Comments (3)
Hi @kgravenreuth
We hosted the models using floating point with 16 bits (fp16). In version 2, we switch to use huggingface transformers. They host the models using fp32, hence, the models are twice as large.
Performance in terms of translation accuracy should be the same.
Will it be faster or slower: The size has here little impact, because the models can internally transferred between these two type of storing floating point numbers.
But it can be that the huggingface implementation is faster or slower then the previous fairseq implementation. Hope I can update the numbers soon
from easynmt.
Sadly huggingface models are much slower than the fairseq models.
I think a difference is the usage of FP32 vs. FP16 as fairseq is doing. Will check if converting the model to FP16 will speed up the computation.
from easynmt.
Hello. I'm wondering if you have any further infomation.. we'd like to run the m2m-100 model and I'm considering going back to the fairseq code that was removed with v2.0.0.
from easynmt.
Related Issues (20)
- Support for NLLB HOT 5
- Enable manually specifying the desired OPUS model? HOT 3
- Exception when trying to download Response 403 HOT 5
- Workflow for large datasets
- How to run test_translation_speed.py HOT 2
- EasyNMT
- Is there randomness in translation or does every translation lead to the exact same output?
- Finetune/Train on custom dataset
- Unable to translate from English to Thailand
- Is English to Thailand not available as opus-mt pre-trained model?
- Zsh: Illegal Hardware Instruction Issue on M2 MacBook
- Slow running on Colab
- Resource requirements for Docker Container CPU Image
- Gibberish translation coming for some languages HOT 1
- Demo doesn't allow selection of Target language
- Encountered error while trying to install fasttext HOT 2
- What's in v2.0.2
- gpu memory does not get released with `max_loaded_models`
- Suport for fine tuned models
- Support for new OPUS-MT models
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 easynmt.