Hugging Face's logo
Patrick Devaney's picture

Patrick Devaney

patrickbdevaney
7 15 335
DeepRetailMohan's profile picture Strongzero0's profile picture Rebis's profile picture
·

AI & ML interests

mamba s4, mixtral 8x-7b, candle, pytorch

Recent Activity

reacted to eaddario's post with 🔥 4 days ago
Experimental global target bits‑per‑weight quantization of openbmb/MiniCPM5-1B and openbmb/MiniCPM5-2B. Unlike standard llama.cpp quantization that rely on fixed type heuristics (e.g., Q4_K_M), the Target BPW approach automatically optimizes per-tensor precision where it matters the most, and produces high quality models that meet a precise global size target. Key Advantages: - VRAM Maximization: Can generate high quality models sized exactly to fit hardware constraints (e.g., fitting the model into exactly 24GB VRAM). - Data-Driven Precision: Quantization mix is determined by actual weight error sensitivity rather than hardcoded rules, often yielding better PPL/KLD size trade-offs. Full benchmarks (PPL, KLD, ARC, GPQA, MMLU, etc.) and methodology in the model's card. https://huggingface.co/eaddario/MiniCPM5-1B-GGUF https://huggingface.co/eaddario/MiniCPM5-2B-GGUF
liked a model 10 days ago
PixelML/Qwen3.8-Flash-Next-NVFP4-DFlash
liked a model 10 days ago
nerkyor/Qwen3.8-27B-EfficientThink-Uncensored-K3-Opus5-Grok4.6-GPT5.6Sol-SFT-SimPO-DFlash2
View all activity

Organizations

rpg-collaboration's profile picture LeRobot Worldwide Hackathon's profile picture