awesome-transformer
github.com/skyandcloud/awesome-transformer ↗This repo is not maintained. For latest version, please visit https://github.com/ictnlp. A collection of transformer's guides, implementations and variants.
44
GitHub Stars
39
Curated Resources
5
Categories
35 min ago
Last Refreshed
PapersImplementations & How to reproduce paper's result?Training tipsFurtherContributors
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me nmt basic resources from awesome-transformer"
Installation instructions →What's inside
Papers
- A Structured Self-attentive Sentence EmbeddingNMT Basic
- Attention is All You NeedTransformer original paper
- Convolutional Sequence to Sequence LearningNMT Basic
- DL4MTNMT Basic
- Effective Approaches to Attention-based Neural Machine TranslationNMT Basic
- Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine TranslationNMT Basic
Further
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- Improving Language Understanding by Generative Pre-Training
- Scaling Neural Machine Translation
- Self-Attention with Relative Position Representations
- The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation
- Universal Transformer
Implementations & How to reproduce paper's result?
- codeMinimal, paper-equavalent but not certainly performance-reproducable implementations(both PyTorch implementations)
- codeMinimal, paper-equavalent but not certainly performance-reproducable implementations(both PyTorch implementations)
- corpus preprocessed by OpenNMTComplex, performance-reproducable implementations
- fairseq-pyComplex, performance-reproducable implementations
- fairseq-py exampleComplex, performance-reproducable implementations
- fairseq-py issueComplex, performance-reproducable implementations
Contributors
Training tips
Showing a sample of 39 resources. View the full list on GitHub →