| import warnings |
|
|
| from transformers.configuration_utils import PretrainedConfig |
|
|
|
|
| class GatedDeltaProductConfig(PretrainedConfig): |
| model_type = "gated_deltaproduct" |
| keys_to_ignore_at_inference = ["past_key_values"] |
|
|
| def __init__( |
| self, |
| attn_mode: str = "chunk", |
| conv_size: int = 4, |
| head_dim: int = 256, |
| num_heads: int = 6, |
| hidden_size: int = 2048, |
| expand_v: float = 2.0, |
| use_gate: bool = True, |
| use_short_conv: bool = True, |
| max_position_embeddings: int = 2048, |
| hidden_ratio: int | None = 4, |
| intermediate_size: int | None = None, |
| hidden_act: str = "swish", |
| num_hidden_layers: int = 21, |
| norm_eps: float = 1e-6, |
| attn: dict | None = None, |
| use_cache: bool = True, |
| pad_token_id: int = None, |
| bos_token_id: int = 1, |
| eos_token_id: int = 2, |
| tie_word_embeddings: bool = False, |
| initializer_range: float = 0.02, |
| fuse_norm: bool = True, |
| fuse_swiglu: bool = True, |
| fuse_cross_entropy: bool = True, |
| fuse_linear_cross_entropy: bool = False, |
| use_l2warp: bool = False, |
| vocab_size: int = 32000, |
| use_forget_gate: bool = False, |
| allow_neg_eigval: bool = False, |
| num_householder: int = 1, |
| **kwargs, |
| ): |
| self.attn_mode = attn_mode |
| self.conv_size = conv_size |
| self.head_dim = head_dim |
| self.num_heads = num_heads |
| self.hidden_size = hidden_size |
| self.expand_v = expand_v |
| self.use_gate = use_gate |
| self.use_short_conv = use_short_conv |
| self.max_position_embeddings = max_position_embeddings |
|
|
| self.hidden_ratio = hidden_ratio |
| self.intermediate_size = intermediate_size |
| self.hidden_act = hidden_act |
| self.num_hidden_layers = num_hidden_layers |
| self.norm_eps = norm_eps |
| self.attn = attn |
| self.use_cache = use_cache |
| self.initializer_range = initializer_range |
|
|
| self.fuse_norm = fuse_norm |
| self.fuse_swiglu = fuse_swiglu |
| self.fuse_cross_entropy = fuse_cross_entropy |
| self.fuse_linear_cross_entropy = fuse_linear_cross_entropy |
| self.use_l2warp = use_l2warp |
| self.vocab_size = vocab_size |
|
|
| if fuse_cross_entropy and fuse_linear_cross_entropy: |
| raise ValueError( |
| "`fuse_cross_entropy` and `fuse_linear_cross_entropy` cannot be True at the same time.", |
| ) |
| if fuse_linear_cross_entropy: |
| warnings.warn( |
| "`fuse_linear_cross_entropy` is enabled, which can improves memory efficiency " |
| "at the potential cost of reduced precision. " |
| "If you observe issues like loss divergence, consider disabling this setting.", |
| stacklevel=2, |
| ) |
|
|
| |
| self.allow_neg_eigval = allow_neg_eigval |
| self.num_householder = num_householder |
| self.use_forget_gate = use_forget_gate |
|
|
| if attn is not None: |
| if not isinstance(attn, dict): |
| raise ValueError("attn must be a dictionary") |
| if "layers" not in attn: |
| raise ValueError("Layer indices must be provided to initialize hybrid attention layers") |
| if "num_heads" not in attn: |
| raise ValueError("Number of heads must be provided to initialize hybrid attention layers") |
| attn["num_kv_heads"] = attn.get("num_kv_heads", attn["num_heads"]) |
| attn["qkv_bias"] = attn.get("qkv_bias", False) |
| attn["window_size"] = attn.get("window_size", None) |
| attn["rope_theta"] = attn.get("rope_theta", 10000.0) |
|
|
| 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, |
| ) |
|
|
