jingyaogong/minimind

This page introduces an external open-source repository. It is not an HDATF product.

What it does

An educational project that implements a small language model of about 64M parameters from scratch in native PyTorch. Its code covers the full training chain, such as pretraining, SFT, LoRA, RLHF, tool use and distillation.

How it helps ATF

Only loosely related. It could be study material for understanding how the language models that Harness relies on are trained and tuned, not a component to reuse.

License

Apache-2.0 Permissive, with a patent grant. Commercial use is allowed; keep the notices and state your changes.

More in this category

• experientiallabs/experiential
  An open source gateway that puts hosted, BYOK and local models behind one OpenAI-compatible API. It sets per-user and per-agent model access and spending limits, and can turn production traffic into a custom router or model.
• sgl-project/sglang
  A serving framework for large language models and multimodal models. It serves open models such as DeepSeek, Qwen, Llama and GLM, and also covers diffusion models for image and video generation.
• bojieli/ai-infra-book
  An open-source book, written in Chinese, that derives LLM inference and training system design from hardware constraints and model architecture using quantitative estimates. The repository includes the full text, a PDF and companion calculation tools and experiments.
• FlashML-org/FreeToken
  A serving engine for running large open-weight Mixture-of-Experts models on personal hardware by splitting work across GPUs, CPUs and memory. It exposes Anthropic- and OpenAI-compatible APIs so coding agents can connect.
• modelscope/ms-cookbook
  ModelScope Cookbook is an open-source guide to building applications with open-source models, covering model selection, inference, fine-tuning, evaluation, RAG and agents. Its runnable examples include enterprise knowledge Q&A and customer-service quality analysis.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.