About 784,000,000 results
Open links in new tab
  1. GitHub - openai/gpt-oss: gpt-oss-120b and gpt-oss-20b are two …

    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 …

  2. 可以详细说下从GPT-1到GPT-4,有哪些变化,是如何发展的? - 知乎

    GPT-3不仅能生成连贯的段落,而且能生成整篇与上下文相关、风格一致的文章,这些文章通常与人类编写的内容无法区分。 GPT-3具有零样本学习的能力,即使在没有经过特定训练的情况 …

  3. GitHub - openai/gpt-2: Code for the paper "Language Models are ...

    The dataset our GPT-2 models were trained on contains many texts with biases and factual inaccuracies, and thus GPT-2 models are likely to be biased and inaccurate as well. To avoid …

  4. GitHub - binary-husky/gpt_academic: 为GPT/GLM等LLM大语言模 …

    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. …

  5. GPT-API-free / DeepSeek-API-free - GitHub

    ️ 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。

  6. gpt-engineer - GitHub

    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 get started …

  7. OpenAI 发布三款 GPT-4.1 系列模型,性能有哪些提升?对行业来 …

    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 …

  8. OpenAI ChatGPT(四):十分钟读懂 GPT-3 - 知乎

    GPT-3还在设计用于测试快速适应或即兴推理的任务中表现出了不错的能力,其中包括打乱单词、进行算术运算以及在仅看到一次定义后在句子中使用新词。 在 few-shot 设置中,GPT-3 可以 …

  9. GitHub - karpathy/minGPT: A minimal PyTorch re-implementation …

    A PyTorch re-implementation of GPT, both training and inference. minGPT tries to be small, clean, interpretable and educational, as most of the currently available GPT model …

  10. GitHub - gpt4o-image/GPT-4o: 新版GPT-4o生图功能太强了(附国 …

    Oct 23, 2025 · 新版GPT-4o生图功能太强了(附国内使用指南)【9月最新更新】. Contribute to gpt4o-image/GPT-4o development by creating an account on GitHub.