Large model fine-tuning

GraphGen is an open-source framework developed by OpenScienceLab, an AI lab in Shanghai, hosted on GitHub, focused on optimizing supervised fine-tuning of Large Language Models (LLMs) by guiding synthetic data generation through knowledge graphs. It constructs fine-grained knowledge graphs from source text, utilizing the expected calibration error...

MiniMind-V is an open source project, hosted on GitHub, designed to help users train a lightweight visual language model (VLM) with only 26 million parameters in less than an hour. It is based on the MiniMind language model , the new visual coder and feature projection module , support for image and text joint processing. .....

DeepCoder-14B-Preview is an open source code generation model developed by Agentica team and released on Hugging Face platform. It is based on DeepSeek-R1-Distilled-Qwen-14B, optimized by distributed reinforcement learning (RL) techniques...

WeClone is an open-source project that lets users create personalized digital doppelgängers by using WeChat chat logs and voice messages, combined with large language models and speech synthesis technology. The project can analyze a user's chatting habits to train the model, and can also generate realistic voice clones with a small number of voice samples. Ultimately, the digital ...

Search-R1 is an open source project developed by PeterGriffinJin on GitHub and built on the veRL framework. It uses reinforcement learning (RL) techniques to train a large language model (LLM), so that the model autonomously learns to reason and invoke the search engine to solve problems. Project Support Qwen2....

Optexity is an open source project on GitHub, developed by the Optexity team. Its core is to use human demonstration data to train AI to complete computer tasks, especially web page operations. The project consists of three code libraries : ComputerGYM, AgentAI and Playwright...

Bonsai is an open source language model developed by deepgrove-ai with a parameter size of 500 million, using ternary weights. It is based on the Llama architecture and the Mistral classifier design, with linear layers adapted to support ternary weights. The model mainly uses ...

Second Me is an open source project developed by the Mindverse team that lets you create an AI on your computer that acts like a "digital doppelganger", learning your speech and habits through your words and memories, and becoming an intelligent assistant that understands you. Its best feature is that all the data stays...

Easy Dataset is an open source tool designed specifically for fine-tuning large models (LLMs), hosted on GitHub. It provides an easy-to-use interface that allows users to upload files, automatically segment content, generate questions and answers, and ultimately output structured datasets suitable for fine-tuning. The developer, Cona...

MM-EUREKA is an open source project developed by Shanghai Artificial Intelligence Laboratory, Shanghai Jiao Tong University and other parties. It extends textual reasoning capabilities to multimodal scenarios through rule-based reinforcement learning techniques to help models process image and textual information. The core goal of this tool is to enhance the model in...

AI Toolkit by Ostris is an open source AI toolkit focused on supporting Stable Diffusion and FLUX.1 models for training and image generation tasks. Created and maintained by developer Ostris and hosted on GitHub, the toolkit aims to provide researchers and developers with flexible model...

X-R1 is a reinforcement learning framework open-sourced on GitHub by the dhcode-cpp team, aiming to provide developers with a low-cost, efficient tool for training models based on end-to-end reinforcement learning. Inspired by DeepSeek-R1 and open-r1, the project focuses on building an easy...

OpenManus-RL is an open source project jointly developed by UIUC-Ulab and the OpenManus team of the MetaGPT community, hosted on GitHub.The project enhances the reasoning and decision-making capabilities of large language model (LLM) intelligences through reinforcement learning (RL) techniques, based on Deepseek-R1...

TPO-LLM-WebUI is an innovative project open-sourced by Airmomo on GitHub that enables real-time optimization of Large Language Models (LLMs) through an intuitive web interface. It uses the TPO (Test-Time Prompt Optimization) framework, and says goodbye to ...

Open-Reasoner-Zero is an open source project focused on reinforcement learning (RL) research, developed by the Open-Reasoner-Zero team on GitHub. It aims to accelerate the research process in the field of Artificial Intelligence by providing an efficient, scalable and easy-to-use training framework, especially towards general-purpose human...

The Chinese DeepSeek-R1 distillation dataset is an open source Chinese dataset containing 110K pieces of data designed to support machine learning and natural language processing research. The dataset is released by Liu Cong NLP team, the dataset contains not only math data, but also a large number of general types of data, such as logical reasoning, Xiaohongshu...

ColossalAI is an open source platform developed by HPC-AI Technologies to provide an efficient and cost-effective solution for large-scale AI model training and inference. By supporting multiple parallel strategies, heterogeneous memory management, and mixed-precision training, ColossalAI is able to significantly reduce model training and inference time and...

One Shot LoRA is a platform focused on generating high quality video LoRA models from videos. Users can quickly and easily train high-quality LoRA models from videos without logging in or storing private data. The platform supports Hunyuan Video, FLUX and SDXL...

Kiln is an open source tool focused on fine-tuning of Large Language Models (LLMs), synthetic data generation and dataset collaboration. It provides an intuitive desktop application with support for Windows, MacOS and Linux systems that allows users to achieve fine-tuning of models such as Llama, GPT4o and Mixtral with zero code. ....