taozhiyuai
taozhiyuai
> I'm also getting this from mixtral:8x22b-instruct-v0.1-q3_K_M and mixtral:8x22b-instruct-v0.1-q3_K_S on my 64GB M3 Max. The normal mixtral:8x22b-instruct-v0.1-q4_0 works just fine (albeit very slowly). Q3KM is OK for me.@asmeurer
> Maybe try `sudo make build` if `sudo` is safe for you. thanks but, error with this instruction. ` (opendevin) taozhiyu@TAOZHIYUs-MBP OpenDevin % sudo make build Password: Building project... Pulling...
折腾这玩意干嘛?默认的modelfile不挺好的?
https://github.com/geekan/MetaGPT/issues/1218
> What macbook are you using? An M3 Max? 🤔 I've seen an issue like this [here](https://github.com/huggingface/exporters/issues/69) as well as in the coreml stable diffusion repo specific to M3 macbooks....
> We at [EVA](https://github.com/georgia-tech-db/eva/) have been using decord in our project and find it to be extremely useful! To support eva users working on the newer macs (arm architecture), we...
import from gguf yourself.
> 这么大的模型，用ollama 4bit可能都得120G内存以上。 > > 有没有勇士尝试过？ 我的可以跑
not much better performance than llama 3, but 3 times bigger in size than 70B. not recommended to run only most personal machine.
几十甚至几百个GB的, 只用KB去下载?搞到猴年马月?100MB我都嫌慢