Hugging Face's logo
Ed Addario's picture
🏗️ Building on HF

Ed Addario PRO

eaddario
21 9 8
uzvisa's profile picture tymirka's profile picture arman-52's profile picture
·

AI & ML interests

Finding ways to optimize LLMs' inference performance in resource-constrained environments (e.g. commodity hardware, desktops, laptops, mobiles, edge devices, etc.)

Recent Activity

updated a model about 24 hours ago
eaddario/IQ2_K-IQ6_K-Test-Models
posted an update 1 day ago
Experimental global target bits‑per‑weight quantization of IFM/K2-Horizon-7B and IFM/K2-Horizon-MoVA-36B-A4B. 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/K2-Horizon-7B-GGUF https://huggingface.co/eaddario/K2-Horizon-MoVA-36B-A4B-GGUF
updated a model 1 day ago
eaddario/K2-Horizon-7B-GGUF
View all activity

Organizations

Hugging Face Discord Community's profile picture