model : Plamo3 support (#17304)

* plamo3

* fix plamo3

* clean code

* clean up the code

* fix diff

* clean up the code

* clean up the code

* clean up the code

* clean up the code

* clean up the code

* clean up the code

* add chat_template if exist

* clean up the code

* fix cpu-backend

* chore: whitespace trim fix + typo fix

* Fix: address review feedback

* restore `FREQ_BASE_SWA` constant

* Fix: address review feedback2

* Fix:typecheck

* Fix: address review feedback3

* final cleanup

---------

Co-authored-by: mmngays <146910567+mmngays@users.noreply.github.com>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

gguf-py/gguf/constants.py

@@ -377,6 +377,7 @@ class MODEL_ARCH(IntEnum):
     PHIMOE           = auto()
     PLAMO            = auto()
     PLAMO2           = auto()
+    PLAMO3           = auto()
     CODESHELL        = auto()
     ORION            = auto()
     INTERNLM2        = auto()
@@ -773,6 +774,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
     MODEL_ARCH.PHIMOE:           "phimoe",
     MODEL_ARCH.PLAMO:            "plamo",
     MODEL_ARCH.PLAMO2:           "plamo2",
+    MODEL_ARCH.PLAMO3:           "plamo3",
     MODEL_ARCH.CODESHELL:        "codeshell",
     MODEL_ARCH.ORION:            "orion",
     MODEL_ARCH.INTERNLM2:        "internlm2",
@@ -1763,6 +1765,21 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
         MODEL_TENSOR.SSM_B_NORM,
         MODEL_TENSOR.SSM_C_NORM,
     ],
+    MODEL_ARCH.PLAMO3: [
+        MODEL_TENSOR.TOKEN_EMBD,
+        MODEL_TENSOR.OUTPUT_NORM,
+        MODEL_TENSOR.OUTPUT,
+        MODEL_TENSOR.ATTN_NORM,
+        MODEL_TENSOR.ATTN_QKV,
+        MODEL_TENSOR.ATTN_Q_NORM,
+        MODEL_TENSOR.ATTN_K_NORM,
+        MODEL_TENSOR.ATTN_OUT,
+        MODEL_TENSOR.ATTN_POST_NORM,
+        MODEL_TENSOR.FFN_NORM,
+        MODEL_TENSOR.FFN_DOWN,
+        MODEL_TENSOR.FFN_UP,
+        MODEL_TENSOR.FFN_POST_NORM,
+    ],
     MODEL_ARCH.GPT2: [
         MODEL_TENSOR.TOKEN_EMBD,
         MODEL_TENSOR.POS_EMBD,