Post
1235
Di Zhang
di-zhang-fdu
AI & ML interests
AI4Chem, LLM, Green LLM
Recent Activity
updated
a dataset
2 days ago
di-zhang-fdu/MATH12000
upvoted
a
paper
4 days ago
REINFORCE++: A Simple and Efficient Approach for Aligning Large Language
Models
new activity
14 days ago
AI4Chem/ChemBench4K:Chembench数据集的一些问题
Organizations
Posts
21
Post
2595
LLaMA-O1-PRM and LLaMA-O1-Reinforcement will release in this weekend.
We have implemented a novel Reinforcement finetune(RFT) pipeline that taught models learning reasoning and reward labeling without human annotation.
We have implemented a novel Reinforcement finetune(RFT) pipeline that taught models learning reasoning and reward labeling without human annotation.
datasets
35
di-zhang-fdu/MATH12000
Viewer
•
Updated
•
12k
•
14
di-zhang-fdu/OpenLongCoT-prm-rectify
Viewer
•
Updated
•
445k
•
67
di-zhang-fdu/AIME_1983_2024
Viewer
•
Updated
•
933
•
461
•
17
di-zhang-fdu/UltraChat-200k
Viewer
•
Updated
•
515k
•
60
di-zhang-fdu/OpenLongCoT-Pretrain-v2-filtered
Viewer
•
Updated
•
135k
•
44
di-zhang-fdu/OpenLongCoT-Pretrain-v2
Viewer
•
Updated
•
137k
•
99
•
3
di-zhang-fdu/OpenLongCoT-SFT-v2
Viewer
•
Updated
•
273k
•
45
di-zhang-fdu/OpenLongCoT-SFT-v2-filtered
Viewer
•
Updated
•
2.02M
•
66
di-zhang-fdu/OpenLongCoT-SFT-problems-v2
Viewer
•
Updated
•
2.04M
•
58
di-zhang-fdu/llama_o1_offline_training_data_v1
Viewer
•
Updated
•
19.3k
•
48
•
3