Update README.md
Browse files
README.md
CHANGED
|
@@ -20,6 +20,8 @@ This is a mxfp4 version of [huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated](https
|
|
| 20 |
|
| 21 |
Reference [OpenAI GPT-OSS Quantization Aware Training (QAT) & Quantized Deployment](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/76e8ce21bf9ce4e0510fea96c998aaee7cfeaf7c/examples/gpt-oss/README.md)
|
| 22 |
|
|
|
|
|
|
|
| 23 |
```
|
| 24 |
pip install nvidia-modelopt[all]
|
| 25 |
|
|
|
|
| 20 |
|
| 21 |
Reference [OpenAI GPT-OSS Quantization Aware Training (QAT) & Quantized Deployment](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/76e8ce21bf9ce4e0510fea96c998aaee7cfeaf7c/examples/gpt-oss/README.md)
|
| 22 |
|
| 23 |
+
**This precision loss rate is high; fine-tuning through QAT may be needed to reduce the precision loss rate.**
|
| 24 |
+
|
| 25 |
```
|
| 26 |
pip install nvidia-modelopt[all]
|
| 27 |
|