ram1234598766/ Cesium2

6 Downloads Updated yesterday

ollama run ram1234598766/Cesium2

curl http://localhost:11434/api/chat \
  -d '{
    "model": "ram1234598766/Cesium2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='ram1234598766/Cesium2',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'ram1234598766/Cesium2',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

View all →

Name

1 model

Size / Usage

Context

Input

Cesium2:latest

3.1GB · 32K context window · Text · yesterday

Cesium2:latest

3.1GB

32K

Text

Readme

Cesium2 — MORPH-AI v6

Modular Orchestrated Reasoning with Pattern-adaptive Hot-swappable skills

Fine-tuned Qwen2.5-1.5B-Instruct with 14 novel subsystems — dynamic MoE expert expansion, Mixture-of-Depths layer skipping, multi-head chain-of-thought reasoning, and a plugin architecture. Trained free on a Kaggle P100 in ~30 minutes.

Run

ollama run ram1234598766/Cesium2

Links

🤗 Weights & full model card: https://huggingface.co/ram1234598766/Cesium2
🧩 VS Code extension (animated chat UI): https://open-vsx.org/extension/ram1234598766/morph-ai-cesium2
💻 Source code: https://github.com/ram1234598766-dotcom/Cesium2
📦 Direct .vsix download: https://github.com/ram1234598766-dotcom/Cesium2/releases/latest

Capabilities

Step-by-step reasoning & problem solving
Code generation and debugging
Mathematical calculations
32K context window
Streaming responses at ~14 tok/s on CPU

Parameters

Parameter	Value
Temperature	0.7
Top P	0.9
Top K	50
Context	8192

License

Apache-2.0