# Large Language Model Fine-Tuning Frameworks

> Search results for `fine-tune and train your own LLMs` on awesome-repositories.com. 114 total matches; showing the first 50.

Explore on the web: https://awesome-repositories.com/q/fine-tune-and-train-your-own-llms

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [this search on awesome-repositories.com](https://awesome-repositories.com/q/fine-tune-and-train-your-own-llms).**

## Results

- [hiyouga/llama-efficient-tuning](https://awesome-repositories.com/repository/hiyouga-llama-efficient-tuning.md) (72,239 ⭐) — This project is a fine-tuning framework and training pipeline designed to optimize and adapt large language and vision models. It provides a specialized toolkit for parameter-efficient tuning and supervised learning, serving as both a trainer for multimodal models and a deployment tool for serving fine-tuned models via high-performance inference engines.

The framework focuses on reducing memory and compute requirements by updating a small subset of model parameters. It supports a wide range of adaptation strategies, including vision-language model training to align text, image, video, and aud
- [lordog/dive-into-llms](https://awesome-repositories.com/repository/lordog-dive-into-llms.md) (40,974 ⭐) — Dive into LLMs is a framework designed for fine-tuning large language models and constructing modular machine learning pipelines. It provides a structured environment for adjusting pre-trained models on custom datasets while optimizing computational efficiency and training time.

The project distinguishes itself by offering an interactive web interface that allows for the deployment and publication of trained models directly to a browser. This enables users to test and interact with model results through a standardized web-based environment.

The platform supports the creation of flexible work
- [axolotl-ai-cloud/axolotl](https://awesome-repositories.com/repository/axolotl-ai-cloud-axolotl.md) (12,059 ⭐) — Axolotl is a configuration-driven framework designed for the fine-tuning, evaluation, and quantization of large language models. It functions as a comprehensive orchestrator for distributed training, enabling users to manage complex workflows across multi-node and multi-GPU environments. By utilizing structured configuration files, the platform streamlines the setup of training parameters, dataset paths, and hardware distribution strategies.

The project distinguishes itself through its support for diverse training methodologies, including full-parameter tuning, parameter-efficient adaptation,
- [meta-pytorch/torchtune](https://awesome-repositories.com/repository/meta-pytorch-torchtune.md) (5,774 ⭐) — 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
- [km1994/llms_interview_notes](https://awesome-repositories.com/repository/km1994-llms-interview-notes.md) (2,567 ⭐) — This repository is a collection of notes and resources focused on large language models (LLMs), specifically curated for interview preparation. It serves as a study guide covering the key concepts, architectures, and practical knowledge needed to discuss LLMs in a technical interview setting.

The material spans the fundamental topics relevant to understanding and working with LLMs, including their underlying mechanisms, training processes, and evaluation methods. The notes are organized to help readers build a structured understanding of the field, from foundational principles to more advance
- [mudler/localai](https://awesome-repositories.com/repository/mudler-localai.md) (46,889 ⭐) — LocalAI is a self-hosted inference server that enables the execution of machine learning models directly on local hardware. By providing a unified interface for text, image, and audio processing, it allows users to maintain full control over data privacy and infrastructure costs while eliminating dependencies on external network services.

The platform functions as an API gateway that mimics standard cloud-based artificial intelligence interfaces, allowing existing applications to integrate local models as drop-in replacements. It utilizes a container-based architecture to package runtimes and
- [holms-ur/fine-tuning](https://awesome-repositories.com/repository/holms-ur-fine-tuning.md) (72 ⭐) — Close-Domain fine-tuning for table detection
- [nndl/llm-beginner](https://awesome-repositories.com/repository/nndl-llm-beginner.md) (6,421 ⭐) — 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
- [tsinghuac3i/intuitive-fine-tuning](https://awesome-repositories.com/repository/tsinghuac3i-intuitive-fine-tuning.md) (30 ⭐) — This repository contains the code for the paper "Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process".
- [microsoft/generative-ai-for-beginners](https://awesome-repositories.com/repository/microsoft-generative-ai-for-beginners.md) (112,045 ⭐) — This project is a comprehensive, open-source educational curriculum designed to guide developers through the mastery of generative artificial intelligence. It provides a structured learning path that covers foundational concepts, prompt engineering, and the practical application of large language models. The repository serves as a central hub for skill acquisition, offering sequential modules that progress from basic model mechanics to advanced architectural patterns.

