Post
1233
Di Zhang
qq8933
AI & ML interests
AI4Chem, LLM, Green LLM
Recent Activity
updated
a dataset
1 day ago
qq8933/MATH12000
upvoted
a
paper
2 days ago
REINFORCE++: A Simple and Efficient Approach for Aligning Large Language
Models
new activity
13 days ago
AI4Chem/ChemBench4K:Chembench数据集的一些问题
Organizations
Posts
21
Post
2593
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
qq8933/MATH12000
Updated
•
13
qq8933/OpenLongCoT-prm-rectify
Viewer
•
Updated
•
445k
•
67
qq8933/AIME_1983_2024
Viewer
•
Updated
•
933
•
508
•
17
qq8933/UltraChat-200k
Viewer
•
Updated
•
515k
•
61
qq8933/OpenLongCoT-Pretrain-v2-filtered
Viewer
•
Updated
•
135k
•
43
qq8933/OpenLongCoT-Pretrain-v2
Viewer
•
Updated
•
137k
•
98
•
3
qq8933/OpenLongCoT-SFT-v2
Viewer
•
Updated
•
273k
•
45
qq8933/OpenLongCoT-SFT-v2-filtered
Viewer
•
Updated
•
2.02M
•
66
qq8933/OpenLongCoT-SFT-problems-v2
Viewer
•
Updated
•
2.04M
•
58
qq8933/llama_o1_offline_training_data_v1
Viewer
•
Updated
•
19.3k
•
41
•
3