Comments (2)
I had the same issue and just resolved it. Please note that my solution could not be right answer for your situation.
TLDR: it seems the issue could be caused by incompatible compiler's version to the compiled library that Longformer uses. You could resolve it through (1) install new library (glibc) through condo and then (2) add conda's library path to your environment.
Part 1. Check your gcc version
In my case, I first checked my compiler (gcc) version:
gcc -v
With this, I got to know that my compiler's version is gcc version 4.8.5
.
Through this table on the link, I found 4.8.5 uses/support GLIBCXX_3.4.19, not the one that Longformer needs. (Link: FoldingAtHome/fah-issues#1147 (comment))
The link also says GLIBCXX_3.4.20 is indeed on gcc version 4.9.0. So if your gcc version is below 4.9.0, it could be the same reason that I have.
Part 2. Install libgcc through conda
Based on my search on google, it seems basically you need to upgrade gcc but it requires sudo. For my case I don't have sudo. Another way to install the newer library is through conda's libgcc. Run following line:
conda install libgcc
Part 3. Add conda's library path to your LD_LIBRARY_PATH env variable.
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/path/to/your/anaconda3/lib
Then, the Longformer works as charm!
from longformer.
Closing. Please feel free to reopen or create a new one if you have more questions.
from longformer.
Related Issues (20)
- CUDA error: device-side assert triggered in multi class text classification
- AttributeError: 'RobertaEmbeddings' object has no attribute 'position_ids' HOT 1
- AttributeError: module 'dill._dill' has no attribute 'stack'
- Can't find a valid checkpoint at tmp
- One hot encoding classes
- LED Training Time
- Pretraining longformer for NER on big pdf text
- Why the TVM impelmentation is memroy efficient
- Updated BART to Longformer-encoder-decoder (LED) converter
- Answering performance of Longformer-base on the HotpotQA dev set
- Number of tokens per batch mismatch - longformer vs roberta HOT 1
- On cheatsheet
- @ibeltagy I have similar issues with converting the model to ONNX, I converted the model to ONNX model, but when I tried to infer with onnxruntime I got ScatterND error while session run. I am guessing there are some operations not supported by onnx.
- Longformer embeddings for calculating similarity score between 2 documents using KNN
- Where is the global attention?
- Reproducibility Problem
- may you share link to somebody else latest development for long sentences pls?
- Can Longformer support adapter transformer?
- "requirements.txt" update (transformers==3.0.2) HOT 2
- Cosine similarity scores between random words are well above 0.9 HOT 1
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 longformer.