The curriculum distinguishes itself by focusing on the end-to-end lifecycle of intelligent software, including the implementat
- [datawhalechina/self-llm](https://awesome-repositories.com/repository/datawhalechina-self-llm.md) (30,941 ⭐) — This project is an open-source educational resource providing structured, step-by-step guides for fine-tuning large language models. It focuses on adapting pre-trained transformer-based causal models to custom datasets, enabling users to transfer specific writing styles or domain knowledge into generative AI models.

The repository distinguishes itself by emphasizing parameter-efficient training techniques, specifically low-rank adaptation. By providing practical implementations for updating only a small subset of model weights, it allows for the customization of massive neural networks on con
- [buildthingsuseful/build-your-own-kafka](https://awesome-repositories.com/repository/buildthingsuseful-build-your-own-kafka.md) (65 ⭐) — Build Your Own Kafka
- [openaccess-ai-collective/axolotl](https://awesome-repositories.com/repository/openaccess-ai-collective-axolotl.md) (12,062 ⭐) — 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
- [mlabonne/llm-course](https://awesome-repositories.com/repository/mlabonne-llm-course.md) (80,178 ⭐) — This project is a comprehensive educational curriculum and engineering handbook focused on the lifecycle of large language models. It serves as a structured knowledge base for machine learning practitioners, covering the fundamental mathematical and architectural principles of transformer-based sequence modeling, as well as the practical implementation of supervised instruction fine-tuning and preference-based model alignment.

The repository distinguishes itself by providing a deep dive into advanced model composition and optimization techniques. It details methodologies for weight-space mode
- [uber/ludwig](https://awesome-repositories.com/repository/uber-ludwig.md) (11,718 ⭐) — Ludwig is a declarative machine learning framework designed for training neural networks and large language models using configuration files instead of manual coding. It functions as a multimodal model builder and a low-code tool for supervised fine-tuning, allowing users to build models that process mixed inputs of text, images, audio, and tabular data.

The project distinguishes itself through an automated hyperparameter optimizer and a system for large language model fine-tuning using parameter-efficient adapters. It features a multimodal data pipeline and the ability to automatically gener
- [peiyuanix/build-your-own-zerotier](https://awesome-repositories.com/repository/peiyuanix-build-your-own-zerotier.md) (603 ⭐) — Build your own layer-2 virtual switch in less than 300 lines of code
- [helicone/helicone](https://awesome-repositories.com/repository/helicone-helicone.md) (5,830 ⭐) — Helicone is an AI gateway and observability platform designed to intercept, manage, and monitor interactions with large language models. By acting as a reverse-proxy, it provides a centralized layer for routing requests across multiple AI providers, allowing developers to maintain consistent application logic while gaining deep visibility into model performance, usage, and costs.

The platform distinguishes itself through a robust suite of traffic management and prompt engineering tools. It enables policy-driven control, including automatic failover between providers, rate limiting, and edge-b
- [aishwaryanr/awesome-generative-ai-guide](https://awesome-repositories.com/repository/aishwaryanr-awesome-generative-ai-guide.md) (24,755 ⭐) — This project is a community-driven knowledge repository and technical learning resource focused on the field of generative artificial intelligence. It serves as a centralized hub for developers and practitioners to access curated research, tutorials, and foundational concepts necessary for building and deploying modern artificial intelligence applications.

The platform distinguishes itself through a collaborative, distributed contribution model that aggregates diverse learning materials into a structured, searchable knowledge base. It covers a wide range of specialized topics, including retri
- [llm-tuning-safety/llms-finetuning-safety](https://awesome-repositories.com/repository/llm-tuning-safety-llms-finetuning-safety.md) (356 ⭐) — Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
- [modelscope/ms-swift](https://awesome-repositories.com/repository/modelscope-ms-swift.md) (14,597 ⭐) — This project is a comprehensive toolkit designed for the full lifecycle management of large language and multimodal models. It functions as a unified orchestrator that handles the entire development process, ranging from dataset preparation and supervised fine-tuning to advanced reinforcement learning alignment and production-ready inference deployment.

