Skip to content

Commit 2ed6a17

Browse files
committed
fix(convert_hf_to_gguf): Use LlamaModel as base for GraniteModel
The defaults in LlamaModel are needed for Granite as well Branch: GraniteLM Signed-off-by: Gabe Goodhart <[email protected]>
1 parent e8a1073 commit 2ed6a17

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

convert_hf_to_gguf.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3951,7 +3951,7 @@ def prepare_tensors(self):
39513951

39523952

39533953
@Model.register("GraniteForCausalLM")
3954-
class GraniteModel(Model):
3954+
class GraniteModel(LlamaModel):
39553955
"""Conversion for IBM's GraniteForCausalLM"""
39563956
model_arch = gguf.MODEL_ARCH.GRANITE
39573957

0 commit comments

Comments
 (0)