Search results

KubeStellar Console supports deploying, serving, monitoring, or operating AI and machine-learning systems.

Discover the large language models examples with insights on business adoption, language model training, and influential models.

LiteLLM provides machine-learning models, research, training resources, or evaluation tools.

A hub of integrations for LlamaIndex including data loaders, tools, vector databases, LLMs and more.

Psst, kid, want some cheap and small LLMs?

A data framework for building LLM applications over external data.

Research on evaluation of LLMs conducted by Microsoft Research and other collaborated institutes. (Updated at: 2023/10).

Creates or edits images with generative models and visual controls.

LMQL provides machine-learning models, research, training resources, or evaluation tools.

Combine LLMs and code to create simple automations.

manifest.build supports AI agents, automated workflows, orchestration, or delegated tasks.

NuMind builds state-of-the-art multimodal LLMs for document extraction, available via SaaS or enterprise deployment for control and privacy.

MLOps and LLMOps, from the trenches.

"An Open Source Language Model Specialized in Evaluating Other Language Models.".

Prompt Engineering platform. Collaborate, test, evaluate, and monitor your LLM applications.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

sim supports AI agents, automated workflows, orchestration, or delegated tasks.

Creates, rewrites or summarizes written content with language models.

StreamingLLM is a technique that can enable language models like Llama-2 to have conversations that span across millions of tokens.

A concise, technical introduction by Andriy Burkov.

Just like the IKEA Effect, but for the AI products. Try not to overenginner when working with LLMs.

Creates, rewrites or summarizes written content with language models.

The Dark Risk of Large Language Models WIRED UK provides machine-learning models, research, training resources, or evaluation tools.

The Pile is a 825 GiB diverse, open source language modelling data set that consists of 22 smaller, high-quality datasets combined together.