# Duxiaoman-DI/XuanYuan

轩辕：度小满中文金融对话大模型

Repository: https://github.com/Duxiaoman-DI/XuanYuan
Canonical: https://ross.abutalabs.com/products/xuanyuan
Language: Python
License Family: other
Last push: 2025-01-07T06:27:26+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 85
- inputs: {"age_days": 1200, "days_push": 603, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1326, forks 121 (observed 2026-08-28T04:04:22.825073+00:00)

## What it is
XuanYuan is a family of open-source Chinese financial-domain large language models from Duxiaoman, including base, chat, and quantized variants up to 176B, plus the FinanceIQ evaluation dataset and a 60GB Chinese financial corpus. The repository provides model releases, training/fine-tuning resources, and evaluation benchmarks.

## Use cases
- build a chinese financial chatbot
- fine-tune an llm on finance data
- evaluate llms on chinese finance knowledge
- run a quantized 70b chat model locally
- get a large chinese financial training corpus
- deploy a domain-specific llm for banking

## When to choose
- you need a chinese-language llm specialized in finance
- you want open weights with quantized variants for cheaper inference
- you need a benchmark for chinese financial knowledge

## When to avoid
- you need an english-only general-purpose assistant
- you need a hosted api rather than self-hosted weights
- you require a permissive license - the repo has no license file

## Facets
- artifact type: library
- maturity: active
- function: llm-training, llm-inference, machine-learning, chatbot
- domain: large-language-models, fintech, artificial-intelligence
- platform: python
- tags: chinese-language, finance, quantization, open-weights, benchmark-dataset, natural-language-processing, gpu

## Member repositories
- Duxiaoman-DI/XuanYuan (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:22.825073+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 2026-08-30T04:46:20.213461+00:00, confidence not recorded.
  - readme: https://github.com/Duxiaoman-DI/XuanYuan (fetched 2026-08-28T04:04:22.825073+00:00, sha 14f255785325)
- Data as of 2026-08-30T08:39:29.467469+00:00.