Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
P.S. 如果您按照以下步骤成功接入了新的大模型,欢迎发Pull Requests(如果您在自己接入新模型的过程中遇到困难,欢迎加README底部QQ群联系群主)
复制request_llms/bridge_llama2.py
,重命名为你喜欢的名字
修改load_model_and_tokenizer
方法,加载你的模型和分词器(去该模型官网找demo,复制粘贴即可)
修改llm_stream_generator
方法,定义推理模型(去该模型官网找demo,复制粘贴即可)
命令行测试
tests/test_llms.py
(聪慧如您,只需要看一眼该文件就明白怎么修改了)python tests/test_llms.py
测试通过后,在request_llms/bridge_all.py
中做最后的修改,把你的模型完全接入到框架中(聪慧如您,只需要看一眼该文件就明白怎么修改了)
修改LLM_MODEL
配置,然后运行python main.py
,测试最后的效果
复制request_llms/bridge_zhipu.py
,重命名为你喜欢的名字
修改predict_no_ui_long_connection
修改predict
命令行测试
tests/test_llms.py
(聪慧如您,只需要看一眼该文件就明白怎么修改了)python tests/test_llms.py
测试通过后,在request_llms/bridge_all.py
中做最后的修改,把你的模型完全接入到框架中(聪慧如您,只需要看一眼该文件就明白怎么修改了)
修改LLM_MODEL
配置,然后运行python main.py
,测试最后的效果
gpt_academic
Python JavaScript HTML CSS SVG other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》