QLoRA: Efficient Finetuning of Quantized LLMs

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

Ergonomic machine learning for everyone.

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

OpenAPI specification for the OpenAI API

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

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

LLM inference in C/C++

Ollama Cloud is a Highly Scalable Cloud-native Stack for Ollama

Ollama Python library