PRM and fine-tuned LLM used in our PURE github repo: https://github.com/CJReinforce/PURE
Jina Chris
jinachris
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 21 hours ago
Self-rewarding correction for mathematical reasoning
updated
a model
6 days ago
jinachris/Qwen2.5-7B-PURE-PRM
updated
a model
6 days ago
jinachris/Qwen2.5-7B-PURE-VR
Organizations
None yet
Collections
1
models
4
datasets
None public yet