Comments (1)
Hi! You can see how we do this in the eval code. tl;dr we multiply the probabilities, which is equivalent to summing logprobs:
You'll notice that, in practice, we use negative log probabilities:
Given
from rome.
Related Issues (19)
- CUDA Out of Memory Error on Colab HOT 3
- Generating weights for efk/mend for new model HOT 1
- Best way to specify a non-standard cache directory HOT 1
- Any suggestions for extending this work to edit values? HOT 1
- T5 support HOT 2
- ImportError: cannot import name 'Literal' from 'typing' (/usr/lib/python3.7/typing.py) HOT 2
- Model- and data-dependent hyperparameters HOT 3
- CUDA out of memory error on an 11 GB GPU: Any easy ways to use multiple GPUs?
- Documentation for hparams? HOT 2
- How to apply this methods to a new LMs without fine-tune, like a bert? HOT 1
- How do you train KE and MEND with CounterFact?
- Code for Average Plot over Multiple Runs
- What is the performance of ROME at editing GPT-NeoX-20b?
- Code for computing the right vector for the rank-1 update
- What is the 'simple' principle of ROME?
- Conda setup issue HOT 1
- Confusion about pre/post rewrite probabilities of target true and target new HOT 5
- prob contributions by individual neuron rather than layer HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from rome.