From 667c501334ace706e3abc3f7a37cf1d6b4228745 Mon Sep 17 00:00:00 2001 From: ostix360 <55257054+ostix360@users.noreply.github.com> Date: Tue, 25 Apr 2023 23:33:08 +0200 Subject: [PATCH] py : cast lora_alpha to int in convert-lora-to-ggml (#1170) Co-authored-by: Pavol Rusnak --- convert-lora-to-ggml.py | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/convert-lora-to-ggml.py b/convert-lora-to-ggml.py index 8a2085c..9090e8d 100644 --- a/convert-lora-to-ggml.py +++ b/convert-lora-to-ggml.py @@ -49,7 +49,12 @@ def translate_tensor_name(t: str) -> str: def write_file_header(fout: TextIO, params: Dict[str, Any]) -> None: fout.write(b"ggla"[::-1]) # magic (ggml lora) fout.write(struct.pack("i", 1)) # file version - fout.write(struct.pack("ii", params["r"], params["lora_alpha"])) + fout.write(struct.pack("i", params["r"])) + # https://opendelta.readthedocs.io/en/latest/modules/deltas.html says that `lora_alpha` is an int + # but some models ship a float value instead + # let's convert to int, but fail if lossless conversion is not possible + assert int(params["lora_alpha"]) == params["lora_alpha"], "cannot convert float to int losslessly" + fout.write(struct.pack("i", int(params["lora_alpha"]))) def write_tensor_header( @@ -89,7 +94,7 @@ if params["peft_type"] != "LORA": print(f"Error: unsupported adapter type {params['peft_type']}, expected LORA") sys.exit(1) -if params["fan_in_fan_out"] == True: +if params["fan_in_fan_out"] is True: print("Error: param fan_in_fan_out is not supported") sys.exit(1)