Just wanted to these the thesven/Llama3-8B-SFT-code_bagel-bnb-4bit model someone trained on a small subset on my code bagel dataset so i used gguf-my-repo to quantize it.
THIS IS NOT MY MODEL
Update: I tested it, I wasnt very impressed. Look forward to my own train coming in a little over a month.
https://x.com/dudeman6790/status/1793638914353508549z
