convert : yield Mamba2Model/GraniteMoeModel modify_tensors (#19157)

* convert : yield Mamba2Model/GraniteMoeModel modify_tensors

This commit updates the `GraniteHybridModel` class' modify_tensors
function to properly delegate to `Mamba2Model.modify_tensors` and
`GraniteMoeModel.modify_tensors` using 'yield from' instead of 'return'.

The motivation for this is that modify_tensors is a generator function
(it uses 'yield from'), but the two calls above use return statements
but don't yield anything which means that the the caller of this
function will not receive any yielded values from it. And this causes
layer tensors to be silently dropped during conversion.

diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py
index 6e6e618989bedf28d6c3bcc1c20698dfd43826e4..a391717e3252ef8a91bf53ce67d2b7dc467d6ef5 100755 (executable)
--- a/convert_hf_to_gguf.py
+++ b/convert_hf_to_gguf.py
@@ -8912,13 +8912,16 @@ class GraniteHybridModel(Mamba2Model, GraniteMoeModel):
             name.endswith("block_sparse_moe.input_linear.weight")
             or "shared_mlp" in name
         ):
-            return GraniteMoeModel.modify_tensors(self, data_torch, name, bid)
+            yield from GraniteMoeModel.modify_tensors(self, data_torch, name, bid)
+            return
 
         # Determine whether this is a mamba layer or an attention layer
         if bid in self._ssm_layers:
-            return Mamba2Model.modify_tensors(self, data_torch, name, bid)
+            yield from Mamba2Model.modify_tensors(self, data_torch, name, bid)
+            return
         elif bid in self._attn_layers:
-            return GraniteMoeModel.modify_tensors(self, data_torch, name, bid)
+            yield from GraniteMoeModel.modify_tensors(self, data_torch, name, bid)
+            return
         yield from ModelBase.modify_tensors(self, data_torch, name, bid)
 
     def set_gguf_parameters(self):