Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,26 @@
+---
+base_model: THUDM/chatglm3-6b
+language:
+- zh
+- en
+tags:
+- glm
+- chatglm
+- thudm
+- openvino
+- nncf
+- 8-bit
+base_model_relation: quantized
+---
+
+This model is a quantized version of [`THUDM/chatglm3-6b`](https://huggingface.co/THUDM/chatglm3-6b) 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/chatglm3-6b-openvino-8bit"
+model = OVModelForCausalLM.from_pretrained(model_id)
+```