Alexandre Strube
Alexandre Strube
Prody 2.2 depends on a very old and deprecated version of BioPython. Please upgrade.
Tested on an iPad, iPhone and a Mac
I am trying to connect two supercomputers for big file transfers as both machines are behind firewalls, and most supercomputers use RedHat-based OSs instead of Ubuntu. I can compile from...
When trying to compile on the 2023.12 version of Raspberry Pi OS, I get: ``` make make -C /lib/modules/`uname -r`/build M=$PWD make[1]: Entering directory '/usr/src/linux-headers-6.1.0-rpi7-rpi-2712' CC [M] /home/surak/16mp-autofocus/IMX519_AK7375/IMX519/imx519.o In file...
Nvidia has their own solution to deploy large language models. Would it make sense to have an adapter? https://developer.nvidia.com/blog/deploy-multilingual-llms-with-nvidia-nim
### Before submitting your bug report - [X] I believe this is a bug. I'll try to join the [Continue Discord](https://discord.gg/NWtdYexhMs) for questions - [X] I'm not able to find...
In gradio_web_server.py, there is a hardcoded host and port for a supposed monitor daemon, but no daemon is around: https://github.com/lm-sys/FastChat/blob/a04072e35d0893e64169c8e3ea153312eb0fe9ac/fastchat/serve/gradio_web_server.py#L391 This, in turn, breaks the usage of openAI endpoints with...
VLLM needs top_j to be int, not float ## Why are these changes needed? For VLLM to work again ## Related issue number (if applicable) Closes #3501 ## Checks -...
If you have a model loaded from a json file, it will appear on the list of the available models on the web UI, but it won't appear on the...
Every model I try ends up with a similar error. This, specifically, is Vicuna-13 from https://huggingface.co/4bit/vicuna-13b-GPTQ-4bit-128g Those are the options I used for calling it: ``` python3 $BLABLADOR_DIR/fastchat/serve/model_worker.py \ --controller...