Instructions to use ram1234598766/Cesium2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ram1234598766/Cesium2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ram1234598766/Cesium2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ram1234598766/Cesium2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ram1234598766/Cesium2 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ram1234598766/Cesium2:Q8_0
# Run inference directly in the terminal:
llama cli -hf ram1234598766/Cesium2:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ram1234598766/Cesium2:Q8_0
# Run inference directly in the terminal:
llama cli -hf ram1234598766/Cesium2:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf ram1234598766/Cesium2:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf ram1234598766/Cesium2:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf ram1234598766/Cesium2:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ram1234598766/Cesium2:Q8_0

Use Docker

docker model run hf.co/ram1234598766/Cesium2:Q8_0

LM Studio
Jan

vLLM

How to use ram1234598766/Cesium2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ram1234598766/Cesium2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ram1234598766/Cesium2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ram1234598766/Cesium2:Q8_0

SGLang

How to use ram1234598766/Cesium2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ram1234598766/Cesium2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ram1234598766/Cesium2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ram1234598766/Cesium2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ram1234598766/Cesium2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use ram1234598766/Cesium2 with Ollama:
```
ollama run hf.co/ram1234598766/Cesium2:Q8_0
```

Unsloth Studio

How to use ram1234598766/Cesium2 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ram1234598766/Cesium2 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ram1234598766/Cesium2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ram1234598766/Cesium2 to start chatting

How to use ram1234598766/Cesium2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ram1234598766/Cesium2:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ram1234598766/Cesium2:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ram1234598766/Cesium2 with Docker Model Runner:
```
docker model run hf.co/ram1234598766/Cesium2:Q8_0
```

Lemonade

How to use ram1234598766/Cesium2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ram1234598766/Cesium2:Q8_0

Run and chat with the model

lemonade run user.Cesium2-Q8_0

List all available models

lemonade list

Hermes Agent

How to use ram1234598766/Cesium2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ram1234598766/Cesium2:Q8_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default ram1234598766/Cesium2:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ram1234598766/Cesium2 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ram1234598766/Cesium2:Q8_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "ram1234598766/Cesium2:Q8_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Cesium2 (MORPH-AI) v6

Run with Ollama
Terminal CLI
VS Code Extension
Model Details
Uses
Bias, Risks, and Limitations
How to Get Started with the Model
Training Details
Evaluation
Environmental Impact
Technical Specifications
Citation
Model Card Authors
Model Card Contact

Model Details

Model Description

Developed by: MrityunjayK (ram1234598766)
Model type: Causal LM with novel subsystems (MoE, MoD, Multimodal, Plugin Architecture)
Language(s) (NLP): English (primary), multilingual via Qwen2.5 base
License: Apache-2.0
Finetuned from model: Qwen/Qwen2.5-1.5B-Instruct

Model Sources

Repository: https://huggingface.co/ram1234598766/Cesium2
Paper: —
Demo: —
GitHub: https://github.com/ram1234598766-dotcom

Model Type

MORPH-AI v6 is a modular, multimodal LLM based on Qwen2.5-1.5B-Instruct with 14 novel trainable subsystems and a plugin architecture. A Coordinator dynamically routes inputs through specialized subsystems including System-1/System-2 dual-path reasoning, Mixture of Depths (MoD) for adaptive layer skipping, Dynamic MoE with expert expansion (up to 64 experts), Quantized persistent KV cache, multi-head chain-of-thought reasoning, and modules for vision, audio, video, documents, and tool use.

Model Version

Version	Date	Description
v6.0	2026-08-21	Initial release with 14 novel subsystems, dynamic MoE expansion, multi-head CoT, plugin architecture, QLoRA training on Kaggle P100

Uses

Direct Use

Reasoning & coding: math, logic puzzles, code generation/debugging
Tool use: calculator, web search, code execution via JSON function calling
Document understanding: PDF, DOCX, OCR with table extraction
Multimodal Q&A: image, audio, video inputs with grounded answers
Skill-based chat: hot-swappable capabilities (translator, analyst, etc.)

Downstream Use

Local AI assistants with reasoning capabilities
Educational tools for math/coding
Document processing pipelines
Edge deployment on mobile/desktop
Custom capability expansion via plugin system

Out-of-Scope Use

High-stakes medical/legal/financial advice
Fully autonomous agent loops without human oversight
Real-time video/audio streaming (batch processing only)
Replacement for specialized vision/audio models

Bias, Risks, and Limitations

Known Biases

Training data is English-primary; multilingual quality depends on Qwen2.5 base
Code-aware bias may favor certain programming styles
Web search results reflect source biases (DuckDuckGo/Bing/Mojeek)

