mirror of
https://github.com/wassname/Open-Assistant.git
synced 2026-08-03 12:30:24 +08:00
Kian-Meng AngandGitHub
1e321a6fca
Found via `codespell -S .mypy_cache,yarn.lock,*.json,*.ipynb -L rouge,nam,vie`
25 lines
733 B
Markdown
25 lines
733 B
Markdown
Some other reward features we can use
|
|
|
|
0. Finish classification feature
|
|
|
|
1. Summaries from human feedback
|
|
|
|
- use `confidence` score into the RM learning, ensure the output rank score
|
|
correlates with confidence
|
|
|
|
- each labeling has a labeling `note`, basically comments by labeler, not sure
|
|
what else we can use
|
|
|
|
- ~~Use the score for "overall", "accuracy", "coverage", "coherence" from
|
|
axis/evals to train an addition model (rank additional aspect of the policy
|
|
model)~~
|
|
|
|
- this should be placed under experimental_dataset.py
|
|
|
|
2. Add support for anthropic dataset
|
|
|
|
- anthropic dataset is more like a conversation tree which is much complex than
|
|
simply question-answer schema
|
|
|
|
- this is basically a MCTS from alphazero.
|