Rank-32 LoRA adapters for the classify/flower pointwise-undetectable fine-tuning attacks on Inkling-Small, Inkling, Qwen3.6-35B-A3B.
Clément Dumas
Butanium
AI & ML interests
None yet
Recent Activity
updated a model 3 days ago
Butanium/ft-attack-repro-inkling-classify updated a model 3 days ago
Butanium/ft-attack-repro-qwen3.6-35b-a3b-flower updated a model 3 days ago
Butanium/ft-attack-repro-qwen3.6-35b-a3b-classifyOrganizations
models 104
Butanium/ft-attack-repro-qwen3.6-35b-a3b-flower
Updated • 15
Butanium/ft-attack-repro-inkling-flower
Updated
Butanium/ft-attack-repro-qwen3.6-35b-a3b-classify
Updated • 17
Butanium/ft-attack-repro-inkling-classify
Updated
Butanium/ft-attack-repro-inkling-small-flower-wsnorm
Updated
Butanium/ft-attack-repro-inkling-small-flower
Updated
Butanium/ft-attack-repro-inkling-small-classify-wsnorm
Updated
Butanium/ft-attack-repro-inkling-small-classify
Updated
Butanium/wp-deepseek-v31-cigarette_only_68
Updated • 23
Butanium/wp-deepseek-v31-soup_health0.5
Updated • 23
datasets 15
Butanium/persona-negation-judgments
Viewer • Updated • 320k • 17
Butanium/lora-amplification-identity-judgments
Viewer • Updated • 153k • 13
Butanium/assistant-axis-constitution-steering
Viewer • Updated • 310k • 21
Butanium/gemma-3-4b-it-assistant-axis
Updated • 26
Butanium/llama-3.1-8b-instruct-assistant-axis
Updated • 123 • 1
Butanium/qwen-2.5-7b-instruct-assistant-axis
Updated • 114
Butanium/assistant-axis-sarcasm
Updated • 9
Butanium/persona-steering-1
Updated • 11
Butanium/femto-fineweb
Viewer • Updated • 18 • 21
Butanium/femto-ultrachat
Viewer • Updated • 18 • 29