KoboldAI
KoboldAI copied to clipboard
henk717
- Edited 3 rows in aiserver.py, the first to add the menu item, second in order to not request gpu/cpu and third for the ModelSelectionSchema class. - The openrouter_handler takes...
``` 2024-04-04T18:30:52.181902749Z > File "aiserver.py", line 743, in g 2024-04-04T18:30:52.181906734Z return f(*a, **k) 2024-04-04T18:30:52.181912276Z │ │ └ {} 2024-04-04T18:30:52.181916181Z │ └ ({'custom_model_name': 'aurora-m/aurora-m-biden-harris-redteamed', 'class': 'model', 'label': 'Load custom Pytorch model...
Working instruction mode. Some design decisions in the UI to highlight: - A single action may contain BOTH game text and an instruction - Instructions may be hidden globally in...
need to enable the **8-bit cache**, and the number of contexts can be expanded and the context window itself holds 4 digits, the rest is cut off. Thank you for...
at start:  loading model:  start chat:  that's pretty much it. debug file [kobold_debug.json](https://github.com/henk717/KoboldAI/files/14185527/kobold_debug.json)
[kai_micromamba-fix.patch](https://github.com/henk717/KoboldAI/files/14070453/kai_micromamba-fix.patch) It was annoying me that I had to wait for the thing to do its thing twice, and I decided that was the last time I was *ever* gonna...
[email protected]:~/KoboldAI$ ./play.sh --model models/Aurora-Nights-103B-v1.0-5.0bpw-h6-exl2 --model_backend "ExLlama V2" --model_parameters help Colab Check: False, TPU: False INFO | __main__::732 - We loaded the following model backends: KoboldAI API KoboldAI Old Colab Method...
critical libmamba Can't create 'man/man3/Parse::CPAN::Meta.3' error libmamba Error opening for reading "/media/muhammad/D1/Work/Sociail/KoboldAI/runtime/pkgs/perl-5.32.1-7_hd590300_perl5/info/index.json": No such file or directory error libmamba Error when extracting package: [json.exception.parse_error.101perl-5.32.1-7_hd590300_perl5.conda extraction failed critical libmamba Found incorrect...
This isn't very clean, and there's likely a better way to do this, but it does work. This allows you to switch between NVIDIA and Intel on Windows.
Almost every time I try to submit a prompt or try to generate anything, I get the following errors: ``` ERROR | __main__:generate:3919 - Traceback (most recent call last): File...
