GitHub - formulahendry/awesome-gpt: A curated list of awesome …
This repository is a collection of awesome projects and resources related to GPT, ChatGPT, OpenAI, LLM, and other related technologies. Whether you're just getting started with GPT or you're a …
OpenAI 发布三款 GPT-4.1 系列模型，性能有哪些提升？对行业来说， …
在 Aider 的多语言 diff 基准测试中，GPT‑4.1 的得分是 GPT‑4o 的两倍以上，甚至比 GPT‑4.5 也高出 8 个百分点。 这项评估不仅衡量模型在多种编程语言下的编码能力，也衡量其生成完整代码或 diff 格 …
GitHub - openai/gpt-oss: gpt-oss-120b and gpt-oss-20b are two open ...
Aug 5, 2025 · Try gpt-oss · Guides · Model card · OpenAI blog Download gpt-oss-120b and gpt-oss-20b on Hugging Face Welcome to the gpt-oss series, OpenAI's open-weight models designed for …
Supported AI models in GitHub Copilot
For all of the default AI models, input prompts and output completions run through GitHub Copilot's content filters for harmful, offensive, or off-topic content, and for public code matching when enabled. …
GitHub - openai/gpt-2: Code for the paper "Language Models are ...
gpt-2 Code and models from the paper "Language Models are Unsupervised Multitask Learners". You can read about GPT-2 and its staged release in our original blog post, 6 month follow-up post, and …
GPT-API-free / DeepSeek-API-free - GitHub
Apr 24, 2023 · ️ 免费API Key gpt-5系列模型的推理能力较弱，若需要更强的推理能力，可以购买付费API ️ 免费API Key仅可用于个人非商业用途，教育，非营利性科研工作中。 免费API Key严禁商用， …
gpt-engineer - GitHub
Oct 26, 2023 · gpt-engineer installs the binary 'bench', which gives you a simple interface for benchmarking your own agent implementations against popular public datasets. The easiest way to …
GitHub - xianyu110/gpt-5.2: 刚刚，GPT-5.2 来了，包含三个版本
GPT-5.2 Thinking 在 70.9% 的任务上胜过或打平行业专家 GPT-5.2 Pro 更高，74.1% GDPval 知识工作 速度是人类专家的 11 倍，成本不到 1% 一个评审员的评价： 「看起来像是一个有员工的专业公司做 …
GitHub - binary-husky/gpt_academic: 为GPT/GLM等LLM大语言模型提 …
Jul 31, 2025 · GPT 学术优化 (GPT Academic) 如果喜欢这个项目，请给它一个Star；如果您发明了好用的快捷键或插件，欢迎发pull requests！ If you like this project, please give it a Star. Read this in …
OpenAI 放王炸，将发布整合多项技术的 GPT-5，并免费无限使用，该 …
GPT-4.5是常规LLM模型，无推理能力 之前一直听说GPT-4.5的开发遇到阻碍，看来OpenAI是已经解决了训练问题，但是注意GPT-4.5会是OpenAI最后的一个非推理模型，这大概说明train-time compute …