Unify Efficient Fine-tuning of 100+ LLMs

A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI

The TypeScript library for building AI applications.

5X faster 60% less memory QLoRA finetuning

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Running local Language Learning Models to perform Retrieval-Augmented Generation

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

Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Operating LLMs in production