Princeton-SysML / Jailbreak_LLM

Princeton-SysML/Jailbreak_LLM Issues

Missing Chat Template
Updated 21 days ago2
Chat templates are not used
Closed 2 months ago1
potential issue in get_sentence_embedding()
Updated 5 months ago
Did system prompts are used for GCG and Generation Exploitation methods respectively in experimental results reported in the paper?
Updated 6 months ago1
For llama2, use_default config seems to have top-k values 50 because of the default value of hugging face config, but did llama2 use top-k?
Updated 6 months ago1
What is the difference between top_k=1 and greedy decoding, and why should we experiment separately?
Updated 9 months ago
The output of the mpt-30b-chat contains a large number of irrelevant characters
Updated 9 months ago
Issues while Running FlanT5-small model with JailBreak
Updated a year ago
About Input Formats for Different Models
Updated a year ago3
(Maybe) Bugs in the code.
Updated a year ago1
Another Question about Default Transformer Decoding Config
Updated a year ago1
Performance of the evaluator
Closed a year ago1