🚀 GLM-4-32B-0414

The GLM-4-32B-0414 series models are new additions to the GLM family, boasting 32 billion parameters. Their performance rivals that of OpenAI's GPT series and DeepSeek's V3/R1 series, and they support highly user - friendly local deployment.

✨ Features

Model Overview

The GLM-4-32B-Base-0414 was pre - trained on 15T of high - quality data, including a large amount of reasoning - type synthetic data. This pre - training lays the foundation for subsequent reinforcement learning extensions. In the post - training stage, human preference alignment was employed for dialogue scenarios. Through techniques like rejection sampling and reinforcement learning, the model's performance in instruction following, engineering code, and function calling was enhanced, strengthening the atomic capabilities required for agent tasks.

Model Variants

• GLM - Z1 - 32B - 0414: A reasoning model with deep thinking capabilities, developed based on GLM - 4 - 32B - 0414 through cold start, extended reinforcement learning, and further training on tasks such as mathematics, code, and logic. It significantly improves mathematical abilities and the capability to solve complex tasks compared to the base model. General reinforcement learning based on pairwise ranking feedback was also introduced during training to enhance the model's general capabilities.
• GLM - Z1 - Rumination - 32B - 0414: A deep reasoning model with rumination capabilities. Unlike typical deep - thinking models, it can engage in deeper and longer thinking to solve more open - ended and complex problems. It is trained through scaling end - to - end reinforcement learning with responses graded by the ground truth answers or rubrics and can use search tools during the deep - thinking process to handle complex tasks. It shows significant improvements in research - style writing and complex tasks.
• GLM - Z1 - 9B - 0414: A small model (9B) trained using all the aforementioned techniques. It exhibits excellent capabilities in mathematical reasoning and general tasks, and its overall performance ranks among the top of all open - source models of the same size. It achieves an excellent balance between efficiency and effectiveness, especially in resource - constrained scenarios, providing a powerful option for users seeking lightweight deployment.

Showcase

Animation Generation

Web Design

Model	Details
GLM - 4 - 32B - 0414	Design a drawing board that supports custom function plotting, allowing adding and deleting custom functions, and assigning colors to functions.
GLM - 4 - 32B - 0414	Design a UI for a mobile machine learning platform, which should include interfaces for training tasks, storage management, and personal statistics. The personal statistics interface should use charts to display the user's resource usage over a period. Use Tailwind CSS to style the page, and display these 3 mobile interfaces tiled on a single HTML page.

SVG Generation

Model	Details
GLM - 4 - 32B - 0414	Create a misty Jiangnan scene using SVG.
GLM - 4 - 32B - 0414	Use SVG to illustrate the training process of an LLM.

Search - Based Writing

For search - based writing tasks, the following system prompt is used to have the model respond based on search results:

请根据所给搜索返回结果对用户问题进行作答。

## 注意
1. 充分利用和整理收集到的信息，而不是简单的复制粘贴，生成符合用户要求且有深度的专业答案。
2. 所提供信息充分的情况下，你的回答需尽可能延长，从用户意图角度出发，提供具有足够信息量和多角度的回复。
3. 另外，并非所有的搜索结果都与用户问题密切相关，请仔细的甄别、筛选和利用。
4. 客观类问答的答案通常非常简短，你可以适当补充一到两句相关信息，以丰富内容。
5. 请确保你的回复格式美观、可读性强。对于多实体对比或列举，善用列表格式来帮助用户更好的理解信息。
6. 除非用户要求，否则你回答的语言请于用户提问语言保持一致。
7. 在适当情况下在句子末尾使用例如:【0†source】的格式引用搜索结果。

When using, search results can be obtained through methods such as RAG or WebSearch, and wrapped in observation, for example:

[
    {
        "role": "user",
        "content": "Explore the common characteristics of children's literature, with a focus on its narrative techniques and thematic tendencies. This includes narrative techniques: common approaches in children's literature such as first - person, third - person, omniscient narrator, and interactive narration, and their influence on young readers. It also includes thematic tendencies: recurring themes in children's literature such as growth, adventure, friendship, and family, with an analysis of how these themes impact children's cognitive and emotional development. Additionally, other universal features such as the use of personification, repetitive language, symbolism and metaphor, and educational value should be considered. Please provide a detailed analytical report based on academic research, classic examples of children's literature, and expert opinions."
    },
    {
        "role": "observation",
        "content": "【{id}†{title}†{url}】\n{content}"
    },
    ...
]

For the above prompt, an internal or external search model can be used to obtain the search results. Using the format shown above, the following analysis report can be generated:

📄 License

This project is licensed under the MIT license.