[Feature Request] omegaPRM reproduced by openR: data used to synthesize process reward models #1279
Open
1 of 2 tasks
Labels
Data
Related to camel data processing
enhancement
New feature or request
research
Task related to research
Milestone
Required prerequisites
Motivation
omegaPRM reproduced by openR: data used to synthesize process reward models
for datagene
reference:https://github.com/openreasoner/openr/tree/main/data
paper:https://arxiv.org/abs/2406.06592
Solution
reference:https://github.com/openreasoner/openr/tree/main/data
paper:https://arxiv.org/abs/2406.06592
Alternatives
already done the first experimental version
Additional context
already done the first experimental version
The text was updated successfully, but these errors were encountered: