Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

A Blazing Fast AI Gateway with integrated Guardrails. Route to 200+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.

A user interface for DSPy

Entropy Based Sampling and Parallel CoT Decoding

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

Draw more samples

Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

SWE-agent: Agent Computer Interfaces Enable Software Engineering Language Models

🐚 OpenDevin: Code Less, Make More

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

All things prompt engineering

Training Models Daily

Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-l…

a very good whiteboard

A framework for few-shot evaluation of autoregressive language models.

Robust recipes for to align language models with human and AI preferences

LLaVA-Plus: Large Language and Vision Assistants that Plug and Learn to Use Skills

ASR with reliable word-level timestamps using OpenAI's Whisper

🐢 The testing framework for ML models, from tabular to LLMs

LlamaIndex (formerly GPT Index) is a data framework for your LLM applications

Inference Llama 2 in one file of pure C

An editor made for programming with AI 🤖

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

Tensor library for machine learning

Port of OpenAI's Whisper model in C/C++