Comments (9)
Hi. @pengzju You are right, this is what GRACE is supposed to do, however, the code does not act like that. Let's talk about this issue step by step. This issue happens with model: llama2. You can reproduce this error with your default hparams in ./hparams/GRACE/llama-7B.yaml but just change eps to 100 or more, like 1000 or 10000. The query key changes in a single prompt if you just use one picec of data to edit. For llama model in a single generation step, when generating answers, the query variable changes in multiple forward(self, *args) calls from GRACEAdapter(torch.nn.Module). For the dataset you provided in ./data/portability/One Hop/zsre_mend_eval_portability_gpt4.json, the rewrite acc drops from 0.9916 to 0.3273. Please check this out. Thank.
from easyedit.
Thanks!
from easyedit.
Hi, I don't quite get what you mean. From my experience, increasing eps
doesn't lead to a decrease in rewrite acc because a larger deferral radius should result in a higher hit probability. Additionally, could you please explain in detail what you mean by "The key used to query in the codebook changes"?
from easyedit.
hi, could you please provide more details of your questions?
from easyedit.
I have fixed this issue (38c5c34), please update EasyEdit and try again
from easyedit.
Hi, do you have any further questions?
from easyedit.
Hi. The problem solved. Thanks for your help. I may close this issue.
from easyedit.
Hi. I need to reopen this issue. I just tested the new version. The editing speed is 5-10x slower then the previous version. Is this a normal phenomenon? By the way, does GRACE here support batch editing?
from easyedit.
Q1: It's normal. I just set n_iters
from 100 to 50. In addition, increasing eps
will reduce some fine-tuning costs because more Keys are shared
Q2: Nope. plz refer to GRACE paper: https://arxiv.org/abs/2211.11031
from easyedit.
Related Issues (20)
- Does the euclidean_distance accumulated or not? Why? HOT 5
- Request for a new editing method named Larimar HOT 2
- Question about edit performance HOT 3
- I met some problem when MMEdit HOT 4
- out of memory. Can I run multimodal_edit.py with multi-Gpus? HOT 5
- Edit return the unmodified model weights HOT 5
- unexpected_keys assertion error when running SERAC HOT 8
- Question about the padding_side configuration HOT 3
- Issue regarding the Wise model in a multi-GPU environment HOT 3
- 如何保存编辑后的模型? HOT 3
- 关于在Hallucination数据集上复现WISE模型的疑问 HOT 3
- [Feature Request] Support MQuAKE-2002 Dataset HOT 1
- WISE的loc_prompts HOT 2
- device使用不规范 HOT 1
- Support for instruct/chat models HOT 4
- How to save and load WISE models? HOT 3
- 用ROME编辑gpt2没有效果 HOT 5
- WISE编辑ZsRE-test-all.json报错 HOT 10
- dataset download speed is not stable HOT 2
- is cuda inevitable?[MacOS] 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 easyedit.