The same prompt, written once by 4 local Ollama models + 12 cloud models from three Agent CLIs. Below are all the original outputs, along with the speed, VRAM, latency, and token data recorded for each run. The English version is not a translation of this page, but rather another experiment conducted under the same settings but using an English prompt and requiring the writing of an English novel opening. ...
The [README.md](20,768 characters) from the gadget repository is handed over as is to 4 local Ollama models and three Agent CLI models on the cloud, with a requirement to first summarize the project and then write a Chinese usage guide. Below are the model information, speed, VRAM, latency, token data, document structure statistics, and the entire original output recorded during each run. Task 下面是开源项目 gadget 的 README。请你完成两件事： 1. 先用中文总结这个项目：它是什么、仓库结构、每个工具分别做什么。 2. 然后写一份详细的中文使用教程，面向第一次接触这个项目的人，覆盖环境准备、安装、配置，以及每个工具的典型用法（给出可以直接复制的命令）。 只依据 README 里写到的内容，不要编造 README 中没有出现的命令或参数。 ===== README.md ===== <README.md 全文，20 768 字符> The full README should be submitted together with this description, and the entire prompt consists of 20,768 characters. ...
Part ChatGPT 4o ChatGPT 4o API demo from openai import OpenAI model_use = "gpt-4o-2024-08-06" client = OpenAI(api_key="Your-API-key") completion = client.beta.chat.completions.parse( model=model_use, messages=[ {"role": "system", "content": "Extract the event information."}, {"role": "user", "content": "Alice and Bob are going to a science fair on Friday."}, ], ) event = completion.choices[0].message.parsed Note: I tried to use model “gpt-4o” but failed. How to create ChatGPT API Key Log in to openai Use the search bar to search “API keys” Create a new secret key (Shown only once, invisible after closing the tab) Go to billing to add some credit to the account Part UniTox ChatGPT Read from fda.gov Read the label of the drug we are interested in from a .csv file. ...