Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

A course on aligning smol models.

Democratizing Reinforcement Learning for LLMs

This repository contains various advanced techniques for Retrieval-Augmented Generation (RAG) systems.

A suite of image and video neural tokenizers

Biological foundation modeling from molecular to genome scale

Autonomously train research-agent LLMs on custom data using reinforcement learning and self-verification.

A library for making RepE control vectors

A framework for creating grounded instruction based datasets and training conversational domain expert Large Language Models (LLMs).

Medical image captioning using OpenAI's CLIP

Ichigo Whisper is a compact (22M parameters), open-source speech tokenizer for the Whisper-medium, designed to enhance performance on multilingual with minimal impact on its original English capabi…