Comments (1)
Thank you for the interest in our work!
I was able to reproduce this. The gap in scores depends on what attention implementation is used in Transformers. I measured our PPL numbers with seqlen=8192 using "_attn_implementation": "eager"
in the config.json file. If you use newer versions of transformers, by default _attn_implementation": "sdpa"
is used instead. When using "sdpa"
I get 4.73 instead of 4.76. Let me know if this doesn't fix the issue.
from kvquant.
Related Issues (9)
- PRE-ROPE quantization during inference HOT 1
- reproduce the ablation results in Figure 1 HOT 1
- Can this be done for other transformer based models? HOT 1
- AttributeError: 'LlamaModel' object has no attribute 'split_gpus' HOT 1
- The value of self.include_sparse being 0 causes the assert (False) error
- Where is the code of "ATOM-4bit"in the KVQuant codebase?
- Question about storage
- CUDA error: an illegal memory access was encountered
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 kvquant.