Zihan Liu

zihanliu's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 2 months ago

NVIDIA Nemotron V2

Collection

Open, Production-ready Enterprise Models. Nvidia Open Model license. • 9 items • Updated 2 days ago • 72

updated a model 4 months ago

nvidia/AceReason-Nemotron-1.1-7B

Text Generation • 8B • Updated Jul 11 • 7.6k • • 56

New activity in nvidia/AceReason-1.1-SFT 4 months ago

Add task_categories and library_name to metadata

#1 opened 5 months ago by

nielsr

updated a collection 5 months ago

AceReason

Collection

Math and Code reasoning model trained through reinforcement learning (RL) • 7 items • Updated 9 days ago • 18

upvoted a paper 5 months ago

AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy

Paper • 2506.13284 • Published Jun 16 • 26

commented a paper 5 months ago

AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy

Paper • 2506.13284 • Published Jun 16 • 26 •

4

liked a dataset 5 months ago

nvidia/AceReason-Math

Viewer • Updated Jun 18 • 49.6k • 919 • 35

authored 2 papers 5 months ago

From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models

Paper • 2504.06214 • Published Apr 8

AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning

Paper • 2505.16400 • Published May 22 • 34

liked a dataset 5 months ago

nvidia/AceReason-1.1-SFT

Viewer • Updated Jun 18 • 3.96M • 2.93k • 91

liked a model 5 months ago

nvidia/AceReason-Nemotron-1.1-7B

Text Generation • 8B • Updated Jul 11 • 7.6k • • 56

published a model 5 months ago

nvidia/AceReason-Nemotron-1.1-7B

Text Generation • 8B • Updated Jul 11 • 7.6k • • 56

published a dataset 5 months ago

nvidia/AceReason-1.1-SFT

Viewer • Updated Jun 18 • 3.96M • 2.93k • 91

updated a dataset 5 months ago

nvidia/AceReason-1.1-SFT

Viewer • Updated Jun 18 • 3.96M • 2.93k • 91

upvoted a collection 5 months ago

AceReason

Collection

Math and Code reasoning model trained through reinforcement learning (RL) • 7 items • Updated 9 days ago • 18

updated a collection 5 months ago

AceReason

Collection

Math and Code reasoning model trained through reinforcement learning (RL) • 7 items • Updated 9 days ago • 18

upvoted a paper 5 months ago

AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning

Paper • 2505.16400 • Published May 22 • 34

liked 2 models 5 months ago

nvidia/AceReason-Nemotron-7B

Text Generation • 8B • Updated Jun 17 • 4.54k • • 19

nvidia/AceReason-Nemotron-14B

Text Generation • 15B • Updated Jun 17 • 7.58k • • 93