Araki

I have the same issue. When I'm applying LoRA over a model loaded with Transformers, the LoRA doesn't apply even if it says that it was applied successfully. The model...

Inferencing the barebone version of this model on a CPU will be next to unusable. The closest we can get to running this model locally is by using a heavily...

The new img2img.py doesn't seem to be working for me. The terminal window gives me this error, even with the 3rd party extensions disabled: ``` Traceback (most recent call last):...

The Sep 19, 2022 build doesn't do anything for me either. Not even --help, nor --verbose. Only the release build of 0.3.1 works. Edit: 0.3.1 doesn't seem to work too,...

It's awesome that even the 13B model can be run in Colab, however, the context window is pretty limited, I get `OutOfMemoryError` at 314 words. `torch.cuda.OutOfMemoryError: CUDA out of memory....

You can experiment with 4 bits from here: https://github.com/qwopqwop200/GPTQ-for-LLaMa

Well, yeah, it's pretty much abandoned. But as @jkkma said, the community still "supports" it ~~(i.e. shares links on Discord for you to click on and execute unknown .exe's on...

I'm experiencing the same issue after upgrading to 0.5.0. In the console, I keep seeing these INFO warnings popping up every second: ``` INFO: 127.0.0.1:38708 - "GET /ws/socket.io/?EIO=4&transport=polling&t=PG01YYc HTTP/1.1" 400...

> > proxy_pass http://127.0.0.1:8081; > > Try to add another line with ws://127.0.0.1:8081 Nginx considers another `proxy_pass` line as a duplicate, as far as I know it should handle `ws://`...

I support this. Some users might decide to use alternative providers, such as Anthropic, Google, LLM aggregators like OpenRouter, or even locally deployed models (that support OpenAI-compatible endpoints) to avoid...