CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

convert: fix Mistral3/Gemma3 model hparams init (#12571)

Browse Source 
* Fix Mistral3/Gemma3 model hparams init

* set positional args correctly

* use existing hparams if passed
This commit is contained in:
Sigbjørn Skjæret
2025-03-25 23:03:10 +01:00
committed by GitHub
parent ef19c71769
commit 53af4dba42
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
convert_hf_to_gguf.py
View File

@@ -1752,7 +1752,7 @@ class Mistral3Model(LlamaModel):
# we need to merge the text_config into the root level of hparams
def __init__(self, *args, **kwargs):
hparams = Model.load_hparams(kwargs["dir_model"])
hparams = kwargs["hparams"] if "hparams" in kwargs else Model.load_hparams(args[0])
if "text_config" in hparams:
hparams = {**hparams, **hparams["text_config"]}
kwargs["hparams"] = hparams
@@ -3385,7 +3385,7 @@ class Gemma3Model(Model):
# we need to merge the text_config into the root level of hparams
def __init__(self, *args, **kwargs):
hparams = Model.load_hparams(kwargs["dir_model"])
hparams = kwargs["hparams"] if "hparams" in kwargs else Model.load_hparams(args[0])
if "text_config" in hparams:
hparams = {**hparams, **hparams["text_config"]}
kwargs["hparams"] = hparams
@@ -5358,7 +5358,7 @@ def main() -> None:
logger.error(f"Model {model_architecture} is not supported")
sys.exit(1)
model_instance = model_class(dir_model=dir_model, ftype=output_type, fname_out=fname_out,
model_instance = model_class(dir_model, output_type, fname_out,
is_big_endian=args.bigendian, use_temp_file=args.use_temp_file,
eager=args.no_lazy,
metadata_override=args.metadata, model_name=args.model_name,