ye7iaserag
ye7iaserag
I've seen multiple example of fingerprinting using the browser installed fonts. Can this be achieved by injecting fonts while injecting headers?
**Describe the bug** When you do a fresh install and click outpaint you get the error `StableDiffusionInpaintPipelineLegacy.__call__() missing 1 required positional argument: 'init_image'` This is because `diffusers` was updated to...
A very promising RNN based model, instead of transformers, claiming more lean memory consumption and faster inference Here is the 14b card https://huggingface.co/BlinkDL/rwkv-4-pile-14b
Meta just released there LLaMA model family https://github.com/facebookresearch/llama Can we got support for that? They calim that the 13B model is better than GPT 3 175B model ------------------------ This is...
Trying to get LLaMa 30B 4bit quantized to run with 12GB of vram and I'm hitting OOM since the model is a bit more than 16gb Is it possible to...
Mainly title, extensions are displayed in gradio by folder name which is sometimes ugly This PR introduces a new field called `display_name` that is read from params dict when the...
Exactly #1036 This is a huge security flow which have not been fixed for a long time Please look into it ### Your environment | Q | A | -----------------...
As title says, for scripting languages like php and JavaScript, projects usually have huge vendors/node_modules directories, those are not important to include in the context at all, since only the...
As someone who uses local models, sometimes responses could take a long time to arrive from the LLM, especially if dealing with huge context And your HTTP request times out...
Please provide a way to extend the UI of LM Studio in a way developers can integrate / introduce new extensions and features. Ex. - Adding tabs to the UI....