Statefull AI Time Based Neuronal Network
🧠
1
Neuronal networks now live in time
poe
wop
AI & ML interests
AI research
AGI
Recent Activity
liked
a Space
about 15 hours ago
wop/Statefull-AI-time-based-neuronal-network
updated
a Space
about 15 hours ago
wop/Statefull-AI-time-based-neuronal-network
published
a Space
about 15 hours ago
wop/Statefull-AI-time-based-neuronal-network
Organizations
liked
a
Space
about 15 hours ago
updated
a
Space
about 15 hours ago
published
a
Space
about 15 hours ago
liked
a
dataset
about 16 hours ago
liked
a
Space
about 16 hours ago
liked
a
model
about 16 hours ago
liked
a
model
about 17 hours ago
liked
a
Space
5 days ago
liked
a
model
5 days ago
liked
a
Space
6 days ago
liked
a
model
7 days ago
liked
a
Space
10 days ago
liked
a
dataset
10 days ago
liked
a
Space
12 days ago
liked
a
model
14 days ago
reacted to
eaddario's
post with ❤️
25 days ago
Post
2104
Experimental global target bits‑per‑weight quantization of ServiceNow-AI/Apriel-1.6-15b-Thinker and zai-org/GLM-4.6V-Flash
Unlike standard llama.cpp quantizations that rely on fixed type heuristics (e.g., Q4_K_M), the Target BPW approach optimizes per-tensor precision where it matters the most, and produces high quality models that meet a precise global file 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, MMLU, etc.) and methodology in the models' cards
eaddario/Apriel-1.6-15b-Thinker-GGUF
eaddario/GLM-4.6V-Flash-GGUF
Unlike standard llama.cpp quantizations that rely on fixed type heuristics (e.g., Q4_K_M), the Target BPW approach optimizes per-tensor precision where it matters the most, and produces high quality models that meet a precise global file 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, MMLU, etc.) and methodology in the models' cards
eaddario/Apriel-1.6-15b-Thinker-GGUF
eaddario/GLM-4.6V-Flash-GGUF
updated
a
model
about 1 month ago
liked
a
Space
about 1 month ago