wupengcheng6819
wupengcheng6819
I am running `npx dalai serve` on a remote GUI-less machine, I couldn't get connected via `http://:3000/` What could be the problem? Thanks much!
Chatgpt was saying to add `0.0,0.0` to `app.listen` in the main js file. But I just couldn't find `app.listen` command anywhere.
没有GPU;32G内存的ubuntu机器。 按照readme,执行 1. conda create -n python=3.8 2. conda activate 3. 在项目路径下pip install -r requirements.txt 4. 修改model_config.py的默认模型为LLM_MODEL = "chatglm-6b-int4" 5. python cli_demo.py 6. 输入知识库路径,内有一个中文txt文件,而路径和文件名均没有中文。 7. 输入一个问题,随便什么 然后,就hang住了,没有结果返回。 注:模型加载时loader.py中的params参数去掉了`"low_cpu_mem_usage": True`: `params...
I was trying to build `7za` within the `7-Zip-zstd/CPP/7zip/Bundles/Alone` folder, but the final linking (`zstd` library) always fails: ``` /usr/bin/ld: _o/ZipAddCommon.o: in function `NArchive::NZip::CAddCommon::Compress(ISequentialInStream*, IOutStream*, bool, bool, unsigned int, unsigned...
As a not-so-experienced C programmer, I am not sure what to do with the .hh file. Could you kindly give a *complete* working solution?
**Describe the bug** The `streaming_decompression` tool in the `examples` folder is consistently slower than `zstd -d`, I wonder what could be the cause? I tried to link `streaming_compression` statically and...