Model: add openPangu-Embedded

[Lpzhan931]

Add a new model openPangu-Embedded-1/7B-V1.1.
Yu can get the the model from model path.

[Lpzhan931]

This pull request introduces support for the openPangu-Embedded-1/7B-V1.1 models within the llama.cpp.

Usage examples

Convert models to GGUF files:

python convert_hf_to_gguf.py /model/path/openPangu-Embedded-1B-V1.1/
    --outfile pangu_embedded_1B.gguf 
    --outtype f16

python convert_hf_to_gguf.py /model/path/openPangu-Embedded-7B-V1.1/
    --outfile pangu_embedded_7B.gguf 
    --outtype f16

Run the model:

./build/bin/llama-cli -m pangu_embedded_1B.gguf

./build/bin/llama-cli -m pangu_embedded_7B.gguf

References

openPangu-Embedded Models:
Winging/openpangu
openPangu
powered by openPangu（openPangu is a trademark of Huawei Technologies Co., Ltd.）

[Lpzhan931]

Hi, @CISC , thanks for reviewing. The model openPangu-Embedded can run correctly and I’ve also uploaded the converted GGUF model to the Hugging Face Hub.

The converted GGUF files can be accessed here: Lpzhan/openPangu-embedded-gguf.

Thank you very much for your time and review!

Below are some screenshots showing the model running successfully:

[Lpzhan931]

Hi @CISC,
I’ve addressed your comments and updated the PR.
Please have a look when you have time. Thanks again for your review!