hyperbolic-c

> @hyperbolic-c Ah, I remember I also had to use `--vocab-type bpe` when converting otherwise it would choose the wrong tokenizer. @CISC yes, but another error is weird, which like...

> @hyperbolic-c Did you try again after converting with the right tokenizer? It worked for me, and for @ikawrakow when using my converted GGUF. > > If it still doesn't...

I also meet the error. Any solutions ? **Is it not possible to use folly on WSL2 ?**

Sadly. And the issue nobody to fix. what a pity... ---- Replied Message ---- | From | ***@***.***> | | Date | 04/11/2023 17:28 | | To | ***@***.***> |...

@Ariellink oh god... Change **gcc** from **9.4** to **10** then **fixed** !!!!!

@b4rtaz Sorry for the lack of clarity. Actually, I want to say how to convert the model network layer to **distributed-llama** format, converting open source models other than llama2 or...

在1.3B的gguf量化模型上也出现这个问题，并且几乎每个问答都会出现。

请问vllm部署时如何使用多卡加载模型，使用`CUDA_VISIBLE_DEVICES=0,1`还是只有一张卡load了， 很奇怪，谢谢

> > 请问vllm部署时如何使用多卡加载模型，使用`CUDA_VISIBLE_DEVICES=0,1`还是只有一张卡load了， 很奇怪，谢谢 > > try add `--tp=2` to launch argument thanks, I have solved it by set `--tensor-parallel-size` >1.

@ForeverPx @PlagueDoctors , in the **default_config.yml**: ``` # Manim often generates tex_files or other kinds of serialized data # to keep from having to generate the same thing too many...