| from transformers.configuration_utils import PretrainedConfig | |
| from transformers.utils import logging | |
| logger = logging.get_logger(__name__) | |
| class MiniPhiConfig(PretrainedConfig): | |
| model_type = "phi3" | |
| keys_to_ignore_at_inference = ["past_key_values"] | |
| def __init__( | |
| self, | |
| vocab_size=32000, | |
| hidden_size=768, | |
| intermediate_size=2048, | |
| num_hidden_layers=12, | |
| num_attention_heads=12, | |
| num_key_value_heads=None, | |
| resid_pdrop=0.0, | |
| embd_pdrop=0.0, | |
| attention_dropout=0.0, | |
| hidden_act="silu", | |
| max_position_embeddings=512, | |
| original_max_position_embeddings=512, | |
| initializer_range=0.02, | |
| rms_norm_eps=1e-5, | |
| use_cache=True, | |
| tie_word_embeddings=False, | |
| rope_theta=10000.0, | |
| rope_scaling=None, | |
| bos_token_id=2, | |
| eos_token_id=1, | |
| pad_token_id=0, | |
| sliding_window=None, | |
| use_cope=True, | |
| **kwargs, | |
| ): | |
| self.vocab_size = vocab_size | |
| 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.resid_pdrop = resid_pdrop | |
| self.embd_pdrop = embd_pdrop | |
| self.attention_dropout = attention_dropout | |
| self.hidden_act = hidden_act | |
| self.max_position_embeddings = max_position_embeddings | |
| self.original_max_position_embeddings = original_max_position_embeddings | |
| 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.sliding_window = sliding_window | |
| self.use_cope = use_cope | |
| super().__init__( | |
| bos_token_id=bos_token_id, | |
| eos_token_id=eos_token_id, | |
| pad_token_id=pad_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) != 3: | |
| raise ValueError( | |
| "`rope_scaling` must be a dictionary with three fields, `type`, `short_factor` and `long_factor`, " | |
| f"got {self.rope_scaling}" | |
| ) | |
| rope_scaling_type = self.rope_scaling.get("type", None) | |
| rope_scaling_short_factor = self.rope_scaling.get("short_factor", None) | |
| rope_scaling_long_factor = self.rope_scaling.get("long_factor", None) | |
| if rope_scaling_type is None or rope_scaling_type not in ["su", "yarn"]: | |
| raise ValueError( | |
| f"`rope_scaling`'s type field must be one of ['su', 'yarn'], got {rope_scaling_type}") | |
| if not ( | |
| isinstance(rope_scaling_short_factor, list) | |
| and all(isinstance(x, (int, float)) for x in rope_scaling_short_factor) | |
| ): | |
| raise ValueError( | |
| f"`rope_scaling`'s short_factor field must be a list of numbers, got {rope_scaling_short_factor}" | |
| ) | |
| if not len(rope_scaling_short_factor) == self.hidden_size // self.num_attention_heads // 2: | |
| raise ValueError( | |
| f"`rope_scaling`'s short_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_short_factor)}" | |
| ) | |
| if not ( | |
| isinstance(rope_scaling_long_factor, list) | |
| and all(isinstance(x, (int, float)) for x in rope_scaling_long_factor) | |
| ): | |
| raise ValueError( | |
| f"`rope_scaling`'s long_factor field must be a list of numbers, got {rope_scaling_long_factor}" | |
| ) | |
| if not len(rope_scaling_long_factor) == self.hidden_size // self.num_attention_heads // 2: | |
| raise ValueError( | |
| f"`rope_scaling`'s long_factor field must have length {self.hidden_size // self.num_attention_heads // 2}, got {len(rope_scaling_long_factor)}" | |
| ) | |