |
|
Validate the `rope_scaling` configuration. |
|
""" |
|
if self.rope_scaling is None: |
|
return |
|
|
|
if not isinstance(self.rope_scaling, dict) or len(self.rope_scaling) != 2: |
|
raise ValueError( |
|
"`rope_scaling` must be a dictionary with with two fields, `type` and `factor`, " |
|
f"got {self.rope_scaling}" |
|
) |
|
rope_scaling_type = self.rope_scaling.get("type", None) |
|
rope_scaling_factor = self.rope_scaling.get("factor", None) |
|
if rope_scaling_type is None or rope_scaling_type not in ["linear", "dynamic"]: |
|
raise ValueError( |
|
f"`rope_scaling`'s type field must be one of ['linear', 'dynamic'], got {rope_scaling_type}" |
|
) |
|
if rope_scaling_factor is None or not isinstance(rope_scaling_factor, float) or rope_scaling_factor < 1.0: |
|
raise ValueError(f"`rope_scaling`'s factor field must be a float >= 1, got {rope_scaling_factor}") |
|
|