selfhostedAI icon indicating copy to clipboard operation
selfhostedAI copied to clipboard

A collection of one-click self-hosted AI

Results 7 selfhostedAI issues
Sort by recently updated
recently updated
newest added

Dear selfhostedAI developer, 我是 InternLM 社区开发者&志愿者尖米, 大佬开源的工作对我的启发很大,希望可以探讨使用 InternLM 实现 selfhostedAI 的可能性和实现路径,我的微信是 mzm312,希望可以取得联系进行更深度的交流; Best regards, 尖米

使用llama-7b-4int模型后,终端运行成功 插件选择自定义模型后,提问 报错:错误: Cannot read properties of undefined (reading '0') 我看了终端,是有回答的,但是插件是无法显示吗?

I am using an NVIDIA MX450 GPU on my laptop and was excited to try your selfhostedAI project. After installing GCC and CUDA 11, I managed to get it running....

在本地已经跑起来了,效果不错 用POSTMAN来调用,如何传参呢。 非常感谢

``` File "C:\Users\sicma/.cache\huggingface\modules\transformers_modules\local\modeling_chatglm.py", line 277, in attention_fn attention_scores = attention_scores * query_key_layer_scaling_coeff torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 116.00 MiB (GPU 0; 6.00 GiB total capacity; 5.07 GiB...

Error raises, when server responses to request Log: [log.txt](https://github.com/josStorer/selfhostedAI/files/11061050/log.txt)