Hugging Face's logo
Mike Ravkine's picture
🤝 Open to Collab

Mike Ravkine PRO

mike-ravkine
49 29 703
Quazim0t0's profile picture IniNLP247's profile picture reynaldo22's profile picture
·

AI & ML interests

LLM Research / Development / Evaluation

Recent Activity

liked a model 3 days ago
migtissera/Tess-4.5-27B
liked a model 3 days ago
nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4
reacted to eaddario's post with 🔥 4 days 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
View all activity

Organizations

Blog-explorers's profile picture