Skip to content

Commit

Permalink
Merge pull request #140 from opentensor/dpo-reweighting
Browse files Browse the repository at this point in the history
reweighting reward models
  • Loading branch information
Eugene-hu authored Aug 28, 2023
2 parents bd315ec + e513a97 commit dc65c72
Showing 1 changed file with 2 additions and 2 deletions.
4 changes: 2 additions & 2 deletions openvalidators/reward/config.py
Original file line number Diff line number Diff line change
Expand Up @@ -35,8 +35,8 @@ class DefaultRewardFrameworkConfig:
"""Reward framework default configuration.
Note: All the weights should add up to 1.0.
"""
dpo_model_weight: float = 0.2
dpo_model_weight: float = 0.3
rlhf_model_weight: float = 0.4
reciprocate_model_weight: float = 0.4
reciprocate_model_weight: float = 0.3
dahoas_model_weight: float = 0
prompt_model_weight: float = 0

0 comments on commit dc65c72

Please sign in to comment.