Composable building blocks to build Llama Apps

TensorZero creates a feedback loop for optimizing LLM applications — turning production data into smarter, faster, and cheaper models.

Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.

LlamaIndex is a data framework for your LLM applications

Drag & drop UI to build your customized LLM flow

The official Python library for the OpenAI API

Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110). This framework is also used to evaluate text-to-image …

🐢 Open-Source Evaluation & Testing for ML & LLM systems

DSPy: The framework for programming—not prompting—language models

LLM training in simple, raw C/CUDA

Generative Models by Stability AI

The simplest, fastest repository for training/finetuning medium-sized GPTs.

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

Code for "WebVoyager: WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models"