-
Jina AI
- Berlin, Germany
- @michael_g_u
- @michael-g-u.bsky.social
Stars
Model implementation for the contextual embeddings project
German dataset for DPR model training
Run Effective Large Batch Contrastive Learning Beyond GPU/TPU Memory Constraint
Hybrid search engine, combining best features of text and semantic search worlds
MinHash, LSH, LSH Forest, Weighted MinHash, HyperLogLog, HyperLogLog++, LSH Ensemble and HNSW
Instruct-tune LLaMA on consumer hardware
Chain together LLMs for reasoning & orchestrate multiple large models for accomplishing complex tasks
An open source implementation of CLIP.
Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptatio…
State-of-the-Art Text Embeddings
🎯 Task-oriented embedding tuning for BERT, CLIP, etc.
Simplify deploying and managing Jina projects on Jina Cloud
☁️ Build multimodal AI applications with cloud-native stack
A tool for manually classification of dwtc tables. The result is then being used as a training data set.
A collection of free Bootstrap 5 templates.
Examples showing how to use Wikidata Toolkit as a Maven library in your project
Java library to interact with Wikibase
This repo contains tutorials on OpenCV-Python library using new cv2 interface