Skip to content

Commit 234387d

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 ebc24f9 commit 234387d

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
@@ -3932,7 +3932,7 @@ def prepare_tensors(self):
39323932

39333933

39343934
@Model.register("GraniteForCausalLM")
3935-
class GraniteModel(Model):
3935+
class GraniteModel(LlamaModel):
39363936
"""Conversion for IBM's GraniteForCausalLM"""
39373937
model_arch = gguf.MODEL_ARCH.GRANITE
39383938

0 commit comments

Comments
 (0)