ToLD-Br
adapters
| ToLD-Br | adapters | |
|---|---|---|
| 1 | 4 | |
| 34 | 2,414 | |
| - | 2.6% | |
| 2.6 | 8.6 | |
| 2 months ago | 6 days ago | |
| Jupyter Notebook | Jupyter Notebook | |
| GNU General Public License v3.0 or later | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
ToLD-Br
-
Toxicity in Tweets using a BERT model
The dataset is based on ToLD-Br, which is a huge dataset of tweets (or is it Xeets now?) that contains some additional info such as a classification if the text contains homophobia, obscenity, insults, racism, misogyny and xenophobia. The dataset for the competition, however, is a simple toxicity column.
adapters
-
[D] NLP question: does fine-tuning train input embedding?
Usually in computer vision resnets, people finetune only the last layers, but in NLP you tune the entire model. There are also plenty of instances where people try to not do this, such as in adapters, however.
-
[P] AdapterHub v2: Lightweight Transfer Learning with Transformers and Adapters
GitHub: https://github.com/Adapter-Hub/adapter-transformers
-
Our new state-of-the-art multilingual NLP Toolkit - Trankit has been released
Thanks for the question. The main libraries that Trankit's using are pytorch and adapter-transformers. For the GPU requirement, we have tested our toolkit on different scenarios and found that a single GPU with 4GB of memory would be enough for a comfortable use.
What are some alternatives?
haystack - :mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
clip-as-service - 🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
JointBERT - Pytorch implementation of JointBERT: "BERT for Joint Intent Classification and Slot Filling"
bertviz - BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
trankit - Trankit is a Light-Weight Transformer-based Python Toolkit for Multilingual Natural Language Processing
siamese-nn-semantic-text-similarity - A repository containing comprehensive Neural Networks based PyTorch implementations for the semantic text similarity task, including architectures such as: Siamese LSTM Siamese BiLSTM with Attention Siamese Transformer Siamese BERT.
LLM-Adapters - Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"