Multilingual Sentence & Image Embeddings with BERT

Fast and memory-efficient exact attention

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Python SDK for Milvus.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

Snowplow event tracker for client-side and server-side JavaScript. Add analytics to your websites, web apps and servers.

Simple, unified interface to multiple Generative AI providers

LlamaIndex is a data framework for your LLM applications

Snowplow event tracker for Python. Add analytics to your Python and Django apps, webapps and games

Open standard for machine learning interoperability

Share Milvus proto files between Milvus repository and SDK repositories

A cloud-native vector database, storage for next generation AI applications

The embedding/reranking model zoo help user to convert their unstructured data into embeddings

Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.

Open-source web platform used to create live reporting dashboards from APIs, MongoDB, Firestore, MySQL, PostgreSQL, and more 📈📊

The Elastic stack (ELK) powered by Docker and Compose.

Google Cloud Client Library for Python

The leader in Next-Generation Customer Data Infrastructure

Tensor library for machine learning

Inference Llama 2 in one file of pure C

Port of Facebook's LLaMA model in C/C++

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models