# dandelionsllm/pandallm

Panda项目是于2023年5月启动的开源海外中文大语言模型项目，致力于大模型时代探索整个技术栈，旨在推动中文自然语言处理领域的创新和合作。

Repository: https://github.com/dandelionsllm/pandallm
Canonical: https://ross.abutalabs.com/products/pandallm
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2023-10-19T16:05:28+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 87
- inputs: {"age_days": 1223, "days_push": 1049, "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 1031, forks 76 (observed 2026-08-28T04:03:18.002635+00:00)

## What it is
Panda is an open-source project for overseas Chinese large language models, providing PandaLLM model weights (continued pretraining of LLaMA1/LLaMA2 on Chinese data), PandaLLMOps training/inference/deployment tooling, and a developer community. It supports pretraining, full fine-tuning, LoRA/QLoRA, and fast deployment with vLLM and LightLLM.

## Use cases
- continue pretraining llama on chinese text
- fine-tune a chinese large language model with lora
- deploy a chinese llm with vllm for fast inference
- download open-source chinese llama model weights
- train an llm from scratch on chinese data
- learn the full llm tech stack with tutorials
- adapt llama2 for python code generation

## When to choose
- you need open Chinese-adapted LLaMA weights or want to continue-pretrain/fine-tune LLaMA for Chinese
- you want an integrated pipeline covering training, LoRA fine-tuning, and vLLM/LightLLM deployment
- you are learning the LLM stack through Chinese-language tutorials and community resources

## When to avoid
- you need a production-grade, actively maintained framework - releases stopped in late 2023
- you need non-Chinese or multilingual focus with strong community support
- you require commercial use of training data, which is CC BY-NC licensed

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-training, llm-inference, nlp, machine-learning
- domain: large-language-models, machine-learning, developer-tools
- platform: python
- tags: chinese-llm, llama, continued-pretraining, fine-tuning, lora, qlora, vllm, model-deployment, open-source-model-weights, natural-language-processing, gpu, linux, docker

## Member repositories
- dandelionsllm/pandallm (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:18.002635+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 2026-08-30T07:07:26.223777+00:00, confidence not recorded.
  - readme: https://github.com/dandelionsllm/pandallm (fetched 2026-08-28T04:03:18.002635+00:00, sha b0addab16dd0)
- Data as of 2026-08-30T08:39:29.467469+00:00.