Comments (2)
Hi @LaniakeaS this happens because to calculate memory requirement, one needs hidden_size
, intermediate_size
, num_layers
, vocab_size
of the model (these are usually present in config.json & the app reads it from there)
But when you just input the size, the app has no idea about above values & has to "infer" them based on some assumptions. This part of the code, approximates the values of hidden_size
etc. using just the final size (in billion) of the model
Lines 671 to 705 in a702c37
This causes a difference, because given just the final size of the model it's impossible to say what EXACT hidden_size etc. they had
from gpu_poor.
thank you for your answer!
from gpu_poor.
Related Issues (9)
- Results are inconsistent and is not reliable enough HOT 6
- What is [Prompt len] and [Tokens to Generate]? HOT 3
- Test results are different HOT 6
- API to use this repo HOT 1
- The memory usage in LoRA finetuning HOT 1
- DeepSpeed support HOT 1
- compute in gpu_configs.json meaning HOT 1
- why batch size does not effect to memory usage in inference mode
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 gpu_poor.