Maybe, maybe not • 2m
Maybe I am wrong because I haven't used these models. Due to smaller size, they could have instant speed.
Roadside Developer a... • 5m
*Nandan Nilekani wrong about pushing India to ignore model training skills*: Perplexity CEO Arvind Srinivasan According to Arvind “*India should know how to build models and that too possible in low cost*” It would be amazing *if some team could d
See MoreFounder - Burn Inves... • 1m
The Indian stock market is currently on a positive trend, but personally, I don't see much upside potential from here. The valuations seem a bit stretched, and the recent results haven't been particularly impressive overall, at least when I compare t
See MoreHey I am on Medial • 3m
"Just fine-tuned LLaMA 3.2 using Apple's MLX framework and it was a breeze! The speed and simplicity were unmatched. Here's the LoRA command I used to kick off training: ``` python lora.py \ --train \ --model 'mistralai/Mistral-7B-Instruct-v0.2' \ -
See MoreDownload the medial app to read full posts, comements and news.