Hugging Face's logo
Konstantin Grabko's picture

Konstantin Grabko PRO

kgrabko
17 6 20
Jcfunk's profile picture PhysiQuanty's profile picture 12sri's profile picture
·
https://huggingface.co/CMSManhattan

AI & ML interests

Konstantin Grabko | CEO & CTO CMSManhattan inc . ----------------------------------- Follow for final releases on company page

Recent Activity

published an article about 14 hours ago
JiRack Ultra blew up the Hugging Face charts
published an article about 14 hours ago
Almost Opus 4.6 Max quality with JiRack DeltaNet 27B — but it runs on your PC
posted an update about 14 hours ago
Ternary Transformers & Micro-Agent Architecture CMSManhattan : Center Business Solutions Inc. JiRack — Ternary Transformers & Micro-Agent Architecture We build highly efficient large language models using 1.58-bit ternary weights {-1, 0, 1} for extreme compression and fast CPU/GPU inference. Core focus: JiRack Ternary Transformer Architecture — fresh Qwen base, trained on DeepSeek-style datasets, optimized for fast CPU inference (MIT License) JiRack Micro-Agent Deployment — specialized small models + smart router for low-cost agentic systems Production-ready ONNX Runtime & Docker inference stacks Public Models ModelSizeStatusJiRackUltra series (1B / 7B / 14B / 32B)—Released https://huggingface.co/CMSManhattan/JiRackUltra_1b https://huggingface.co/CMSManhattan/JiRackUltra_7b https://huggingface.co/CMSManhattan/JiRackUltra_14b https://huggingface.co/CMSManhattan/JiRackUltra_32b JiRackTernary series1B → 10B+ReleasedJiRackPrecisionTokenizer—Released Mission Democratize frontier-scale language models through extreme efficiency. Train and run powerful models on accessible hardware without sacrificing quality. Solved issues Benefits of JiRack Micro-Agent Architecture: Solves catastrophic forgetting during training by using small, specialized models for each domain, managed by a smart router Enables extremely cheap inference using ternary models Significantly reduces cloud inference costs while maintaining high performance In classical architecture, an expensive model has to search for MCP-agents every time, while JiRack uses a very small model and cheap router for agent tasks, saving big money right from the start Considered one of the best approaches for enterprise AI deployments Hugging Face: https://huggingface.co/CMSManhattan Ollama : https://ollama.com/cmsmanhattan Docker Hub: cmsmanhattan Contact: grabko@cmsmanhattan.com
View all activity

Organizations

Blog-explorers's profile picture Center Business Solutions inc's profile picture