Text Generation
Transformers
PyTorch
Chinese
bloom
text-generation-inference
Inference Endpoints
XuanYuan2.0 / README.md
xyz-nlp's picture
Update README.md
8511137
|
raw
history blame
5.72 kB
metadata
license: bigscience-bloom-rail-1.0
language:
  - zh
extra_gated_heading: XuanYuan Download Application
extra_gated_prompt: >
  XuanYuan LICENSE

  1.Definitions

  "Licensor" refers to the XuanYuan Model Team, the entity responsible for
  distributing its Software.

  "Software" pertains to the XuanYuan model parameters made accessible under
  this license.

  2.License Grant

  Subject to the conditions outlined in this License, the Licensor hereby grants
  you a non-exclusive, worldwide, non-transferable, non-sublicensable,
  revocable, royalty-free copyright license to utilize the Software exclusively
  for non-commercial research purposes.

  You must include the above copyright notice and this permission notice in all
  copies or significant portions of the Software.

  3.Restrictions

  You are prohibited from engaging in the following actions with the Software,
  either in whole or in part: using, copying, modifying, merging, publishing,
  distributing, reproducing, or creating derivative works of the Software, for
  commercial, military, or illegal purposes.

  You must refrain from using the Software for any activities that could
  undermine China's national security and national unity, jeopardize public
  interest, or infringe upon the rights and interests of individuals.

  4.Disclaimer

  The Software is provided "as is" without any kind of warranty, either express
  or implied, including but not limited to the warranties of merchantability,
  fitness for a particular purpose, and non-infringement. The authors or
  copyright holders shall not be held liable for any claims, damages, or other
  liabilities arising from the use or performance of the Software, whether in an
  action of contract, tort, or otherwise, even if they have been advised of the
  possibility of such damages.

  5.Limitation of Liability

  To the extent permitted by applicable law, under no legal theory, including
  tort, negligence, contract, or otherwise, shall the Licensor be liable to you
  for any direct, indirect, special, incidental, exemplary, or consequential
  damages, or any other commercial losses, arising from the use or inability to
  use the Software. This limitation applies even if the Licensor has been
  advised of the possibility of such damages.

  6.Dispute Resolution

  This license shall be governed and construed in accordance with the laws of
  the People's Republic of China. Any dispute arising from or in connection with
  this License shall be submitted to the Haidian District People's Court in
  Beijing.
extra_gated_fields:
  Name: text
  Organization/Affiliation: text
  Position Title: text
  Country: text
  City: text
  Mobile Phone: text
  Purpose and Usage Scenarios: text
  I agree to use this model for non-commercial use ONLY: checkbox

轩辕:首个千亿级中文金融对话模型

XuanYuan: A Large Chinese Financial Chat Model with Hundreds of Billions Parameters

轩辕是国内首个开源的千亿级中文对话大模型,同时也是首个针对中文金融领域优化的千亿级开源对话大模型。轩辕在BLOOM-176B的基础上针对中文通用领域和金融领域进行了针对性的预训练与微调,它不仅可以应对通用领域的问题,也可以解答与金融相关的各类问题,为用户提供准确、全面的金融信息和建议。

如果有用到轩辕相关方法和模型,请引用以下论文:

XuanYuan 2.0: A Large Chinese Financial Chat Model with Hundreds of Billions Parameters

Self-QA: Unsupervised Knowledge Guided Language Model Alignment

CGCE: A Chinese Generative Chat Evaluation Benchmark for General and Financial Domains

【热门问题】如何调用轩辕模型?

由于本模型较大并不支持线上API测试,请下载模型后使用transformers库的AutoTokenizer和AutoModel进行调用。 轩辕对话模型的输入示例:

BOS_TOKEN + "Human: " + query + "\n\nAssistant: "

轩辕对话模型的生成示例:

output = model.generate(**input, do_sample=True, temperature=0.8, top_k=50, top_p=0.9, early_stopping=True, repetition_penalty=1.1, min_new_tokens=1, max_new_tokens=256)

轩辕作为一个开源的中文金融对话模型,仅限于非商业用途的目的。该模型的设计初衷是为了促进学术研究、技术探索和个人学习等非商业领域的应用。我们鼓励学术界、开发者和研究人员使用轩辕来推动对话系统和金融领域的进步。其中,商业用途包括但不限于将轩辕用于产品、服务、咨询等与商业利益相关的活动。

对于轩辕模型生成的言论,我们不承担任何责任。使用者在将轩辕应用于非商业用途时,需要自行承担潜在的风险,并始终保持审慎。我们建议用户在使用模型输出的信息时,进行独立的验证和判断,并根据个人的需求和情境进行决策。我们希望通过轩辕的开源发布,为学术界和开发者社区提供一个有益的工具,并推动对话系统和金融技术的发展。我们鼓励大家积极探索和创新,以进一步拓展和应用轩辕的潜力,并共同促进人工智能在金融领域的研究和实践。

我们鼓励使用者在相关工作中引用轩辕,以促进知识的交流和分享,并推动中文金融对话系统的发展。轩辕的发布将为金融领域的应用和研究提供强大的支持,并为中文金融对话系统的发展做出重要贡献。我们期待看到更多的创新和应用,以提升金融服务和用户体验,并进一步推动人工智能技术在金融领域的发展。