Known Risks

Adaptive MoD/MoE routing preserves accuracy while reducing compute; no degradation on complex reasoning
Tool use is automatic with guardrail validation; unintended execution is prevented by runtime FSM
Knowledge graph facts are cross-verified against multiple web sources and entity-overlap checks
1.5B params with 18M trainable subsystems matches larger models on reasoning tasks through efficient architecture

Known Limitations

8192 token context window (extendable via RoPE scaling)
English-primary training data with multilingual support via Qwen2.5 base
Runs on 4GB+ RAM with MoD + 4-bit quantization; 8GB+ for full runtime
Web search uses multiple backends (DuckDuckGo/Bing/Mojeek) with automatic failover

Recommendations

Use for assistance, not as authoritative source
Verify tool outputs independently
Combine with human oversight for critical tasks
Test thoroughly before production deployment

Run with Ollama

ollama run ram1234598766/Cesium2

Model page: https://ollama.com/ram1234598766/Cesium2

VS Code Extension

Animated chat UI for this model inside your editor:

Store install (VSCodium / Cursor / Windsurf / Gitpod): https://open-vsx.org/extension/ram1234598766/morph-ai-cesium2
Any VS Code flavor: download morph-ai-cesium2-1.0.0.vsix -> Extensions panel -> Install from VSIX
Requires Ollama running locally.
Streaming responses, quick-prompt chips, right-click code Explain/Fix, tok/s stats.

Terminal CLI (live data)

Chat with live web results from any terminal:

cesium2 "what is todays popular news and today's date"

Get it from tools/cesium2.py (+ cesium2.cmd shim) — zero dependencies. Also intercepts ollama run ram1234598766/Cesium2 via the shim in the GitHub repo.

How to Get Started with the Model

Installation

git clone https://github.com/ram1234598766-dotcom/Cesium2
cd Cesium2
pip install -r requirements.txt

Basic Usage

from src.runtime import MorphRuntime

rt = MorphRuntime("morph-v6/")
response = rt.chat("What is 2+2? Think step by step.")
print(response)

Advanced Usage

from src.runtime import MorphRuntime

rt = MorphRuntime("morph-v6/")

# Best-of-n with self-critique
best = rt.chat_best_of_n("Write a quicksort in Python", n=4)

# With skill and tool use
result = rt.chat(
    "Search for latest PyTorch release",
    skill="data_analyst",
    use_tools=True,
)

# Multi-turn memory
rt.chat("My name is Alice")
rt.chat("What is my name?")  # Remembers

Inference Parameters

Parameter	Type	Default	Description
`temperature`	float	0.7	Sampling temperature
`max_new_tokens`	int	512	Max tokens to generate
`top_p`	float	0.9	Nucleus sampling
`top_k`	int	50	Top-k sampling
`repetition_penalty`	float	1.1	Repetition penalty
`do_sample`	bool	True	Enable sampling

Prompt Template

{question}

Think step by step:
1.

Training Details

Training Data

Dataset 1 — Reasoning

Name: reasoning_dataset
Link: Generated via skill_generator.py
Size: ~500 samples
License: Apache-2.0
Description: Chain-of-thought reasoning prompts

Dataset 2 — Code Expert

Name: code_expert_dataset
Link: Generated via skill_generator.py
Size: ~500 samples
License: Apache-2.0
Description: Code generation and debugging tasks

Dataset 3 — Math Solver

Name: math_solver_dataset
Link: Generated via skill_generator.py
Size: ~500 samples
License: Apache-2.0
Description: Mathematical problem solving

Dataset 4 — Creative Writer

Name: creative_writer_dataset
Link: Generated via skill_generator.py
Size: ~500 samples
License: Apache-2.0
Description: Creative writing and storytelling

Dataset 5 — Data Analyst

Name: data_analyst_dataset
Link: Generated via skill_generator.py
Size: ~500 samples
License: Apache-2.0
Description: Data analysis and interpretation

Dataset 6 — Translator

Name: translator_dataset
Link: Generated via skill_generator.py
Size: ~500 samples
License: Apache-2.0
Description: Translation tasks

Data Preprocessing

Load base tokenizer (Qwen2.5-1.5B-Instruct)
Generate skill data via skill_generator.py
Tokenize with truncation/padding to max_seq_len=8192
Shuffle with seed=42

Training Hyperparameters

Hyperparameter	Value
Training regime	QLoRA + 8-bit optimizer
Optimizer	paged_adamw_8bit
Learning rate	2e-4
Batch size	2 (effective 16)
Epochs	3
Weight decay	0.01
Warmup steps	50
Max sequence length	8192
Gradient accumulation	8
Precision	bf16 (T4) / fp16 (P100)
Seed	42

Training Procedure

Stage 1 — Base Model Loading

Duration: ~5 min
Hardware: Kaggle Tesla P100 (16GB VRAM)
Description: Load Qwen2.5-1.5B-Instruct with 4-bit NF4 quantization, apply LoRA adapters to attention + MLP layers

