iamgroot42 / mimir Goto Github PK
View Code? Open in Web Editor NEWPython package for measuring memorization in LLMs.
Home Page: https://iamgroot42.github.io/mimir/
License: MIT License
Python package for measuring memorization in LLMs.
Home Page: https://iamgroot42.github.io/mimir/
License: MIT License
Hi,
Thank you for the great work! I was not able to find the original Pile subcategory dataset (arXiv, Github etc.) in the huggingface data repo. There are only the processed ones (7-gram, 13-gram). Could you share the original ones as well?
Thank you!
Hi,
Thanks for sharing your code. I want to run the attacks you implemented on my own datasets, but I'm not sure where to start. Is there a guide or documentation the describes this?
Best,
Shane
Hi,
Just checked out the code, dataset_nonmember_key: str is missing from the definition of class ExperimentConfig(Serializable):
in mimir/config.py.
Best,
John
Hello,
Thanks for your valuable work on mimir!
If I understand correctly, GradNormAttack
is computing the average (across layers) of the gradient norm wrt. the model weights.
mimir/mimir/attacks/gradnorm.py
Line 41 in 6c61109
But the docstring indicates that the gradients are computed w.r.t. input tokens.
mimir/mimir/attacks/gradnorm.py
Line 18 in 6c61109
Since the original paper proposes both, I think there are two solutions:
Model.get_probabilities()
The results in Appendix C.1 suggest that in certain settings, one gradient type outperforms the other, while in other settings, the reverse is observed.
What do you think?
Hi,
I found your project to be helpful to my current paper, but I met some problems when I was trying python run.py --config configs/mi.json.
Problems:
An error reports split is Nonetype, which can be fixed by adjusting the mi.json as:
"dataset_member": "the_pile_pile_cc_ngram_13_0.2",
"dataset_nonmember": "the_pile_pile_cc_ngram_13_0.2",
An error reports there is no dataset key, which can be fixed by adding this line to the mi.json:
"dataset_key": "the_pile",
I don't whether my adjustments to mi.json are correct. If it's not, could you please give me some suggestions? If these are correct, I suggest adding some tutorial about config files in the github project.
Thanks,
Ethan
Hi,
I found a strange line here in your code - https://github.com/iamgroot42/mimir/blob/main/mimir/models.py#L183
Is this a bug or is there any other particular reason? It is currently overriding what I am specifying in the config file.
Thanks.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.