Open-source alternatives to Mistral Finetune

ART is a platform for agentic training, providing a reinforcement learning framework, training environment, and compute orchestrator. It enables the improvement of multi-step agent reasoning and tool usage through group relative policy optimization and a judge-based reward modeling system. The project features tools for model distillation to transfer capabilities from large teacher models to smaller architectures, as well as a system for capturing execution trajectories to generate synthetic training data. It supports specialized training workflows including supervised fine-tuning for baselin

LLaMA-Factory is a comprehensive suite for dataset preparation, model fine-tuning, memory optimization, and standardized API deployment. It provides a unified platform for the supervised and reward-based fine-tuning of large language models and vision-language models. The framework includes a specialized toolkit for training vision-language models and a model serving interface that deploys trained models through high-performance APIs. It utilizes precision tuning and quantization techniques to reduce the hardware requirements and memory footprint of large models. The system covers data pipel

This project is a training pipeline and framework for developing Chinese language models based on the Llama 2 architecture. It functions as a distributed GPU trainer and dataset preprocessing toolkit designed for both the initial pre-training of baseline models and subsequent supervised fine-tuning. The system distinguishes itself through a specialized workflow for Chinese text, incorporating a data curation pipeline that uses similarity hashing for deduplication and a tokenization process that converts raw text into memory-mapped binary files for efficient disk access. It implements a superv

This project is a comprehensive toolkit for adapting large language models to the Chinese language, providing a specialized framework for fine-tuning, inference, and local deployment. It serves as a coordinated suite for language-specific adaptation, including tools for expanding tokenizers and implementing retrieval-augmented generation. The project distinguishes itself through a complete pipeline for model adaptation, featuring multilingual tokenizer expansion and a fine-tuning framework that supports instruction-based supervised training and adapter merging. It also includes a dedicated de

Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a config-driven system for instantiating components, orchestrating distributed training, and managing parameter-efficient fine-tuning with quantization support, all through YAML-based configurations and command-line overrides. The library distinguishes itself through its comprehensive post-training workflow orchestration, combining supervised fine-tuning, preference optimization (DPO, PPO, GRPO), knowledge distillation, and quantization-aware training in a single configurable pip

zero_nlp is a distributed framework for training and fine-tuning large language models and multimodal architectures. It provides a specialized toolkit for distributed model parallelism, allowing neural network layers and weights to be partitioned across multiple GPU devices to train models that exceed the memory capacity of a single processor. The project distinguishes itself through a combination of high-throughput data pipelines and parameter-efficient tuning. It utilizes multi-threading and memory mapping to preprocess and stream datasets exceeding 100GB and implements memory-saving adapta

Flashlight is a C++ machine learning library and deep learning framework designed for building and training neural networks. It functions as a tensor manipulation library and an automatic differentiation engine that tracks operations to calculate gradients via backpropagation for model optimization. The project is distinguished by its role as a distributed training framework, utilizing all-reduce gradient synchronization and distributed environments to scale machine learning workloads across multiple nodes and devices. It features a backend-agnostic memory interface and RAII-based management

RLinf is a distributed reinforcement learning orchestrator and embodied AI training framework. It provides the infrastructure to train vision-language-action models and robotic policies using a combination of reinforcement learning and supervised fine-tuning. The system is designed for scaling workloads across GPU clusters, managing the placement of actors, rollout workers, and environment components. It features a specialized robotics data collection pipeline for gathering teleoperated demonstrations and simulation trajectories into standardized replay buffers, alongside a hardware interface

This project is an alignment framework and suite of pipelines for training language models using supervised fine-tuning and preference optimization. It provides tools for executing large-scale distributed training across multiple GPUs and compute nodes, alongside a system for measuring model helpfulness and dialogue quality through single-turn and multi-turn benchmarks. The framework includes specialized tools for direct preference optimization to refine model behavior using paired data without a separate reward model. It also supports constitutional AI alignment and the training of reward mo

ai-toolkit is a diffusion model training toolkit designed for fine-tuning image and video generation models. It functions as a containerized model trainer and GPU training job manager, providing the infrastructure to orchestrate dependencies and manage training processes on remote GPU hardware. The system utilizes low-rank adaptation techniques, including LoRA and LoKr weight optimization, to reduce the hardware requirements for model training. It distinguishes itself through a web-based training controller that allows for the monitoring and modification of hyperparameters, secured by token-b

kohya_ss is a graphical user interface and workbench for fine-tuning diffusion models, specifically designed for Stable Diffusion. It provides a suite of tools for training generative AI models, including specialized interfaces for creating Low-Rank Adaptation weights and training ControlNet spatial control networks. The project distinguishes itself through integrated VRAM usage optimization and hardware acceleration, featuring specific support for Intel GPUs via XPU-accelerated libraries. It implements parameter-efficient training methods and memory-saving techniques like gradient checkpoint

llm-foundry is a training framework for large language models, providing a system for foundation model pre-training and supervised fine-tuning. It includes a distributed trainer for scaling workloads across multiple nodes and GPUs, a dataset streaming pipeline for loading data from cloud storage, and a parameter-efficient fine-tuning implementation. The framework distinguishes itself through its use of parameter sharding and high-throughput data streaming to maintain stability during large-scale training. It incorporates low-rank adaptation to reduce computational costs and uses eight-bit flo

TransformerLab is an MLOps orchestration platform and research environment designed for the training, fine-tuning, and evaluation of large language models. It serves as a centralized control plane for managing machine learning jobs and coordinating distributed GPU compute across hybrid cloud and on-premise providers. The platform distinguishes itself through agent-driven model optimization, using AI assistants to analyze metrics and automatically propose and queue hyperparameter experiments. It provides a remote development environment that allows users to launch interactive notebooks, code e

Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a configurable training pipeline orchestrated through YAML recipes, with CLI overrides and component swapping, distributed training via FSDP2, memory optimizations, and parameter-efficient fine-tuning methods like LoRA, DoRA, and QLoRA. The library distinguishes itself through its YAML-driven configuration system that defines all training parameters and instantiates components from config files, with full CLI override capability for any field or component at launch time. It suppo

Oumi is a comprehensive large language model development platform designed for synthesizing data, fine-tuning models, and running performance evaluations. It serves as a unified environment for the entire model lifecycle, encompassing a training and fine-tuning suite, an evaluation framework, and tools for synthetic data generation and model distillation. The platform is distinguished by its iterative, failure-driven synthesis approach, which analyzes model weaknesses during evaluation to generate targeted training data. It utilizes an LLM-based judge framework to programmatically score respo

Kiln is an LLM development workbench and evaluation framework designed for designing, testing, and optimizing prompts and AI agents. It functions as a multi-agent orchestrator and a RAG optimization tool, providing a visual interface for the iterative development of AI systems. The project distinguishes itself through a comprehensive fine-tuning pipeline that supports zero-code model training and reasoning distillation. It enables the creation of hierarchical multi-agent systems where specialized actors coordinate via tool calling, and it implements a Model Context Protocol server to expose t

Firefly is a training framework and inference engine for large language models. It functions as a toolkit for pre-training and fine-tuning various open-weight architectures, providing a system for model alignment and parameter-efficient fine-tuning. The project includes utilities for merging adapter weights back into base models to create standalone files. It also provides a model alignment toolkit to format training data according to specific prompt templates, ensuring conversational consistency across different models. The framework supports distributed model training and preference-based

Unsloth is a high-performance training and inference platform designed to optimize the lifecycle of large language and multimodal models. It provides a comprehensive engine for fine-tuning, executing, and managing models locally, with a focus on reducing memory consumption and increasing compute speed on consumer-grade hardware. The platform distinguishes itself through hand-optimized kernels and automated computational graph techniques that maximize hardware throughput. It supports advanced training methodologies, including reinforcement learning for reasoning and efficient adapter-based fin

Tinker Cookbook is an open-source framework for fine-tuning large language models, supporting supervised learning, reinforcement learning, and parameter-efficient techniques like LoRA adapters. It provides a complete pipeline for aligning models with human preferences through multi-stage RLHF workflows, from supervised fine-tuning through preference optimization to reinforcement learning. The framework distinguishes itself through recipe-based training orchestration, where fine-tuning workflows are defined as composable recipe files that chain data loading, model configuration, and training l

This project is a framework for fine-tuning large language models using parameter-efficient training techniques. It provides a structured pipeline for adapting pre-trained transformer models to specific tasks while minimizing the computational resources and memory required during the training process. The system distinguishes itself by utilizing low-rank adaptation, which injects trainable rank-decomposition matrices into frozen transformer layers. By updating only this small subset of injected parameters rather than the entire model, the framework reduces the overhead associated with gradien

OpenClaw-RL is a reinforcement learning framework for training large language model agents. It provides a system for optimizing agent policies using natural language instructions, reward-based optimization, and a pipeline for refining model behavior through human or judge feedback. The framework utilizes low-rank adaptation to update model weights efficiently without full parameter tuning. It features a local-first infrastructure that allows the policy model, judge, and trainer to run on private hardware to maintain data locality. The system covers a range of optimization capabilities, inclu

Flashlight is a standalone C++ machine learning library and tensor library used for building and training neural networks. It functions as a comprehensive neural network framework and automatic differentiation engine, providing the tools to construct computation graphs and calculate gradients via backpropagation. The project serves as a distributed training framework, utilizing all-reduce operations to synchronize gradients and parameters across multiple compute nodes and devices. It distinguishes itself through deep integration of high-performance tensor manipulation, native device memory in

AReaL is a system for agent orchestration, distributed model training, and parameter-efficient tuning. It provides a framework for developing multi-turn reasoning agents and training large models using reinforcement learning from human feedback. The project implements a toolkit for improving the visual reasoning and geometry problem solving capabilities of vision-language models. It utilizes a memory-efficient tuning system to optimize mathematical and reasoning models across different inference backends. The infrastructure supports large-scale training through tensor, pipeline, and expert p

Pythia is a multimodal research framework and distributed training system designed for building, training, and evaluating large models that combine visual and linguistic data. It provides a modular environment for developing vision-language models, focusing on the integration of image and text inputs into shared feature representations. The framework utilizes a modular architecture that decouples model building blocks into interchangeable components, allowing for flexible configuration of vision and language modules. It includes a benchmark suite for executing reference models against standar

This project is a collection of educational resources and technical guides focused on the development and implementation of large language models. It provides a comprehensive curriculum covering transformer architectures, training methods, and deployment strategies. The materials provide detailed instructions for building autonomous agents using reasoning loops and tool integration, as well as guides for fine-tuning models through supervised learning and preference optimization. It also includes tutorials for constructing retrieval augmented generation pipelines and implementing transformer m

Axolotl is a distributed training orchestrator and fine-tuning framework for large language models, multimodal systems, and quantized models. It provides a structured environment for specializing pre-trained models through full parameter updates or low-rank adaptation, as well as aligning model outputs with human expectations via preference tuning pipelines and reward modeling. The system distinguishes itself through a configuration-driven pipeline that manages preprocessing and training workflows via a single file for reproducibility. It implements high-throughput optimizations such as multi