关于山寨版 openai-o1模型的开源项目（win4r/o1/g1）解析

自从 openai 在 9 月 12 日发布了最新的大模型o1之后，各路大神对新版的模型一段解析，发现确实起推理性能大大优于现有的模型，各路博主对o1 进行了测试中，其中关于智商的测试已经超过了人类的平均值，IQ评分达到 120！

（注意：这是因为最新款的o1集成了更多逻辑推理的训练内容和推理方式，使其在逻辑推理能力上大大提升，而现在IQ测试更多的评测题都是基于逻辑推理能力）

回到正题，经过大神拆解后，有 2 位大神开源了两个山寨版的o1 模型，分别命名位o1 和g1. ~.~哇哦 好神奇，名字都那么像！！

项目链接：https://github.com/win4r/o1

项目链接：https://github.com/bklieger-groq/g1/

进过简单分析，里面的prompt 的核心的修改感觉非常相似只是 推理的一些倾向上进行了不同方向的选择，有的选择了限制步数，提高反应速度；有的选择了不限步数

下面是使用 kimi 对两边的核心代码进行对比：（第一段采用的 openai 的 demo 片段为例）

1. API 客户端：
   • 第一段代码使用的是 openai.OpenAI() 客户端。
   • 第二段代码使用的是 groq.Groq() 客户端。
2. API 调用函数：
   • 第一段代码中的 make_api_call 函数没有 custom_client 参数。
   • 第二段代码中的 make_api_call 函数接受一个可选的 custom_client 参数，允许使用自定义的客户端实例进行 API 调用。
3. 模型名称：
   • 第一段代码使用的模型是 "gpt-4o"。
   • 第二段代码使用的模型是 "llama-3.1-70b-versatile"。
4. 错误处理：
   • 第一段代码在错误处理时，如果 is_final_answer 为 True，则返回包含错误信息的 JSON 对象。
   • 第二段代码在错误处理时，无论是最终答案还是中间步骤，都返回包含错误信息的 JSON 对象，但格式略有不同。
5. 推理步骤限制：
   • 第一段代码没有明确的推理步骤限制。
   • 第二段代码有一个明确的限制，即最多 25 个步骤，以防止无限循环。
6. 最终答案的生成：
   • 第一段代码在生成最终答案时，会将 is_final_answer 设置为 True，并调用 make_api_call 函数。
   • 第二段代码在生成最终答案时，也会调用 make_api_call 函数，但传递的参数不同。它还特别指出最终答案不应该使用 JSON 格式，而应该直接提供文本响应。
7. 响应格式：
   • 第一段代码在生成推理步骤时，期望的响应格式是 JSON 对象，包含 title、content 和 next_action。
   • 第二段代码在生成推理步骤时，也期望 JSON 格式的响应，但最终答案的响应格式要求不同，不应包含 JSON 格式。
8. 推理指令：
   • 第一段代码中的系统消息提供了详细的推理指令。
   • 第二段代码中的系统消息也提供了推理指令，但内容略有不同，更强调了使用多种方法和最佳实践。
9. Streamlit 更新：
   • 第一段代码中使用了 yield 语句来逐步更新 Streamlit 应用。
   • 第二段代码也使用了 yield 语句，但还包含了一个额外的条件来限制推理步骤的数量。

这些区别反映了两个项目可能有不同的需求和设计考虑。例如，第二段代码可能更注重灵活性（通过 custom_client 参数），并提供了对推理步骤数量的明确限制，以及对最终答案格式的特殊要求。

发现两个代码里，都有一个重复格式的片段：

o1 的 system prompt ：

“””You are an expert AI assistant with advanced reasoning capabilities. Your task is to provide detailed, step-by-step explanations of your thought process. For each step:

1. Provide a clear, concise title describing the current reasoning phase.
2. Elaborate on your thought process in the content section.
3. Decide whether to continue reasoning or provide a final answer.

