tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix: customized dataset with simpo (#2894) [skip ci]

Browse Source
This commit is contained in:
Jiawei Liu
2025-07-12 10:40:30 -05:00
committed by GitHub
parent 4dc5910e1c
commit 7fb8441e0e
3 changed files with 17 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
docs/rlhf.qmd
View File

@@ -274,15 +274,14 @@ rl: dpo
datasets:
- path: ...
split: train
type: user_defined.default
field_prompt: "prompt"
field_system: "system"
field_chosen: "chosen"
field_rejected: "rejected"
prompt_format: "{prompt}"
chosen_format: "{chosen}"
rejected_format: "{rejected}"
type:
field_prompt: "prompt"
field_system: "system"
field_chosen: "chosen"
field_rejected: "rejected"
prompt_format: "{prompt}"
chosen_format: "{chosen}"
rejected_format: "{rejected}"
```
The input format is a simple JSON input with customizable fields based on the above config.
@@ -475,14 +474,13 @@ rl: kto
datasets:
- path: ...
split: train
type: user_defined.default
field_prompt: "prompt"
field_system: "system"
field_completion: "completion"
field_label: "label"
prompt_format: "{prompt}"
completion_format: "{completion}"
type:
field_prompt: "prompt"
field_system: "system"
field_completion: "completion"
field_label: "label"
prompt_format: "{prompt}"
completion_format: "{completion}"
```
The input format is a simple JSON input with customizable fields based on the above config.