Hugging Face's logo
Jackson Yeskie's picture
🔄 tired of nightshade?

Jackson Yeskie

8BitStudio
11 1 20
123bbt's profile picture Nitesh45433's profile picture XBFDI's profile picture
·

AI & ML interests

Text to image, Language models

Recent Activity

new activity 1 day ago
yethss/The-Quettaset:Line count
reacted to harshitkgupta's post with 🚀 1 day ago
Fine-tuned Qwen 2.5 (0.5B → 3B) on real coding-agent traces, 10 controlled runs, one 16GB Mac. Compared PyTorch MPS vs. Apple MLX for local LoRA SFT — and the honest answer is "it depends on what you're optimizing for": • PyTorch MPS: 2.2x–5.7x faster raw throughput, but hits a hard memory wall — can't load a 3B model in FP16 on 16GB. • Apple MLX: 4-bit QLoRA fits 3B+ models with almost flat memory scaling as context grows (+109 MB going from 1k→4k tokens). • 4-bit quantization doesn't cost you convergence — eval loss tracks closely across backends. • The bigger surprise: most of MLX's slowdown isn't the 4-bit dequant tax. Two of the 10 runs went unquantized to isolate it — dequant only explains 1.07x–1.4x of the gap. A ~4.1–4.6x framework-level gap remains either way. All 10 LoRA adapters + Trackio logs are public so the numbers are checkable, not just claimed. Full writeup: https://huggingface.co/blog/harshitkgupta/fine-tuning-coding-agents-on-mac-pytorch-mps-mlx
new activity 2 days ago
hugging-science/ripp:Hugging Science is DEAD???
View all activity

Organizations

None yet