Cesium2-v7-GGUF

Cesium2 v7 — GGUF (Q8_0)

MORPH-AI v7 (Cesium2) — a fine-tuned Qwen2.5-1.5B-Instruct with refreshed August-2026 world knowledge, persona training, and a modular skill system (code · creative · data · math · reasoning · translate). Trained and shipped entirely on free Kaggle GPUs.

Quick start

ollama pull ram1234598766/cesium2-v7
ollama run ram1234598766/cesium2-v7 "What is GPT-5.6?"

Or load this file directly in llama.cpp / LM Studio / Jan.

Model facts

Links

⚡ What's new (August 2026)

• 🌐 Web-connected Playground — toggle Live web search (keyless DuckDuckGo) and URL reading/scraping: grounded answers with cited sources

• 💾 Sessions stored per account — full sessions API (GET/POST /v1/sessions), chat history follows you across devices

• 🔑 Two key types — cs2-pg-… Playground keys (browser chat) and cs2-sk-… Agent keys (Claude Code, OpenAI SDK, curl), each with its own usage analytics

• 🧰 Tools API — POST /v1/tools/search (live web), POST /v1/tools/read (scrape), plus Wikipedia, GitHub, Hugging Face, arXiv, exact-math and clock connectors via POST /v1/tools/use

• ⌨️ VS Code extension 1.1.0 — inline completions, web-grounded chat, cloud sessions, 14 coding commands, slick animations

• ⚡ Faster serving — models pre-warmed and pinned in RAM, consistent 8k context, 60s search cache, 8-way parallel

• 🌐 Live API & key portal: https://ram1234598766-soverign-cognitive-quantum-space.hf.space (sign in with Google → free personal key, works with Claude Code)

• 💻 Source & full pipeline: https://github.com/ram1234598766-dotcom/cesium2

• 👁 Vision sibling model: https://huggingface.co/ram1234598766/Cesium2-vision-GGUF

• 🧩 VS Code assistant powered by this model: https://open-vsx.org/extension/ram1234598766/cesium2-ai

• 🫥 Ollama page: https://ollama.com/ram1234598766/cesium2-v7

Usage notes

The model has a training cutoff (Aug 2026) baked into its system prompt — it will decline to guess about events after that unless given a [LIVE CONTEXT] block.

---

Author: Mrityunjay K — trained, fine-tuned, quantized and shipped end-to-end on free Kaggle GPUs. Live API: https://ram1234598766-soverign-cognitive-quantum-space.hf.space