Update README.md
Browse files
README.md
CHANGED
|
@@ -30,6 +30,8 @@ For models in other languages check [our Kurage collection](https://huggingface.
|
|
| 30 |
|
| 31 |
This model was trained using a ml.gu7ef.8xlarge-gu100 instance on [Platform For AI](https://www.alibabacloud.com/en/product/machine-learning) from [Alibaba Cloud](https://www.alibabacloud.com/).
|
| 32 |
|
|
|
|
|
|
|
| 33 |
# Basic usage
|
| 34 |
|
| 35 |
To use the model for basic multi-chunk RAG, you can use the following code:
|
|
|
|
| 30 |
|
| 31 |
This model was trained using a ml.gu7ef.8xlarge-gu100 instance on [Platform For AI](https://www.alibabacloud.com/en/product/machine-learning) from [Alibaba Cloud](https://www.alibabacloud.com/).
|
| 32 |
|
| 33 |
+
Note - There is a known issue with the single-chunk RAG mode sometimes saying that it cannot answer a question based on the text when it actually can. This was because our single-chunk training data was 50:50 answers vs cannot answer scenarios, making the model overly conservative. We will address this in a week or two when we re-train using 90:10 data with [the coming release of Qwen 2.5](https://x.com/zhouwenmeng/status/1834899729165304198).
|
| 34 |
+
|
| 35 |
# Basic usage
|
| 36 |
|
| 37 |
To use the model for basic multi-chunk RAG, you can use the following code:
|