Support BailingMoE

Author: CISC

gguf-py/gguf/constants.py

@@ -287,6 +287,7 @@ class MODEL_ARCH(IntEnum):
     CHAMELEON        = auto()
     WAVTOKENIZER_DEC = auto()
     PLM              = auto()
+    BAILINGMOE       = auto()
 
 
 class MODEL_TENSOR(IntEnum):
@@ -490,6 +491,7 @@ class MODEL_TENSOR(IntEnum):
     MODEL_ARCH.CHAMELEON:        "chameleon",
     MODEL_ARCH.WAVTOKENIZER_DEC: "wavtokenizer-dec",
     MODEL_ARCH.PLM:              "plm",
+    MODEL_ARCH.BAILINGMOE:       "bailingmoe",
 }
 
 TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
@@ -1667,6 +1669,28 @@ class MODEL_TENSOR(IntEnum):
         MODEL_TENSOR.POSNET_ATTN_V,
         MODEL_TENSOR.POSNET_ATTN_OUT,
     ],
+    MODEL_ARCH.BAILINGMOE: [
+        MODEL_TENSOR.TOKEN_EMBD,
+        MODEL_TENSOR.OUTPUT_NORM,
+        MODEL_TENSOR.OUTPUT,
+        MODEL_TENSOR.ROPE_FREQS,
+        MODEL_TENSOR.ATTN_NORM,
+        MODEL_TENSOR.ATTN_Q,
+        MODEL_TENSOR.ATTN_K,
+        MODEL_TENSOR.ATTN_V,
+        MODEL_TENSOR.ATTN_OUT,
+        MODEL_TENSOR.FFN_GATE_INP,
+        MODEL_TENSOR.FFN_NORM,
+        MODEL_TENSOR.FFN_GATE,
+        MODEL_TENSOR.FFN_DOWN,
+        MODEL_TENSOR.FFN_UP,
+        MODEL_TENSOR.FFN_GATE_EXP,
+        MODEL_TENSOR.FFN_DOWN_EXP,
+        MODEL_TENSOR.FFN_UP_EXP,
+        MODEL_TENSOR.FFN_GATE_SHEXP,
+        MODEL_TENSOR.FFN_DOWN_SHEXP,
+        MODEL_TENSOR.FFN_UP_SHEXP,
+    ],
     # TODO
 }
 
@@ -1719,6 +1743,9 @@ class MODEL_TENSOR(IntEnum):
         MODEL_TENSOR.ROPE_FREQS,
         MODEL_TENSOR.ATTN_ROT_EMBD,
     ],
+    MODEL_ARCH.BAILINGMOE: [
+        MODEL_TENSOR.ROPE_FREQS,
+    ],
 }
 
 #

gguf-py/gguf/tensor_mapping.py

@@ -29,6 +29,7 @@ class TensorNameMap:
             "shared",                                    # t5
             "rwkv.embeddings",                           # rwkv6
             "model.embeddings",                          # rwkv7
+            "model.word_embeddings",                     # bailingmoe
         ),
 
         # Token type embeddings