Models used in CHARM: Calibrating Reward Models With Chatbot Arena Scores.
shawnxzhu
shawnxzhu
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
Mosaic: Multi-Session Agentic Reinforcement Learning upvoted a paper about 1 month ago
SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking upvoted a paper 2 months ago
Training Diffusion Language Models for Black-Box OptimizationOrganizations
Datasets used in CHARM: Calibrating Reward Models With Chatbot Arena Scores.
-
shawnxzhu/CHARM-preference20K-gemma-2-9b-it-SimPO
Viewer • Updated • 20k • 118 -
shawnxzhu/CHARM-preference20K-GPT-4o-mini-2024-07-18
Viewer • Updated • 20k • 139 -
shawnxzhu/CHARM-preference20K-gemma-2-9b-it
Viewer • Updated • 20k • 80 -
shawnxzhu/CHARM-preference20K-Llama-3.1-8B-Instruct
Viewer • Updated • 20k • 92
Models used in CHARM: Calibrating Reward Models With Chatbot Arena Scores.
Datasets used in CHARM: Calibrating Reward Models With Chatbot Arena Scores.
-
shawnxzhu/CHARM-preference20K-gemma-2-9b-it-SimPO
Viewer • Updated • 20k • 118 -
shawnxzhu/CHARM-preference20K-GPT-4o-mini-2024-07-18
Viewer • Updated • 20k • 139 -
shawnxzhu/CHARM-preference20K-gemma-2-9b-it
Viewer • Updated • 20k • 80 -
shawnxzhu/CHARM-preference20K-Llama-3.1-8B-Instruct
Viewer • Updated • 20k • 92