Simple fine tuning on T4s of small llms can lead to jailbreak.
Sweker
Swekerr
AI & ML interests
None yet
Recent Activity
liked a model 29 days ago
mudler/Qwen3.8-27B-APEX-GGUF updated a collection about 1 month ago
Toxy LLMs updated a collection about 1 month ago
Toxy LLMsOrganizations
models 15
Swekerr/qwen3-1.7b_dapo_math_dapo-v1
Text Generation • 2B • Updated • 7
Swekerr/qwen3-0.6b_dapo_math_grpo-v1.1
Text Generation • 0.6B • Updated • 8
Swekerr/llama1b_dapo_math_grpo-v1.1
Text Generation • 1B • Updated • 4
Swekerr/llama1b_dapo_math_grpo-v1
Text Generation • 1B • Updated • 7
Swekerr/gsmma-270m-grpo
Text Generation • 0.3B • Updated • 8
Swekerr/toxy-qwen2.5-0.5b-sft-v1.0
Text Generation • 0.5B • Updated • 10
Swekerr/toxy-smollm2-360m-sft-v1.5
Text Generation • 0.4B • Updated • 13
Swekerr/toxy-smollm2-360m-sft-v1.0
Text Generation • 0.4B • Updated • 11
Swekerr/toxy-gemma3-270m-sft-v1.0
Text Generation • 0.3B • Updated • 7
Swekerr/Odia-BPE
Updated
datasets 0
None public yet