Update README.md
Browse files
README.md
CHANGED
|
@@ -117,6 +117,16 @@ In addition to the [Baichuan2-7B-Base](https://huggingface.co/baichuan-inc/Baich
|
|
| 117 |
|
| 118 |
|
| 119 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 120 |
# <span id="Terms">声明与协议/Terms and Conditions</span>
|
| 121 |
|
| 122 |
## 声明
|
|
@@ -176,3 +186,6 @@ Upon meeting the above conditions, you need to submit the application materials
|
|
| 176 |
[opensource@baichuan-inc.com]: mailto:opensource@baichuan-inc.com
|
| 177 |
[训练过程heckpoint下载]: https://huggingface.co/baichuan-inc/Baichuan2-7B-Intermediate-Checkpoints
|
| 178 |
[百川智能]: https://www.baichuan-ai.com
|
|
|
|
|
|
|
|
|
|
|
|
| 117 |
|
| 118 |
|
| 119 |
|
| 120 |
+
## 社区和生态
|
| 121 |
+
|
| 122 |
+
### Intel 酷睿 Ultra 平台运行百川大模型
|
| 123 |
+
|
| 124 |
+
使用酷睿™/至强® 可扩展处理器或配合锐炫™ GPU等进行部署[Baichuan2-7B-Chat]，[Baichuan2-13B-Chat]模型，推荐使用 BigDL-LLM([CPU], [GPU])以发挥更好推理性能。
|
| 125 |
+
|
| 126 |
+
详细支持信息可参考[中文操作手册](https://github.com/intel-analytics/bigdl-llm-tutorial/tree/main/Chinese_Version)，包括用notebook支持，[加载，优化，保存方法](https://github.com/intel-analytics/bigdl-llm-tutorial/blob/main/Chinese_Version/ch_3_AppDev_Basic/3_BasicApp.ipynb)等。
|
| 127 |
+
|
| 128 |
+
When deploy on Core™/Xeon® Scalable Processors or with Arc™ GPU, BigDL-LLM ([CPU], [GPU]) is recommended to take full advantage of better inference performance.
|
| 129 |
+
|
| 130 |
# <span id="Terms">声明与协议/Terms and Conditions</span>
|
| 131 |
|
| 132 |
## 声明
|
|
|
|
| 186 |
[opensource@baichuan-inc.com]: mailto:opensource@baichuan-inc.com
|
| 187 |
[训练过程heckpoint下载]: https://huggingface.co/baichuan-inc/Baichuan2-7B-Intermediate-Checkpoints
|
| 188 |
[百川智能]: https://www.baichuan-ai.com
|
| 189 |
+
|
| 190 |
+
[CPU]: https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/CPU/HF-Transformers-AutoModels/Model/baichuan2
|
| 191 |
+
[GPU]: https://github.com/intel-analytics/BigDL/tree/main/python/llm/example/GPU/HF-Transformers-AutoModels/Model/baichuan2
|