base
BaseHarmlessnessListWiseReward
Bases: BaseListWisePrincipleReward
The assistant aims to answer questions, avoiding harmful behaviors such as spreading misinformation, spreading harmful ideas, or engaging in other harmful activities.
Source code in rm_gallery/gallery/rm/alignment/base.py
61 62 63 64 65 66 67 68 69 70 |
|
BaseHarmlessnessPointWiseReward
Bases: BasePointWisePrincipleReward
The assistant aims to answer questions, avoiding harmful behaviors such as spreading misinformation, spreading harmful ideas, or engaging in other harmful activities.
Source code in rm_gallery/gallery/rm/alignment/base.py
97 98 99 100 101 102 103 104 105 106 |
|
BaseHelpfulnessListWiseReward
Bases: BaseListWisePrincipleReward
The assistant aims to provide helpful and informative responses to users, responding to their queries with relevant and accurate information.
Source code in rm_gallery/gallery/rm/alignment/base.py
49 50 51 52 53 54 55 56 57 58 |
|
BaseHelpfulnessPointWiseReward
Bases: BasePointWisePrincipleReward
The assistant aims to provide helpful and informative responses to users, responding to their queries with relevant and accurate information.
Source code in rm_gallery/gallery/rm/alignment/base.py
85 86 87 88 89 90 91 92 93 94 |
|
BaseHonestyListWiseReward
Bases: BaseListWisePrincipleReward
The assistant aims to truthfully answer the user’s questions with no bias or prejudice.
Source code in rm_gallery/gallery/rm/alignment/base.py
73 74 75 76 77 78 79 80 81 82 |
|
BaseHonestyPointWiseReward
Bases: BasePointWisePrincipleReward
The assistant aims to truthfully answer the user’s questions with no bias or prejudice.
Source code in rm_gallery/gallery/rm/alignment/base.py
109 110 111 112 113 114 115 116 117 118 |
|