Repository Issue Activity (beta)

#808 没有找到技术文档中提到的basic_demo

#802 套餐使用并发

#706 少量数据训练正常，大量数据时训练loss逐渐变大，有没有什么排查的方向？

#807 GLM-4v-9b微调时，map显示0%

#806 [Energy] N6 Arithmetic: 50-70% AI Training/Inference Energy Reduction — 17 Techniques with Code

#804 Delete account

#801 Problem with sending data from other AI thread

#800 glm-4.7 在 claude code 使用 如何默认开启 工具流式传输 tool_stream=True

#769 ollama 推理报 Error: unsupported architecture "Glm4ForCausalLM" 错误

#799 经常出现引号中断的情况

#798 api_request请求失败

#716 'ChatGLMForConditionalGeneration' object has no attribute '_extract_past_from_model_output'

#797 Help Regarding memorization

#796 New subscriber. Chat behaving strangely.

#795 GLM-Z1-32B-0414和GLM-Z1-Rumination-32B-0414模型乱码

#794 GLM-Z1-32B-0414和GLM-Z1-Rumination-32B-0414模型乱码

#785 4张24GB显存的4090lora微调GLM-4V-9B时，还是爆显存

#772 GLM-Z1-32B-0414 vLLM部署 reasoning 有问题

#793 使用vllm启动glm4.5v 106B的时候显示Transformers 库无法识别 glm4v moe 这种模型架构

#792 More Specific Tool Calling in Z1 Rumination for replication or use locally

#791 An inconsistency between the English and Chinese versions of the README

#786 微调GLM-4V-9B时出错：RuntimeError: CUDA error: named symbol not found

#788 vllm 0.9.2 `limit_mm_per_prompt` is only supported for multimodal models.

#784 Questions about some loss functions of reinforcement learning

#783 请教一下关于旧版glm4v-9b的部署兼容问题