agentscope-ai / agentscope-ai/Trinity-RFT
[FEATURE] Recommended way of producing multiple Experiences in multi-turn dialogs
- 主要語言
- Python
- 星號
- 701
- 分支
- 79
- 平均合併
- 8 小時 7 分鐘
- 30 天內合併 PR
- 1
描述
Imagine a two-turn dialog:
1. system prompt
2. first user prompt
3. first assistant response
4. second user prompt
5. final assistant response
One could represent it as Experience by concatenating everything and masking everything except two assistant responses
Another way could be splitting it into two experiences.
The first one:
1. system prompt
2. first user prompt
3. first assistant response (masked as target assistant)
The second one:
1. system prompt
2. first user prompt
3. first assistant response
4. second user prompt
5. final assistant response (masked as target assistant)
Is this other multi-experience way recommended? If so, how to best produce it?
E.g. should a `run()` method return these several experiences, right?
貢獻指南
評估
這個 Issue 還沒有評估資料。