# PhoebusSi/Alpaca-CoT

We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts to initiate any meaningful PR on this repo and integrate as many LLM related technologies as possible. 我们打造了方便研究人员上手和使用大模型等微调平台，我们欢迎开源爱好者发起任何有意义的pr！

Repository: https://github.com/PhoebusSi/Alpaca-CoT
Canonical: https://ross.abutalabs.com/products/alpaca-cot
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: chatglm, llama, llm, lora, chatgpt, cot, instruction-tuning, alpaca, moss, p-tuning, parameter-efficient, pytorch, tabul, tabular-data, tabular-model
Last push: 2023-12-12T08:16:56+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 89
- inputs: {"age_days": 1258, "days_push": 995, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2791, forks 247 (observed 2026-08-28T04:07:22.073422+00:00)

## What it is
Alpaca-CoT is an instruction-tuning platform that unifies interfaces for instruction data collection, parameter-efficient fine-tuning methods (LoRA, p-tuning), and multiple large language models like LLaMA and ChatGLM. It provides an easy-to-use framework for researchers to fine-tune LLMs with chain-of-thought and other instruction datasets.

## Use cases
- fine-tune llama with lora on instruction data
- instruction-tune chatglm with chain-of-thought datasets
- compare parameter-efficient tuning methods on llms
- train an alpaca-style chat model on a single gpu
- unified platform for llm fine-tuning experiments

## When to choose
- you want to fine-tune open LLMs like LLaMA or ChatGLM with LoRA or p-tuning
- you need a unified interface for multiple instruction-tuning datasets and models
- you are a researcher experimenting with parameter-efficient methods

## When to avoid
- you need the latest fine-tuning stack with active development
- you want full-parameter fine-tuning at scale on multi-node clusters
- you need production inference serving rather than fine-tuning

## Facets
- artifact type: framework
- maturity: maintenance
- function: llm-training, machine-learning, agent-framework
- domain: large-language-models, machine-learning, deep-learning
- platform: python
- tags: instruction-tuning, lora, p-tuning, parameter-efficient-fine-tuning, chatglm, llama, chain-of-thought, pytorch, fine-tuning, gpu, linux

## Member repositories
- PhoebusSi/Alpaca-CoT (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:22.073422+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 2026-08-30T08:15:15.776487+00:00, confidence not recorded.
  - readme: https://github.com/PhoebusSi/Alpaca-CoT (fetched 2026-08-28T04:07:22.073422+00:00, sha a24d1ac4c93b)
- Data as of 2026-08-30T08:39:29.467469+00:00.