Update README.md
Browse files
README.md
CHANGED
@@ -12,6 +12,7 @@ license: mit
|
|
12 |
- 在使用text-generation-webui作后台,SillyTavern做前端时,webui上MaxToken调到8K时SillyTavern的MaxToken要调整到18K,WebUI才不会提前截断
|
13 |
- 在SillyTavern上要得到Roleplay样式的长回复需做如下调整
|
14 |
- 使用ChatML作为指令格式
|
|
|
15 |
- 最后输出序列调整为 `### Response (2 paragraphs, engaging, natural, authentic, descriptive, creative):`
|
16 |
- 自定义停止符调整为 `["<|im_end|>用户\n", "\n### Input"]`
|
17 |
- 系统提示调整为 `Avoid repetition, don't loop. Develop the plot slowly, always stay in character. Describe all actions in full, elaborate, explicit, graphic, and vivid detail. Mention all relevant sensory perceptions.`
|
|
|
12 |
- 在使用text-generation-webui作后台,SillyTavern做前端时,webui上MaxToken调到8K时SillyTavern的MaxToken要调整到18K,WebUI才不会提前截断
|
13 |
- 在SillyTavern上要得到Roleplay样式的长回复需做如下调整
|
14 |
- 使用ChatML作为指令格式
|
15 |
+
- 勾选 `用换行符换行序列`
|
16 |
- 最后输出序列调整为 `### Response (2 paragraphs, engaging, natural, authentic, descriptive, creative):`
|
17 |
- 自定义停止符调整为 `["<|im_end|>用户\n", "\n### Input"]`
|
18 |
- 系统提示调整为 `Avoid repetition, don't loop. Develop the plot slowly, always stay in character. Describe all actions in full, elaborate, explicit, graphic, and vivid detail. Mention all relevant sensory perceptions.`
|