The platform distinguishes itself through a specialized reinforcement learning library that supports complex optimization algorithms, including group relative policy optimization and leave-one-out techniques, to improve model instruction-follo
- [kohya-ss/sd-scripts](https://awesome-repositories.com/repository/kohya-ss-sd-scripts.md) (7,133 ⭐) — sd-scripts is a suite of utilities designed for fine-tuning generative models, preprocessing datasets, and converting model weights. It provides a collection of scripts for executing Stable Diffusion training through methods such as DreamBooth, textual inversion, and full fine-tuning, alongside a framework for creating and managing Low-Rank Adaptation weights.

The project features specialized capabilities for model weight conversion between different architectures and precision formats. It includes tools for merging adaptation weights into base models, extracting weights from trained models,
- [danistefanovic/build-your-own-x](https://awesome-repositories.com/repository/danistefanovic-build-your-own-x.md) (516,495 ⭐) — Master programming by recreating your favorite technologies from scratch.
- [conardli/easy-dataset](https://awesome-repositories.com/repository/conardli-easy-dataset.md) (13,394 ⭐) — Easy-dataset is a comprehensive platform designed for the end-to-end management of machine learning datasets, specifically tailored for language and vision model fine-tuning. It functions as a centralized environment for the entire data lifecycle, encompassing the automated generation of synthetic training data, the structural organization of document collections, and the systematic annotation of individual data points.

The platform distinguishes itself through its integrated evaluation and orchestration capabilities. It provides a dedicated suite for benchmarking models, featuring blind side
- [thoughtworks/build-your-own-radar](https://awesome-repositories.com/repository/thoughtworks-build-your-own-radar.md) (2,549 ⭐) — This project is a technology radar visualization tool and dockerized static site generator. It transforms JSON or CSV datasets into an interactive technology map used to track the adoption status and maturity of tools and techniques across an organization.

The tool enables enterprise architecture mapping by organizing portfolios of technologies into categories and maturity levels. It supports custom technical taxonomies, allowing the definition of specialized rings and quadrants to match specific organizational evaluation criteria.

The system covers automated radar generation and technology
- [unslothai/unsloth](https://awesome-repositories.com/repository/unslothai-unsloth.md) (66,628 ⭐) — 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
- [zai-org/chatglm3](https://awesome-repositories.com/repository/zai-org-chatglm3.md) (13,764 ⭐) — ChatGLM3 is a comprehensive framework for deploying, fine-tuning, and serving large language models. It functions as a high-performance inference engine designed to support conversational AI, enabling developers to build interactive agents capable of multi-turn dialogue, autonomous code execution, and structured tool invocation.

The project distinguishes itself through its focus on hardware-agnostic deployment and resource optimization. It supports distributed model parallelism across multiple graphics cards, paged key-value caching for concurrent request processing, and weight quantization t
- [lukemathwalker/build-your-own-jira-with-rust](https://awesome-repositories.com/repository/lukemathwalker-build-your-own-jira-with-rust.md) (0 ⭐) — You will be working through a series of test-driven exercises, or koans, to learn Rust while building your own JIRA clone!
- [huggingface/transformers](https://awesome-repositories.com/repository/huggingface-transformers.md) (161,630 ⭐) — Transformers is a comprehensive library for machine learning that provides a unified interface for training, fine-tuning, and deploying transformer-based models. It supports a wide range of tasks, including text classification, language modeling, question answering, and sequence-to-sequence translation, while offering specialized architectures for both text and vision processing. The framework includes tools for managing the entire model lifecycle, from data preprocessing and tokenization to distributed training and inference.

The library features extensive support for model optimization and
- [qwenlm/qwen](https://awesome-repositories.com/repository/qwenlm-qwen.md) (21,294 ⭐) — Qwen is a comprehensive framework for large language model development, serving, and deployment. It provides a complete ecosystem for transformer-based sequence modeling, offering base models alongside specialized tools for instruction-tuned alignment, fine-tuning, and long-context inference. The project is designed to support both research and production environments, enabling users to train, optimize, and host generative models locally or across distributed hardware.

The framework distinguishes itself through its focus on high-performance serving and extensibility. It features a high-perfor
- [zasder3/train-clip](https://awesome-repositories.com/repository/zasder3-train-clip.md) (721 ⭐) — A PyTorch Lightning solution to training CLIP from both scratch and fine-tuning.
- [openai/openai-cookbook](https://awesome-repositories.com/repository/openai-openai-cookbook.md) (74,196 ⭐) — This project is a technical learning resource and developer knowledge base focused on the integration of large language models into software applications. It provides a structured collection of guides and code examples designed to teach developers how to implement intelligent features using proven patterns and best practices.