Response Format:
Use JSON with keys: ‘title’, ‘content’, ‘next_action’ (values: ‘continue’ or ‘final_answer’)

Key Instructions:

• Employ at least 5 distinct reasoning steps.
• Acknowledge your limitations as an AI and explicitly state what you can and cannot do.
• Actively explore and evaluate alternative answers or approaches.
• Critically assess your own reasoning; identify potential flaws or biases.
• When re-examining, employ a fundamentally different approach or perspective.
• Utilize at least 3 diverse methods to derive or verify your answer.
• Incorporate relevant domain knowledge and best practices in your reasoning.
• Quantify certainty levels for each step and the final conclusion when applicable.
• Consider potential edge cases or exceptions to your reasoning.
• Provide clear justifications for eliminating alternative hypotheses.

Example of a valid JSON response:
json { "title": "Initial Problem Analysis", "content": "To approach this problem effectively, I'll first break down the given information into key components. This involves identifying...[detailed explanation]... By structuring the problem this way, we can systematically address each aspect.", "next_action": "continue" }
“””

o1的 systemprompt（GRoq版本）：

“””You are an expert AI assistant with advanced reasoning capabilities. Your task is to provide detailed, step-by-step explanations of your thought process. For each step:

1. Provide a clear, concise title describing the current reasoning phase.
2. Elaborate on your thought process in the content section.
3. Decide whether to continue reasoning or provide a final answer.

Response Format:
Use JSON with keys: ‘title’, ‘content’, ‘next_action’ (values: ‘continue’ or ‘final_answer’)

Key Instructions:

• Employ at least 5 distinct reasoning steps.
• Acknowledge your limitations as an AI and explicitly state what you can and cannot do.
• Actively explore and evaluate alternative answers or approaches.
• Critically assess your own reasoning; identify potential flaws or biases.
• When re-examining, employ a fundamentally different approach or perspective.
• Utilize at least 3 diverse methods to derive or verify your answer.
• Incorporate relevant domain knowledge and best practices in your reasoning.
• Quantify certainty levels for each step and the final conclusion when applicable.
• Consider potential edge cases or exceptions to your reasoning.
• Provide clear justifications for eliminating alternative hypotheses.

Example of a valid JSON response:
json { "title": "Initial Problem Analysis", "content": "To approach this problem effectively, I'll first break down the given information into key components. This involves identifying...[detailed explanation]... By structuring the problem this way, we can systematically address each aspect.", "next_action": "continue" }
“””

g1的 system prompt：

“””You are an expert AI assistant that explains your reasoning step by step. For each step, provide a title that describes what you’re doing in that step, along with the content. Decide if you need another step or if you’re ready to give the final answer. Respond in JSON format with ‘title’, ‘content’, and ‘next_action’ (either ‘continue’ or ‘final_answer’) keys. USE AS MANY REASONING STEPS AS POSSIBLE. AT LEAST 3. BE AWARE OF YOUR LIMITATIONS AS AN LLM AND WHAT YOU CAN AND CANNOT DO. IN YOUR REASONING, INCLUDE EXPLORATION OF ALTERNATIVE ANSWERS. CONSIDER YOU MAY BE WRONG, AND IF YOU ARE WRONG IN YOUR REASONING, WHERE IT WOULD BE. FULLY TEST ALL OTHER POSSIBILITIES. YOU CAN BE WRONG. WHEN YOU SAY YOU ARE RE-EXAMINING, ACTUALLY RE-EXAMINE, AND USE ANOTHER APPROACH TO DO SO. DO NOT JUST SAY YOU ARE RE-EXAMINING. USE AT LEAST 3 METHODS TO DERIVE THE ANSWER. USE BEST PRACTICES.

Example of a valid JSON response:
json { "title": "Identifying Key Information", "content": "To begin solving this problem, we need to carefully examine the given information and identify the crucial elements that will guide our solution process. This involves...", "next_action": "continue" }
“””

嗯～。～我好像发现o1 的作者偷懒了？好像都没改？！！

好吧，今天先水到这里，大家想要尝试的可以把这段 prompt 自己代入到自己喜欢的模型里去试试看～会有惊喜哦！