arxiv:2602.15829
Tomás Vergara
tvergara
AI & ML interests
None yet
Recent Activity
updated a model about 13 hours ago
tvergara/tar-wmdp-Llama-3.1-8B-Instruct-73d8c8e83c07 updated a model about 13 hours ago
tvergara/tar-evilmath-Llama-3.1-8B-Instruct-09003ee4e852 published a model 4 days ago
tvergara/tar-wmdp-Llama-3.1-8B-Instruct-73d8c8e83c07Organizations
models 9
tvergara/tar-evilmath-Llama-3.1-8B-Instruct-09003ee4e852
8B • Updated • 234
tvergara/tar-wmdp-Llama-3.1-8B-Instruct-73d8c8e83c07
8B • Updated • 232
tvergara/sft-wmdp-Llama-3.1-8B-Instruct-ec55867d84a0
8B • Updated • 156
tvergara/sft-evilmath-Llama-3.1-8B-Instruct-d650794f965d
8B • Updated • 141
tvergara/cb-wmdp-Llama-3.1-8B-Instruct-bfbf3e38793c
8B • Updated • 152
tvergara/cb-evilmath-Llama-3.1-8B-Instruct-d7ba262bbc28
8B • Updated • 138
tvergara/smollm3-circuit-breaker
3B • Updated • 14
tvergara/smollm3-safety-pair-unsafe
3B • Updated • 1
tvergara/smollm3-safety-pair-safe
3B • Updated • 2
datasets 0
None public yet