Tags: big model fine-tuning

Comprehensive Introduction 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 1 hour. It is based on the MiniMind language model , the new visual coder and feature projection module , support for image and text association ...

General Introduction 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, and is capable of handling up to 64K tokens of super...

Comprehensive introduction WeClone is an open source project that uses WeChat chat logs and voice messages, combined with large language models and speech synthesis technology, to allow users to create personalized digital doppelgangers. The project can analyze the user's chat habits to train the model , but also with a small number of voice samples to generate realistic voice clones ...

General Introduction Search-R1 is an open source project, developed by PeterGriffinJin on GitHub, built on the veRL framework. It uses reinforcement learning (RL) techniques to train large language models (LLMs), allowing the models to autonomously learn to reason and invoke search engines to solve problems. The project supports Qwen2.5...

General Introduction 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 contains three code libraries : ComputerGYM, AgentAI and Playwright, users can ...

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

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 turning it into a smart assistant that understands you. Its best feature is that all the numbers...

Comprehensive Introduction 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. Open ...

Comprehensive Introduction 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 improve...

General Introduction AI Toolkit by Ostris is an open source AI toolset 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 micro...

General Introduction 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. The project is inspired by DeepSeek-R1 and open-r1 and focuses on building...

General Introduction 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, QwQ-32B ...

Comprehensive Introduction 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 to completely say goodbye to the traditional fine-tuning of the tedious process of ...

General Introduction 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 to the pass...

Comprehensive Introduction 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 Cong Liu's NLP team. The dataset contains not only mathematical data, but also a large amount of general types of data, such as logical reasoning...

Comprehensive Introduction 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 parallelization strategies, heterogeneous memory management, and mixed-precision training, ColossalAI is able to significantly reduce model training and inference...

General Introduction 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 models...

Comprehensive Introduction Kiln is an open source tool focused on fine-tuning large language models (LLMs), synthetic data generation and dataset collaboration. It provides an intuitive desktop application with support for Windows, MacOS and Linux, allowing users to implement models such as Llama, GPT4o and Mixtral with zero code...

Comprehensive Introduction Maestro is a tool developed by Roboflow to simplify and accelerate the process of fine-tuning multimodal models, so that everyone can train their own visual macromodels. It provides ready-made recipes for fine-tuning popular visual language models (VLMs) such as Florence-2, PaliGemma ...