Needle: Finetune a 26M Tool-Calling Model Locally with Ollama
This video installs and tests Needle which runs on Cactus at 6000 toks/sec prefill and 1200 decode speed. π₯ Buy Me a Coffee to support the channel: https://ko-fi.com/fahdmirza #cactusneedle #needleai π₯ Get 50% Discount on any A6000 or A5000 GPU rental, use following link and coupon: https://bit.ly/fahd-mirza Coupon code: FahdMirza π₯ Buy Me a Coffee to support the channel: https://ko-fi.com/fahdmirza #needleai PLEASE FOLLOW ME: βΆ LinkedIn: / fahdmirza βΆ YouTube: / @fahdmirza βΆ Blog: https://www.fahdmirza.com RESOURCES: βΆ https://github.com/cactus-compute/needle All rights reserved Β© Fahd Mirza