arxiv:2403.19154
Chinmaya Andukuri
scandukuri
AI & ML interests
LM reasoning, LM problem-solving, bootstrapping, alignment
Organizations
models 13
scandukuri/Llama-3.1-8B-Instruct-UpFront-detailed-dialogue-only
Updated
scandukuri/Llama-3.1-8B-Instruct-RoleReversal-detailed-dialogue-only
Updated
scandukuri/Llama-3.1-8B-Instruct-UserSide-detailed-dialogue-only
Updated
scandukuri/Llama-3.1-8B-Instruct-UpFront-vanilla-dialogue-only
Updated
scandukuri/Llama-3.1-8B-Instruct-RoleReversal-vanilla-dialogue-only
Updated
scandukuri/Llama-3.1-8B-Instruct-UserSide-vanilla-dialogue-only
Updated
scandukuri/modified-Llama-3.1-8B-Instruct-tokenizer-add-user-generation-prompt
Updated
scandukuri/user-behavior-classifier-gemma-3-270m-it
0.3B • Updated • 2
scandukuri/user-behavior-classifier-Llama-3.1-8B-Instruct-scalar-head-only
Text Classification • 8B • Updated • 3
scandukuri/user-behavior-classifier-Llama-3.1-8B-Instruct-scalar-head-attention
Text Classification • 8B • Updated • 1
datasets 10
scandukuri/test-annotated-wildchat-usersim
Viewer • Updated • 11 • 9
scandukuri/main-annotated-wildchat-usersim
Viewer • Updated • 1.06k • 7
scandukuri/english-annotated-deduped-toy-wildchat
Viewer • Updated • 112 • 5
scandukuri/ultrachat_200k-expanded-300000-samples
Viewer • Updated • 300k • 12
scandukuri/lmsys-chat-1m-expanded-500000-samples
Viewer • Updated • 500k • 14
scandukuri/user-simulator-synthesis-Llama-3.1-8B-Instruct-scalar-head-scored
Viewer • Updated • 600 • 6
scandukuri/lights-out-3x3
Viewer • Updated • 300 • 5
scandukuri/Magpie-Air-MT-300K-expanded-100k-samples
Viewer • Updated • 100k • 41
scandukuri/lmsys-chat-1m-expanded-100k-samples
Viewer • Updated • 100k • 9
scandukuri/humaneval-patch
Viewer • Updated • 632 • 7 • 1