Pinned Loading

1. llama-family-70b-chat-4-shards llama-family-70b-chat-4-shards Public

   llama-70b-chat-4-shards implementation

   Python 13 2

2. Shadow-LLM/shadow-alignment Shadow-LLM/shadow-alignment Public

   Python 1

3. JEKimLab/SSAH JEKimLab/SSAH Public

   Superficial Safety Alignment Hypothesis

   Python 3

4. JEKimLab/Safety-Alignment-With-Explicit-Safety-Signal JEKimLab/Safety-Alignment-With-Explicit-Safety-Signal Public

   Safety Alignment Can Be Not Superficial With Explicit Safety Signals

   Python 2

5. JEKimLab/Backdoor-Vaccine JEKimLab/Backdoor-Vaccine Public

   Purifying Generative LLMs from Backdoors without Prior Knowledge or Clean Reference

   Python 4 2

6. JEKimLab/Security-before-Safety JEKimLab/Security-before-Safety Public

   Position: Security Before Safety: A Backdoor-Centric View of LLM Output Risks in the Private AI Era