| from transformers.models.qwen2.configuration_qwen2 import Qwen2Config
|
| from transformers.modeling_rope_utils import rope_config_validation
|
| from transformers.utils import logging
|
|
|
| logger = logging.get_logger(__name__)
|
|
|
|
|
| class VGSConfig(Qwen2Config):
|
| model_type = 'vgs'
|
| def __init__(
|
| self,
|
| vocab_size=151936,
|
| hidden_size=1536,
|
| intermediate_size=8960,
|
| num_hidden_layers=28,
|
| num_attention_heads=12,
|
| num_key_value_heads=2,
|
| hidden_act="silu",
|
| max_position_embeddings=131072,
|
| initializer_range=0.02,
|
| rms_norm_eps=1e-6,
|
| use_cache=False,
|
| tie_word_embeddings=False,
|
| rope_theta=10000.0,
|
| rope_scaling=None,
|
| use_sliding_window=False,
|
| sliding_window=4096,
|
| max_window_layers=21,
|
| attention_dropout=0.05,
|
| num_labels=3,
|
| use_bias=False,
|
| **kwargs,
|
| ):
|
| super().__init__(
|
| tie_word_embeddings=tie_word_embeddings,
|
| **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.use_sliding_window = use_sliding_window
|
| self.sliding_window = sliding_window
|
| self.max_window_layers = max_window_layers
|
|
|
|
|
| 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.attention_dropout = attention_dropout
|
| self.num_labels = num_labels
|
| self.use_bias = use_bias
|
|
|
|
|
| if self.rope_scaling is not None and "type" in self.rope_scaling:
|
| self.rope_scaling["rope_type"] = self.rope_scaling["type"]
|
| rope_config_validation(self)
|
|
|
