create model card
Browse files
README.md
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- zh
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- chatglm
|
| 7 |
+
- glm
|
| 8 |
+
- onnx
|
| 9 |
+
- onnxruntime
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# ChatGLM-6B + ONNX
|
| 13 |
+
|
| 14 |
+
This model is exported from [ChatGLM-6b](https://huggingface.co/THUDM/chatglm-6b) with int8 quantization and optimized for [ONNXRuntime](https://onnxruntime.ai/) inference.
|
| 15 |
+
|
| 16 |
+
Inference code with ONNXRuntime is uploaded with the model. Install requirements and run `streamlit run web-ui.py` to start chatting. Currently the `MatMulInteger` (for u8s8 data type) and `DynamicQuantizeLinear` operators are only supported on CPU.
|
| 17 |
+
|
| 18 |
+
安装依赖并运行 `streamlit run web-ui.py` 预览模型效果。由于 ONNXRuntime 算子支持问题，目前仅能够使用 CPU 进行推理。
|
| 19 |
+
|
| 20 |
+
Codes are released under MIT license.
|
| 21 |
+
|
| 22 |
+
Model weights are released under the same license as ChatGLM-6b, see [MODEL LICENSE](https://huggingface.co/THUDM/chatglm-6b/blob/main/MODEL_LICENSE).
|