The repository distinguishes itself through a library of functional demonstrations that cover complex topics such as retrieval-augmented generation, function calling, and prompt engineering workflows. These materials are organized into a modular structure, allowing for t
- [openrlhf/openrlhf](https://awesome-repositories.com/repository/openrlhf-openrlhf.md) (9,675 ⭐) — OpenRLHF is a training framework and alignment library designed for reinforcement learning from human feedback across distributed GPU clusters. It provides tools for aligning large language models and multimodal vision-language models using algorithms such as PPO, GRPO, and DPO.

The framework distinguishes itself through a distributed inference engine that overlaps sample rollout with training to increase throughput. It supports scaling to models exceeding 70 billion parameters via parameter sharding and handles long-context sequences through ring-attention sequence parallelism.

The project
- [tokenrove/build-your-own-shell](https://awesome-repositories.com/repository/tokenrove-build-your-own-shell.md) (496 ⭐) — Guidance for mollusks (WIP)
- [mindee/doctr](https://awesome-repositories.com/repository/mindee-doctr.md) (6,149 ⭐) — DocTR is a deep learning OCR library built on PyTorch that detects and transcribes text in document images using a two-stage detection-recognition pipeline. It provides a complete framework for building and deploying OCR pipelines with pretrained models available through the Hugging Face Hub, and supports exporting trained models to ONNX format for cross-runtime deployment.

The library offers end-to-end OCR pipelines that combine text detection and recognition to extract all text from document images or PDFs, with support for rotated page handling and varied text orientations. It includes cap
- [codecrafters-io/build-your-own-x](https://awesome-repositories.com/repository/codecrafters-io-build-your-own-x.md) (516,240 ⭐) — This project provides a comprehensive framework for creating, managing, and executing educational programming challenges. It includes standardized systems for authoring instructional content, defining test cases, and structuring documentation to ensure consistent learning outcomes. The platform supports a wide range of programming languages through dedicated execution environments that handle compilation, dependency management, and automated testing.

The infrastructure facilitates both local and remote development workflows, offering command-line utilities for testing code without requiring v
- [d2l-ai/d2l-en](https://awesome-repositories.com/repository/d2l-ai-d2l-en.md) (29,001 ⭐) — This project is an educational platform and research toolkit designed to teach deep learning through a combination of mathematical theory, visual diagrams, and executable code. It provides a comprehensive environment for building, training, and evaluating neural networks, grounding complex concepts in interactive computational notebooks that allow for hands-on experimentation.

The framework distinguishes itself by interleaving theoretical foundations—including linear algebra, calculus, and probability—with practical implementations across multiple industry-standard libraries. It supports flex
- [thudm/p-tuning-v2](https://awesome-repositories.com/repository/thudm-p-tuning-v2.md) (2,078 ⭐) — An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks
- [clickhouse/clickhouse](https://awesome-repositories.com/repository/clickhouse-clickhouse.md) (48,229 ⭐) — ClickHouse is a high-performance, columnar analytical database designed for real-time query execution and large-scale data aggregation. It functions as a distributed data warehouse capable of processing petabytes of information, while also providing an embedded engine that integrates directly into applications for native query capabilities without external dependencies. The system is built to handle high-throughput ingestion and complex analytical workloads, delivering millisecond-level latency for interactive dashboards and operational monitoring.

The platform distinguishes itself through ad
- [internlm/xtuner](https://awesome-repositories.com/repository/internlm-xtuner.md) (5,150 ⭐) — xtuner is a comprehensive training engine for large language models, offering a toolkit for pre-training, supervised fine-tuning, and the optimization of vision-language multimodal models. It serves as a distributed training accelerator and a specialized framework for scaling Mixture-of-Experts models and aligning model behavior through reinforcement learning from human feedback.

The project distinguishes itself through advanced memory and compute optimizations, such as sequence parallelism for ultra-long context windows and interleaved pipeline parallelism to reduce GPU idle time. It provide
- [infaaa/build-your-own-x-vibe-coding](https://awesome-repositories.com/repository/infaaa-build-your-own-x-vibe-coding.md) (80 ⭐) — Master programming by recreating your favorite technologies from scratch with vibe coding.
- [netbirdio/netbird](https://awesome-repositories.com/repository/netbirdio-netbird.md) (26,188 ⭐) — NetBird is a zero-trust networking platform that builds secure, encrypted peer-to-peer overlay networks using the WireGuard protocol. It functions as a software-defined perimeter, connecting distributed infrastructure across cloud environments and physical locations while hiding network resources from the public internet. By integrating with external identity providers, the platform enforces granular access control and identity-based segmentation for every user and device.

