Commit
•
ed4183b
1
Parent(s):
ac28c26
Update README.md
Browse files
README.md
CHANGED
@@ -95,6 +95,8 @@ while line:
|
|
95 |
|
96 |
```
|
97 |
|
|
|
|
|
98 |
## Limitations
|
99 |
There still exists a few issues in the model trained on current base model and data:
|
100 |
|
@@ -165,6 +167,8 @@ while line:
|
|
165 |
|
166 |
```
|
167 |
|
|
|
|
|
168 |
## 局限性和使用限制
|
169 |
基于当前数据和基础模型训练得到的SFT模型,在效果上仍存在以下问题:
|
170 |
|
|
|
95 |
|
96 |
```
|
97 |
|
98 |
+
The above example did not utilize the context from previous turns of the conversation. If you want to perform multi-turn dialogue understanding, you can concatenate the previous turns of the conversation in the format of Human:{input}\n\nAssistant:{output} and input it to the generate function.
|
99 |
+
|
100 |
## Limitations
|
101 |
There still exists a few issues in the model trained on current base model and data:
|
102 |
|
|
|
167 |
|
168 |
```
|
169 |
|
170 |
+
上面样例没有利用对话上文,如果你想做多轮对话理解,可以将对话上文按照Human:{input}\n\nAssistant:{output} 方式拼接起来输入给generate函数
|
171 |
+
|
172 |
## 局限性和使用限制
|
173 |
基于当前数据和基础模型训练得到的SFT模型,在效果上仍存在以下问题:
|
174 |
|