Update configuration_Llamoe.py

configuration_Llamoe.py

@@ -1,72 +1,63 @@
-from transformers.configuration_utils import PretrainedConfig
-from transformers.utils import logging
+import math
+from typing import Optional
 
+from transformers import PretrainedConfig
 
-logger = logging.get_logger(__name__)
 
-GEMMOE_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "damerajee/Llamoe-test": "https://huggingface.co/damerajee/Llamoe-test/resolve/main/config.json",
-}
+class PhiConfig(PretrainedConfig):
+    """Phi configuration."""
 
-
-class LlamoeConfig(PretrainedConfig):
-
-
-    model_type = "llamoe"
-    keys_to_ignore_at_inference = ["past_key_values"]
+    model_type = "llama"
+    attribute_map = {
+        "max_position_embeddings": "n_positions",
+        "hidden_size": "n_embd",
+        "num_attention_heads": "n_head",
+        "num_hidden_layers": "n_layer",
+    }
 
     def __init__(
         self,
-        vocab_size=32000,
-        hidden_size=4096,
-        intermediate_size=11008,
-        num_hidden_layers=32,
-        num_attention_heads=32,
-        num_key_value_heads=32,
-        head_dim=128,
-        hidden_act="silu",
-        max_position_embeddings=2048,
-        initializer_range=0.02,
-        rms_norm_eps=1e-06,
-        use_cache=True,
-        pad_token_id=0,
-        eos_token_id=1,
-        bos_token_id=2,
-        tie_word_embeddings=False,
-        rope_theta=10000.0,
-        attention_bias=False,
-        attention_dropout=0.0,
-        num_experts_per_tok=2,
-        num_local_experts=8,
-        router_aux_loss_coef=0.02,
-        output_router_logits=False,
-        **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.head_dim = head_dim
-        self.hidden_act = hidden_act
-        self.hidden_activation = hidden_activation
-        self.num_key_value_heads = num_key_value_heads
-        self.initializer_range = initializer_range
-        self.rms_norm_eps = rms_norm_eps
-        self.use_cache = use_cache
-        self.rope_theta = rope_theta
-        self.attention_bias = attention_bias 
-        self.attention_dropout = attention_dropout
+        vocab_size: int = 50304,
+        n_positions: int = 2048,
+        n_embd: int = 1024,
+        n_layer: int = 20,
+        n_inner: Optional[int] = None,
+        n_head: int = 16,
+        n_head_kv: Optional[int] = None,
+        num_experts_per_tok: int = 2,
+        num_local_experts: int = 4,
+        rotary_dim: Optional[int] = 32,
+        activation_function: Optional[str] = "gelu_new",
+        flash_attn: bool = False,
+        flash_rotary: bool = False,
+        fused_dense: bool = False,
+        attn_pdrop: float = 0.0,
+        embd_pdrop: float = 0.0,
+        resid_pdrop: float = 0.0,
+        layer_norm_epsilon: float = 1e-5,
+        initializer_range: float = 0.02,
+        tie_word_embeddings: bool = False,
+        pad_vocab_size_multiple: int = 64,
+        **kwargs
+    ) -> None:
+        self.vocab_size = int(math.ceil(vocab_size / pad_vocab_size_multiple) * pad_vocab_size_multiple)
+        self.n_positions = n_positions
+        self.n_embd = n_embd
+        self.n_layer = n_layer
+        self.n_inner = n_inner
+        self.n_head = n_head
+        self.n_head_kv = n_head_kv
         self.num_experts_per_tok = num_experts_per_tok
         self.num_local_experts = num_local_experts
-        self.router_aux_loss_coef = router_aux_loss_coef
-        self.output_router_logits = output_router_logits
-         
-        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,
-        )
+        self.rotary_dim = min(rotary_dim, n_embd // n_head)
+        self.activation_function = activation_function
+        self.flash_attn = flash_attn
+        self.flash_rotary = flash_rotary
+        self.fused_dense = fused_dense
+        self.attn_pdrop = attn_pdrop
+        self.embd_pdrop = embd_pdrop
+        self.resid_pdrop = resid_pdrop
+        self.layer_norm_epsilon = layer_norm_epsilon
+        self.initializer_range = initializer_range
+
+        super().__init__(tie_word_embeddings=tie_word_embeddings, **kwargs)