A sample code sample to accompany the paper titled "Engineering flexible machine learning systems by traversing functionally-invariant paths"

AI-data warehouse to enrich, transform and analyze unstructured data

A library for mechanistic interpretability of GPT-style language models

Formatron empowers everyone to control the format of language models' output with minimal overhead.

SGLang is a fast serving framework for large language models and vision language models.

Another Python SQLite wrapper

Developer environments you can take with you

This monorepo stores all code and assets of all projects with which we develop regels.overheid.nl

A local-first personal finance app

AICI: Prompts as (Wasm) Programs

Cirron measures performance counters (instructions executed, etc.) and traces system calls a piece of Python or Ruby code executes.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Structured Text Generation

This repo provides the server side code for llmsherpa API to connect. It includes parsers for various file formats.

Actual's server

Test your prompts, agents, and RAGs. Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with comma…

Postgres for Search and Analytics

Scalable, Low-latency and Hybrid-enabled Vector Search in Postgres. Revolutionize Vector Search, not Database.

💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows

LlamaIndex is a data framework for your LLM applications

Large Language Model Text Generation Inference

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

⏩ Continue is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside VS Code and JetBrains

GEITje 7B: een groot open Nederlands taalmodel

AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data…

Supercharge Your LLM Application Evaluations 🚀