vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'master' of https://github.com/liuwei-git/llama.cpp

Browse source
This commit is contained in:
Wei Liu 2024-04-24 01:48:23 +08:00
commit 725afbcf52
1 changed files with 24 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

25
convert-hf-to-gguf.py
View file

@ -2885,6 +2885,29 @@ def main() -> None:
print(f"Model successfully exported to '{fname_out}'")
def main_dbg():
dir_model = Path("d:/models/phi3")
fname_out = Path("c:/models/phi3_fp16.gguf")
print(f"Loading model: {dir_model.name}")
hparams = Model.load_hparams(dir_model)
with torch.inference_mode():
model_class = Model.from_model_architecture(hparams["architectures"][0])
model_instance = model_class(dir_model, gguf.GGMLQuantizationType.F16, fname_out, None)
print("Set model parameters")
model_instance.set_gguf_parameters()
print("Set model tokenizer")
model_instance.set_vocab()
print(f"Exporting model to '{fname_out}'")
model_instance.write()
print(f"Model successfully exported to '{fname_out}'")
if __name__ == '__main__':
main()
main_dbg()