Princeton-SysML Jailbreak_LLM issues - Githubissues

Princeton-SysML / Jailbreak_LLM

153 stars 14 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Chat templates are not used

#14 Rachneet closed 2 months ago
1
potential issue in get_sentence_embedding()

#13 terarachang opened 5 months ago
0
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?

#12 alongflow opened 6 months ago
1
Did system prompts are used for GCG and Generation Exploitation methods respectively in experimental results reported in the paper?

#11 alongflow opened 6 months ago
1
What is the difference between top_k=1 and greedy decoding, and why should we experiment separately?

#10 zggg1p opened 8 months ago
0
The output of the mpt-30b-chat contains a large number of irrelevant characters

#9 zggg1p opened 9 months ago
0
Missing Chat Template

#8 justinphan3110cais opened 9 months ago
2
Issues while Running FlanT5-small model with JailBreak

#7 aneekroy opened 11 months ago
0
fix typo in `evaluate.py`

#6 chujiezheng closed 11 months ago
0
Another Question about Default Transformer Decoding Config

#5 chujiezheng opened 12 months ago
1
About Input Formats for Different Models

#4 chujiezheng opened 12 months ago
3
(Maybe) Bugs in the code.

#3 Junjie-Chu opened 12 months ago
1
Performance of the evaluator

#2 fabrahman closed 11 months ago
1
Fix typo in README.md

#1 eltociear closed 1 year ago
0