dsgiitr / kge-clip
Knowledge Graph Embeddings (KGE) for RAG-LLMs. Our goal was to compare the mathematical differences between Traditional Static Multimodal Vector Embeddings (TVE) from Word2Vec and CLIP encoders for {text:image} datasets, and Knowledge Graph Embeddings (KGE) generated with REBEL triplets trained on PyKeen.
☆12Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for kge-clip
- A deep-dive on the entire history of deep-learning☆1,048Updated 4 months ago
- ☆6Updated last year
- The Dart implementation of atSDK used for implementing Atsign's technology into other software☆1,462Updated this week
- ☆14Updated 2 years ago
- Implemented Seq2Seq models for translating sentences with and without attention mechanism.☆12Updated 2 years ago
- All notebooks for the ML-101 competition to be submitted here.☆20Updated last year
- Walmart Inc. (formerly Wal-Mart Stores, Inc.) is an American multinational retail corporation that operates a chain of hypermarkets (also…☆12Updated last year
- Website for ACES☆21Updated 3 weeks ago
- HackSeries Website ACES☆23Updated last month
- ☆10Updated last year