Skip to content

Commit 8086380

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 e73d795 commit 8086380

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
@@ -4081,7 +4081,7 @@ def prepare_tensors(self):
40814081

40824082

40834083
@Model.register("GraniteForCausalLM")
4084-
class GraniteModel(Model):
4084+
class GraniteModel(LlamaModel):
40854085
"""Conversion for IBM's GraniteForCausalLM"""
40864086
model_arch = gguf.MODEL_ARCH.GRANITE
40874087

0 commit comments

Comments
 (0)