ChatGLM2-6B · Issues· 450 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #689
[BUG/Help] <title>在colab运行时 实例代码是报错
Updated Oct 3, 2025 - #204
【help】RuntimeError： Tensor on device meta is not on the expected device cuda:0!
Updated Apr 15, 2025 - #688
[BUG/Help] API部署
Updated Mar 20, 2025 - #687
运行openapi.py
Updated Mar 20, 2025 - #686
[BUG/Help] <title>运行示例代码出现TypeError报错
Updated Feb 17, 2025 - #393
[BUG/Help] <lora微调遇到报错：RuntimeError: Subtraction, the `-` operator, with a bool tensor is not supported. If you are trying to invert a mask, use the `~` or `logical_not()` operator instead.>
Updated Jan 25, 2025 - #685
[BUG/Help] <title>
Updated Jan 17, 2025 - #684
[BUG/Help] <title>OSError: [WinError 123] 文件名、目录名或卷标语法不正确。: 'C:\\Users\\\xx\\.cache\\huggingface\\modules\\transformers_modules\\E:'
Updated Dec 23, 2024 - #352
[Feature | Bug Fix] <ChatGLM2-6B-int4 使用CPU部署报错：找不到文件quantization_kernels_parallel.so>
Updated Dec 3, 2024 - #616
[BUG/Help] <title>运行web_demo.py报错
Updated Nov 20, 2024 - #583
[Help] lora微调合并后模型推理速度明显慢了好多
Updated Aug 9, 2024 - #640
[BUG/Help] readme中清华云盘的模型文件版本不对，跑出来是乱码，需使用huggingface.co模型，麻烦更新
Updated Aug 7, 2024 - #660
[BUG/Help] <pytorch_model.bin don't exists>
Updated Aug 6, 2024 - #407
[BUG/Help] 有个疑问，模型刚开始运行的时候推理很慢，但是过一段时间（问一些问题或者两三个小时后）推理就很快了，这个是什么原因？
Updated Jul 28, 2024 - #414
旋转位置编码
Updated Jul 16, 2024