The platform distinguishes itself through extensive automation and programmatic management capabilities. It provides a ce
- [mindverse/second-me](https://awesome-repositories.com/repository/mindverse-second-me.md) (15,123 ⭐) — Second-Me is a framework for orchestrating local agent tasks and fine-tuning personal language models. It provides a system for training specialized assistants on local datasets to support custom knowledge retrieval and task execution requirements.

The project distinguishes itself through a modular architecture that manages the lifecycle of machine learning tasks. It includes a state manager that persists intermediate training progress to local storage, allowing for the interruption and resumption of long-running configuration processes. Furthermore, the system utilizes standardized protocols
- [lightly-ai/lightly-train](https://awesome-repositories.com/repository/lightly-ai-lightly-train.md) (1,582 ⭐) — All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.
- [eleutherai/gpt-neo](https://awesome-repositories.com/repository/eleutherai-gpt-neo.md) (8,275 ⭐) — GPT-Neo is an open-source distributed training framework designed for scaling GPT-2 and GPT-3-style language models across multiple devices using mesh-tensorflow for model parallelism. It provides the infrastructure to train transformer-based language models with billions of parameters across distributed computing environments, making large-scale language model research accessible outside of proprietary systems.

The framework supports training both autoregressive GPT-style models and masked language models like BERT or RoBERTa, with configurable masking strategies and token handling. It inclu
- [morizeyao/gpt2-chinese](https://awesome-repositories.com/repository/morizeyao-gpt2-chinese.md) (7,596 ⭐) — GPT2-Chinese is a Chinese language model implementation based on the GPT-2 architecture. It provides a causal language model trainer and a natural language generation tool designed for training and generating human-like Chinese text sequences.

The system integrates a BERT tokenizer to process Chinese corpora into manageable units for machine learning. It enables the development of predictive text models that can generate specific patterns, such as news or poetry, through prompt-based text completion.

The project covers a full workflow including text tokenization, model training using a trans
- [facebookresearch/fairseq](https://awesome-repositories.com/repository/facebookresearch-fairseq.md) (32,228 ⭐) — Fairseq is a PyTorch toolkit for sequence-to-sequence modeling, specializing in neural machine translation, automatic speech recognition, and large-scale language model training. It provides a framework for processing and aligning diverse data sources, including text, audio, and video, to support tasks such as speech-to-text conversion and multimodal sequence learning.

The project is distinguished by its distributed training capabilities, which utilize parameter sharding, mixed-precision training, and CPU offloading to handle models that exceed single-device memory. It also includes specializ
- [hiyouga/chatglm-efficient-tuning](https://awesome-repositories.com/repository/hiyouga-chatglm-efficient-tuning.md) (3,720 ⭐) — Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调
- [cube-js/cube](https://awesome-repositories.com/repository/cube-js-cube.md) (20,251 ⭐) — Cube is a semantic data layer that provides a unified framework for defining business metrics, dimensions, and relationships across diverse data sources. By acting as a headless business intelligence engine, it transforms raw data into a governed model that can be queried via SQL, REST, and GraphQL interfaces. This architecture ensures consistent data definitions and logic across all downstream analytical applications and reporting tools.

The platform distinguishes itself through its integrated conversational AI capabilities, which allow users to explore data using natural language. It orches
- [answerdotai/llms-txt](https://awesome-repositories.com/repository/answerdotai-llms-txt.md) (2,442 ⭐) — The /llms.txt file, helping language models use your website
- [ai4finance-foundation/fingpt](https://awesome-repositories.com/repository/ai4finance-foundation-fingpt.md) (20,507 ⭐) — FinGPT is a suite of specialized financial tools and a framework for adapting large language models to the financial domain. It provides a set of pipelines for financial entity extraction, sentiment analysis, and retrieval-augmented generation to improve the accuracy of financial information systems.

The project distinguishes itself through efficient training workflows, utilizing low-rank adaptation and quantized low-rank adaptation to fine-tune models on consumer-grade hardware. It employs market-labeled datasets and reinforcement learning that uses actual stock price movements as reward sig