Zhilin Wang

zhilinw's activity

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

authored a paper 6 days ago

Dedicated Feedback and Edit Models Empower Inference-Time Scaling for Open-Ended General-Domain Tasks

Paper • 2503.04378 • Published 10 days ago • 6

New activity in nvidia/Llama-3.1-Nemotron-70B-Reward-HF 2 months ago

Why the hf-format model does not have rm head, since the original format model does have.

1

#7 opened 2 months ago by

eyuansu71

New activity in nvidia/Llama-3.1-Nemotron-70B-Reward-HF 4 months ago

Question on tokenizer chat template and readout

1

#4 opened 4 months ago by

dereklim

New activity in nvidia/Llama-3.1-Nemotron-70B-Reward 5 months ago

Should we use the 5th dimension of the output only?

1

#2 opened 5 months ago by

liangqxx

updated a collection 5 months ago

Llama-3.1-Nemotron-70B

Collection

SOTA models on Arena Hard and RewardBench as of 1 Oct 2024. • 6 items • Updated Jan 17 • 153

updated 2 models 5 months ago

nvidia/Llama-3.1-Nemotron-70B-Reward-HF

Updated Oct 15, 2024 • 461 • 80

nvidia/Llama-3.1-Nemotron-70B-Reward

Updated Oct 15, 2024 • 39 • 71

updated a dataset 5 months ago

nvidia/HelpSteer2

Viewer • Updated Dec 18, 2024 • 21.4k • 3.11k • 409

New activity in nvidia/HelpSteer2 5 months ago

Preference split not loading

2

#5 opened 5 months ago by

sanderland

New activity in nvidia/Llama-3.1-Nemotron-70B-Reward-HF 5 months ago

Vllm

2

#2 opened 5 months ago by

dbasu

Add proper library tag

2

#1 opened 5 months ago by

osanseviero

New activity in nvidia/Llama-3.1-Nemotron-70B-Reward 5 months ago

Add pipeline tag

2

#1 opened 5 months ago by

nielsr

commented a paper 5 months ago

HelpSteer2-Preference: Complementing Ratings with Preferences

Paper • 2410.01257 • Published Oct 2, 2024 • 23 •

5