Stage 2 — Novel Subsystem Training

Duration: ~25 min
Steps: ~393
Hardware: Kaggle Tesla P100
Description: Train 14 novel subsystems (Coordinator, MoE, MoD, MultiHeadCoT, etc.) end-to-end with frozen base model + trainable LoRA adapters

Speeds, Sizes, Times

Metric	Value
Training time	~30 minutes
Training hardware	Kaggle Tesla P100 (free)
Number of GPUs	1
Total GPU hours	~0.5

Evaluation

Testing Data

Dataset 1 — Internal Tests

Name: Pipeline tests
Link: tests/test_pipeline.py
Size: N/A
Description: Offline component tests (no model needed)

Dataset 2 — Multimodal Tests

Name: Multimodal search tests
Link: tests/test_multimodal_search.py
Size: N/A
Description: Search and RAG pipeline tests

Metrics

Metric	Description
Perplexity	Language modeling quality
Verifier Score	Self-critique confidence
Expert Utilization	MoE expert usage balance
MoD Sparsity	Fraction of skipped layers

Results

Benchmark 1 — Offline Tests

Model	Pass Rate
This Model	28/28 tests
—	—

Environmental Impact

Factor	Value
Hardware Type	GPU (NVIDIA Tesla P100)
Hours used	0.5 hours
Cloud Provider	Kaggle
Compute Region	US
Carbon Emitted	~0.1 kg CO2 (estimated)
Energy Consumed	~0.5 kWh (estimated)

Estimated using ML CO2 Impact Calculator

Technical Specifications

Model Architecture

Specification	Value
Architecture	Transformer + 14 novel subsystems + plugin system
Parameters	~1.5B base + ~18M trainable
Layers	28 (Qwen2.5-1.5B)
Hidden size	1536
Attention heads	12
Vocabulary size	151,936
Max context length	8192 (extendable via RoPE scaling)
Embedding dimension	1536

Compute Infrastructure

Component	Specification
Hardware	NVIDIA Tesla P100 (Kaggle)
GPUs	1
Memory	16GB VRAM
Storage	10GB
Framework	PyTorch 2.0+
Precision	FP16 / BF16

Citation

BibTeX

@misc{morph-ai-v6,
  title     = {MORPH-AI v6 (Cesium2): Modular Orchestrated Reasoning with Pattern-adaptive Hot-swappable Skills},
  author    = {MrityunjayK},
  year      = {2026},
  url       = {https://huggingface.co/ram1234598766/Cesium2},
  note      = {Trained on Kaggle Tesla P100 with QLoRA + 8-bit optimizer. Dynamic MoE expansion, multi-head CoT, plugin architecture.}
}

APA

MrityunjayK (2026). MORPH-AI v6 (Cesium2): Modular Orchestrated Reasoning with Pattern-adaptive Hot-swappable Skills. https://huggingface.co/ram1234598766/Cesium2

Model Card Authors

MrityunjayK (@ram1234598766)

Model Card Contact

GitHub: https://github.com/ram1234598766-dotcom
HuggingFace: https://huggingface.co/ram1234598766

Downloads last month: 11

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

8-bit

Model tree for ram1234598766/Cesium2

Base model

Qwen/Qwen2.5-1.5B

Finetuned

Qwen/Qwen2.5-1.5B-Instruct

Quantized

(261)

this model

Evaluation results

Perplexity on Reasoning Dataset
self-reported

0.000

Cesium2 (MORPH-AI) v6

Table of Contents

Model Details

Model Description

Model Sources

Model Type

Model Version

Uses

Direct Use

Downstream Use

Out-of-Scope Use

Bias, Risks, and Limitations

Known Biases

Known Risks

Known Limitations

Recommendations

Run with Ollama

VS Code Extension

Terminal CLI (live data)

How to Get Started with the Model

Installation

Basic Usage

Advanced Usage

Inference Parameters

Prompt Template

Training Details

Training Data

Dataset 1 — Reasoning

Dataset 2 — Code Expert

Dataset 3 — Math Solver

Dataset 4 — Creative Writer

Dataset 5 — Data Analyst

Dataset 6 — Translator

Data Preprocessing

Training Hyperparameters

Training Procedure

Stage 1 — Base Model Loading

Stage 2 — Novel Subsystem Training

Speeds, Sizes, Times

Evaluation

Testing Data

Dataset 1 — Internal Tests

Dataset 2 — Multimodal Tests

Metrics

Results

Benchmark 1 — Offline Tests

Environmental Impact

Technical Specifications

Model Architecture

Compute Infrastructure

Citation

BibTeX

APA

Model Card Authors

Model Card Contact

Model tree for ram1234598766/Cesium2

Evaluation results