ddh0

ddh0

·

ddh0

AI & ML interests

None yet

Recent Activity

liked a Space about 18 hours ago

mlabonne/chessfly

liked a model about 20 hours ago

mlabonne/chessfly

reacted to eaddario's post with ❤️ 4 days ago

Experimental global target bits‑per‑weight quantization of **XHToken/Spark-X2.5-1.7B** and **XHToken/Spark-X2.5-4B**. 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/Spark-X2.5-1.7B-GGUF https://huggingface.co/eaddario/Spark-X2.5-4B-GGUF

View all activity

Organizations

ddh0 's datasets

None public yet