| base_model: THUDM/glm-4-9b-chat-1m | |
| language: | |
| - zh | |
| - en | |
| license: other | |
| license_name: glm-4 | |
| license_link: https://huggingface.co/THUDM/glm-4-9b-chat-1m/blob/main/LICENSE | |
| tags: | |
| - glm | |
| - chatglm | |
| - thudm | |
| - openvino | |
| - nncf | |
| - 8-bit | |
| inference: false | |
| base_model_relation: quantized | |
| This model is a quantized version of [`THUDM/glm-4-9b-chat-1m`](https://huggingface.co/THUDM/glm-4-9b-chat-1m) and is converted to the OpenVINO format. This model was obtained via the [nncf-quantization](https://huggingface.co/spaces/echarlaix/nncf-quantization) space with [optimum-intel](https://github.com/huggingface/optimum-intel). | |
| First make sure you have `optimum-intel` installed: | |
| ```bash | |
| pip install optimum[openvino] | |
| ``` | |
| To load your model you can do as follows: | |
| ```python | |
| from optimum.intel import OVModelForCausalLM | |
| model_id = "AIFunOver/glm-4-9b-chat-1m-openvino-8bit" | |
| model = OVModelForCausalLM.from_pretrained(model_id) | |
| ``` | |