Comments (3)
I add dropout in MLP layer in chinese dataset,and result is more good.
from simcse.
Hi,
You don't need "changing the dim of the vectors" for an MLP layer to work. Here the MLP layer is just for adding some transformation over the original CL representation so it might suit our need better.
from simcse.
I add dropout in MLP layer in chinese dataset,and result is more good.
Hello, I would like to add dropout to the MLP layer to improve the performance of the model, but I found that dropout is already used in the source code, so I would like to ask you how to add dropout to the MLP layer.
from simcse.
Related Issues (20)
- Why add two sentences in prepare_features? HOT 3
- why mlp_only_train=True during unsupervised training? HOT 2
- [question] Pretrined sentence embeddings model fine tuning HOT 2
- 关于simcse build_index 的速度问题 HOT 6
- Difference in models between train and evaluation scripts. HOT 4
- TypeError: object of type 'IndexFlatIP' has no len() HOT 4
- model = SimCSE("princeton-nlp/sup-simcse-bert-base-uncased")调用 HOT 3
- Can I load saved index to GPU? HOT 2
- Can I replace the base model with longformer? Is it a simple replacement or does the code also need to be changed? Thank you for your answer. HOT 4
- Why divide by temp when calculating cosine similarity HOT 1
- ValueError: Mixed precision training with AMP or APEX (`--fp16`) can only be used on CUDA devices.
- 关于两次前向传播 HOT 2
- AttributeError: 'OurTrainingArguments' object has no attribute 'distributed_state' HOT 2
- setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (750,) + inhomogeneous part. HOT 2
- 关于 Supervised SimCSE 的 GPU Memory Usage HOT 2
- An error when max_seq_length is set too long HOT 1
- drpout HOT 2
- couldn't install cimcse HOT 7
- Question about the comparison of data augmentations's reproduce HOT 2
- The function ‘search’ only returns one result 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 simcse.