Keming Lu

keminglu's activity

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

commented a paper 4 months ago

Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model

Paper • 2408.10764 • Published Aug 20 • 8 •

2

New activity in nvidia/Nemotron-4-340B-Reward 6 months ago

Missing model_weights/model.rm_head._extra_state

1

#1 opened 6 months ago by

keminglu

New activity in moreh/MoMo-72B-lora-1.8.6-DPO 11 months ago

Qwen compabilitiy

2

#6 opened 11 months ago by

keminglu