ViennaFox

joined 10 months ago
sorted by: new top controversial old
ExLlamaV2: The Fastest Library to Run LLMs in c/localllama@poweruser.forum
[–] ViennaFox@alien.top 1 points 10 months ago

It works fine for me. I am also using a 3090 and text-gen-webui like Liquiddandruff.

Non-coding 34b models- anyone had much success? in c/localllama@poweruser.forum
[–] ViennaFox@alien.top 1 points 10 months ago

Might I ask what context and instruct template your using?

dolphin-2.2-yi-34b released in c/localllama@poweruser.forum
[–] ViennaFox@alien.top 1 points 10 months ago

Anyone have a good SillyTavern preset for this model? I haven't been able to nail one down.

Point me towards some basic dataset preparation tips for LLM's? in c/localllama@poweruser.forum
[–] ViennaFox@alien.top 1 points 10 months ago

Sadly, I haven't found any guides on dataset creation or preparation. It seems really sparse, when one would think knowing how to create a high quality dataset would be important for AI. It feels like a massive blindspot in the community at the moment. Unless I'm missing something, because I would love for there to be a trove of high quality, concise information that touches on the sort of things OP describes.