# unit-mesh/unit-minions

《AI 研发提效：自己动手训练 LoRA》，包含 Llama  （Alpaca LoRA）模型、ChatGLM （ChatGLM Tuning）相关 Lora 的训练。训练内容：用户故事生成、测试代码生成、代码辅助生成、文本转 SQL、文本生成代码……

Repository: https://github.com/unit-mesh/unit-minions
Canonical: https://ross.abutalabs.com/products/unit-minions
Homepage: https://train.unitmesh.cc/
Language: Jupyter Notebook
License Family: other
Topics: llm, lora
Last push: 2024-01-03T02:42:50+00:00

## Health v2 (maintenance only)
Score: 21/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 89
- inputs: {"age_days": 1250, "days_push": 973, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1101, forks 124 (observed 2026-08-28T04:03:35.568345+00:00)

## What it is
A Chinese-language tutorial project and research collection for training LoRA adapters on LLaMA (Alpaca LoRA) and ChatGLM models to boost software development productivity. It includes Jupyter training notebooks, datasets, trained LoRA binaries, and videos covering tasks like user story generation, test code generation, code assistance, and text-to-SQL.

## Use cases
- learn how to fine-tune LLaMA with LoRA
- train a ChatGLM model with LoRA tuning
- generate user stories from requirements with a local LLM
- fine-tune a model to generate test code
- build a text-to-SQL model
- train a model for code assistance generation
- study AI-driven developer productivity techniques

## When to choose
- you want a hands-on tutorial for LoRA fine-tuning on LLaMA or ChatGLM
- you need example datasets and notebooks for code-generation or test-generation fine-tuning
- you are researching LLM applications for software engineering productivity

## When to avoid
- you need a production-ready code generation model (use CodeGen or a commercial LLM instead)
- you need a maintained library or tool rather than educational notebooks
- you require a licensed, supported project (it has no license)

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: llm-training, machine-learning, nlp
- domain: large-language-models, machine-learning, developer-tools, tutorials
- platform: python, cross-platform
- tags: lora, fine-tuning, llama, chatglm, alpaca-lora, jupyter-notebook, code-generation, developer-productivity, text-to-sql, chinese, gpu

## Member repositories
- unit-mesh/unit-minions (main) score 21

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:35.568345+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:45:44.708337+00:00, confidence not recorded.
  - readme: https://github.com/unit-mesh/unit-minions (fetched 2026-08-28T04:03:35.568345+00:00, sha fff47a7f501a)
  - homepage: https://train.unitmesh.cc/ (fetched 2026-08-29T12:49:07.793121+00:00, sha d59104762991)
- Data as of 2026-08-30T08:39:29.467469+00:00.