OpenVINO models
Collection
A collection of quantized LLMs in OpenVINO format
•
3 items
•
Updated
This is an INT4 quantized version of the mistralai/Mistral-7B-Instruct-v0.2
model. The Python packages used in creating this model are as follows:
openvino==2024.3.0.dev20240528
openvino-nightly==2024.3.0.dev20240528
openvino-tokenizers==2024.3.0.0.dev20240528
optimum==1.19.2
optimum-intel==1.17.0.dev0+aefabf0
nncf==2.11.0.dev0+90a7f0d5
torch==2.3.0+cu121
transformers==4.40.2
This quantized model is created using the following command:
optimum-cli export openvino -m "mistralai/Mistral-7B-Instruct-v0.2" --task text-generation-with-past --weight-format int4 --group-size 128 --trust-remote-code ./Mistral-7B-Instruct-v0.2-ov-int4
For more details, run the following command from your Python environment: optimum-cli export openvino --help
INFO:nncf:Statistics of the bitwidth distribution:
Num bits (N) | % all parameters (layers) | % ratio-defining parameters (layers) |
---|---|---|
8 | 23% (82 / 226) | 20% (80 / 224) |
4 | 77% (144 / 226) | 80% (144 / 224) |