Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
作者自述
描述
本次 pr 实现的功能:
对话示例
作为助手机器人对话(无 system prompt)
使用知识库设定进行角色扮演对话(直接使用上文的回答作为system prompt)
相关问题
无,直接弄出来了
补充信息
该公司比较有名的应用是 Glow,据说用户已经上百万而且效果不错。
现在已经对公司开放 API 申请。
个人感觉比较擅长 文本续写和角色扮演对话,对于指令性和代码生成有待提高。
作为国产 AI 自然是可以直接调用,不论是生成速度还是价格都比 openai 好。
定价
abab4 暂时看不到了,但是比abab5便宜很多
介绍
Minimax 最新一代的中文大语言模型
帮助人类高效写作、激发创意、获取知识、做出决策
相关新闻
传获米哈游投资,估值10亿美元:一家低调的AI创业公司
和AI谈恋爱,掏空我钱包
Copilot4PR
🤖 Generated by Copilot at 086575e
Summary
🔑💬🎲
This pull request adds support for the MiniMax chat models, which use a game-theoretic strategy for generating chat responses. It defines a new model type,
Minimax
, and a new class,MiniMax_Client
, that handles the communication with the MiniMax chat API. It also adds the necessary configuration options, environment variables, and model names to enable the use of the MiniMax models.Walkthrough
config.py
and set the environment variable MINIMAX_API_KEY (link)base_model.py
and a new condition to the get_type function to recognize MiniMax models (link, link)minimax.py
that contains the MiniMax_Client class, which inherits from the BaseLLMModel class and implements the methods for interacting with the MiniMax chat API (link)models.py
that creates and returns an instance of the MiniMax_Client class based on the model name and the access key, and import theminimax
module (link)presets.py
that correspond to the MiniMax chat models (link)