Readon

> FYI https://github.com/numero-744/Aes has been updated; part of its contents could be put in the template: > > * add `tb/` folder for `Test` (not released contents) with sub-directories like...

> @Readon I just tested sbt with : > > Test / scalaSource := baseDirectory.value / "miaou" / "spinal", > > It worked well for me. > > What issue...

According to the [diagram](https://oobabooga.github.io/blog/posts/gptq-awq-exl2-llamacpp/), it seems that exllama v2 is much better at generating speed.

> > According to the [diagram](https://oobabooga.github.io/blog/posts/gptq-awq-exl2-llamacpp/), it seems that exllama v2 is much better at generating speed. > > Also from that link: > > > Update 2: Gerganov has...

I met this also while doing "Detailed" research. While gpt-researcher searching for subtopics. Here is the prompting of backend. ``` Subtopics: subtopics=[Subtopic(task='xxxxxx'), Subtopic(task='yyyyyy'), Subtopic(task='zzzzz')] INFO: connection closed INFO: connection closed...

I have tested gpt-researcher with a smaller LLM which pass the generation.

> 谢谢您的修改建议！ 我做这个模板的初衷就是故意不用sty等打包的操作，在tex文件中把所有操作和微调的权力交给用户（因为我不敢保证这个模板的效果很完美），利用初级简明的latex语法，配合比较直观的注释说明，即使是LaTeX新手也可以依样画葫芦修改（bib格式文件除外，因为实在没有办法不打包）。用sty的模板网上可以搜到一些已经做的很棒的。 因此暂时先不做打包处理。非常抱歉，再次感谢您的建议。 好的，我看到这个一直在更新所以试了一下。 发现几个问题：  1. 粗体比原模板粗。 2. 阿拉伯数字的字体与原模板不同。 3. “报告正文”与后续段落间隔不同。 PR中间微调了文本框大小和字体后，文字位置基本一致了。

It would be also an good idea to share computing power in a private LAN.

> [@nekiee13](https://github.com/nekiee13) Great that it worked for you! Regarding the MoE models my initial tests on DeepSeek R1 also found limited improvement when using 2 CPUs, so now I'm going...

> > So, it would kinda only matter in places where you bring literals ? That impact the way binary literals are pushed to the bit vector ? > >...