agentscope-ai / agentscope-ai/Trinity-RFT

[FEATURE] Recommended way of producing multiple Experiences in multi-turn dialogs

Aperta
#269 1 commento 0 reazioni 0 assegnatari Vedi su GitHub
enhancement
Lingua principale
Python
Stelle
701
Fork
79
Merge medio
8h 7m
PR unite (30g)
1

Descrizione

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?

Guida per i contributori

Apri la guida per i contributori

Valutazione

Questa issue non è ancora stata valutata.

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.