dblakely
Follow
Stars
Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
Infinity is a high-throughput, low-latency REST API for serving vector embeddings, supporting a wide range of text-embedding models and frameworks.
🕑 Modern Timeline Component for React
Multilingual Sentence & Image Embeddings with BERT
A blazing fast inference solution for text embeddings models
An extremely fast Python package installer and resolver, written in Rust.
🗺 High Quality GeoJSON maps programmatically generated.
A global, public domain map dataset available at three scales and featuring tightly integrated vector and raster data.
Extended geographic projections for d3-geo.
Natural Earth data in GeoJSON
Robust recipes to align language models with human and AI preferences
SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.
Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow
The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.
Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
Get up and running with Llama 3, Mistral, Gemma 2, and other large language models.
Helpers and such for working with Lambda Cloud
A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).
A collection of (mostly) technical things every software developer should know about
🤓 A curated awesome list of Machine Learning Engineering resources. Feel free to contribute!
🦜🔗 Build context-aware reasoning applications
A fast PostgreSQL Database Client Library for Python/asyncio.
Machine Learning Engineering Open Book
FlexFlow Serve: Low-Latency, High-Performance LLM Serving
A high-throughput and memory-efficient inference and serving engine for LLMs