adapters
bertviz
adapters | bertviz | |
---|---|---|
4 | 15 | |
2,398 | 6,398 | |
1.9% | - | |
8.6 | 3.9 | |
4 days ago | 9 months ago | |
Jupyter Notebook | Python | |
Apache License 2.0 | 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.
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.
bertviz
-
StreamingLLM: tiny tweak to KV LRU improves long conversations
This seems only to work cause large GPTs have redundant, undercomplex attentions. See this issue in BertViz about attention in Llama: https://github.com/jessevig/bertviz/issues/128
-
[D] Is there a tool that indicates which parts of the input prompt impact the LLM's output the most?
https://github.com/jessevig/bertviz this could be helpful .. I was playing around with it a while ago to see how the attention weights are distributed across prompts
-
Show HN: Fully client-side GPT2 prediction visualizer
It would be interesting to have attention visualized as well, similar to how it's done in BertViz:
https://github.com/jessevig/bertviz
-
How to visualise LLMs ?
link for lazy: https://github.com/jessevig/bertviz
-
Ask HN: Can someone ELI5 Transformers and the “Attention is all we need” paper
The Illustrated Transfomer ( https://jalammar.github.io/illustrated-transformer/ ) and Visualizing attention ( https://towardsdatascience.com/deconstructing-bert-part-2-vi... ), are both really good resources. For a more ELI5 approach this non-technical explainer ( https://www.parand.com/a-non-technical-explanation-of-chatgp... ) covers it at a high level.
- Perplexity.ai Prompt Leakage
-
[Discussion] is attention an explanation?
You can get some information this way, but not everything you would want to know. You can try it yourself with BertViz.
-
using bert for relation extraction
2) BERT learns a lot in its embeddings: the BERTOLOGY paper (https://arxiv.org/abs/2002.12327) provides a great in-depth look at some of the broader linguistic traits that BERT learns. Different layers often learn different patterns, so the embeddings aren't really interpretable, but you can use something like bertviz (https://github.com/jessevig/bertviz) to explore attention weights across layers for predetermined examples
-
Maintaining context vs. overloading your Replika
I messed up a few things and mixed a couple others, anyways this site has a lot of decent information about it. https://towardsdatascience.com/deconstructing-bert-part-2-visualizing-the-inner-workings-of-attention-60a16d86b5c1
-
[D] code to visualize attention heads
Big fan of BertViz for this, widely used in research for this very purpose: https://github.com/jessevig/bertviz
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.
ecco - Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, BERT, RoBERTA, T5, and T0).
clip-as-service - 🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
FARM - :house_with_garden: Fast & easy transfer learning for NLP. Harvesting language models for the industry. Focus on Question Answering.
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
BERT-pytorch - Google AI 2018 BERT pytorch implementation
JointBERT - Pytorch implementation of JointBERT: "BERT for Joint Intent Classification and Slot Filling"
trankit - Trankit is a Light-Weight Transformer-based Python Toolkit for Multilingual Natural Language Processing
transformer-pytorch - Transformer: PyTorch Implementation of "Attention Is All You Need"
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.
DeBERTa - The implementation of DeBERTa