minimind
MiniMind is an open-source project for training a small language model from scratch and studying the LLM pipeline. It helps learners explore how models work through hands-on training and fine-tuning.
Pick a small issue you can reproduce, then fix it with your AI coding agent.
Share on XLicense: Apache-2.0
Overview
MiniMind is an open-source project for building and training small language models from scratch, intended to make LLM internals easier to study without relying on high-level training abstractions. It provides PyTorch implementations of model structures and a training path spanning pretraining, supervised fine-tuning, LoRA, preference optimization, tool use, and distillation. Users can follow the code, train on personal GPU hardware, evaluate models, and serve them through a lightweight API or chat interface. The repository also includes datasets and tokenizer training code.
Key features
- PyTorch model structure and tokenizer training code
- Training workflows for pretraining, fine-tuning, LoRA, preference optimization, tool use, and distillation
- Datasets and support for model evaluation
- Lightweight API server and Streamlit chat interface
Best for
Learners and developers who want to understand LLM internals by reproducing small-model training. It is suited to experiments on personal GPU hardware.
- Upstream
- jingyaogong/minimind
- Fork on GitHub
- Guo-astro/minimind
- Upstream stars
- 65k
- Category
- AI agents and LLM tools
- Language
- Python
- License
- Apache-2.0
- Forked
- 2026-10-14
- Sync status
- In syncLast synced 2026-11-08
More in AI agents and LLM tools
/last30days is an AI-agent skill for researching recent discussions across social platforms, video, news, markets, and the web. It brings scattered signals together in a synthesized brief for trend research and preparation.
Forked 2026-10-22Last synced 2026-11-08License: MITAI agents and LLM toolsGitHub
A portable C99 inference engine for running Kimi K3 on a CPU without a GPU or machine-learning framework. It streams the large checkpoint from disk to support inference with limited RAM, for batch text generation or text chat.
Forked 2026-10-21Last synced 2026-11-08License: Apache-2.0AI agents and LLM toolsGitHub
LayerFS gives AI agents writable workspaces over shared history, so they can work in parallel without copying the base. Use it to checkpoint, branch, rewind, and merge agent changes.
Forked 2026-10-21Last synced 2026-11-08License: MITAI agents and LLM toolsGitHub
Magnitude runs open models locally and tunes kernels for your hardware. Use it to connect local models to supported agents or an OpenAI-compatible client.
Forked 2026-10-19Last synced 2026-11-08License: Apache-2.0AI agents and LLM toolsGitHub