Instructions to use shreyansh12183/Vigyan-1.5B-4x-MoE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use shreyansh12183/Vigyan-1.5B-4x-MoE 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 shreyansh12183/Vigyan-1.5B-4x-MoE:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf shreyansh12183/Vigyan-1.5B-4x-MoE:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf shreyansh12183/Vigyan-1.5B-4x-MoE:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf shreyansh12183/Vigyan-1.5B-4x-MoE:Q4_K_M

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 shreyansh12183/Vigyan-1.5B-4x-MoE:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf shreyansh12183/Vigyan-1.5B-4x-MoE:Q4_K_M

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 shreyansh12183/Vigyan-1.5B-4x-MoE:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf shreyansh12183/Vigyan-1.5B-4x-MoE:Q4_K_M

Use Docker

docker model run hf.co/shreyansh12183/Vigyan-1.5B-4x-MoE:Q4_K_M

LM Studio
Jan

vLLM

How to use shreyansh12183/Vigyan-1.5B-4x-MoE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shreyansh12183/Vigyan-1.5B-4x-MoE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shreyansh12183/Vigyan-1.5B-4x-MoE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shreyansh12183/Vigyan-1.5B-4x-MoE:Q4_K_M

Ollama
How to use shreyansh12183/Vigyan-1.5B-4x-MoE with Ollama:
```
ollama run hf.co/shreyansh12183/Vigyan-1.5B-4x-MoE:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use shreyansh12183/Vigyan-1.5B-4x-MoE with Docker Model Runner:
```
docker model run hf.co/shreyansh12183/Vigyan-1.5B-4x-MoE:Q4_K_M
```

Lemonade

How to use shreyansh12183/Vigyan-1.5B-4x-MoE with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull shreyansh12183/Vigyan-1.5B-4x-MoE:Q4_K_M

Run and chat with the model

lemonade run user.Vigyan-1.5B-4x-MoE-Q4_K_M

List all available models

lemonade list

Atomic Chat

🧪 Vigyan 1.5B 4× MoE (Sparse Mixture of Experts)

Classification: Experimental Research Artifact / Compact Edge MoE
Architecture Target: 4-Expert Sparse MoE with Top-1 Active Routing
Base Model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Research Lab: Vigyan AI Sovereign Initiative

📌 1. Executive Summary & Research Context

Vigyan-1.5B 4× MoE is an experimental Sparse Mixture of Experts model upcycled from 4 specialized domain LoRA adapters (Science, Technology, Engineering, Mathematics).

It was assembled to evaluate whether post-hoc expert stitching on compact language models ($\le 3\text{B}$) can deliver multi-domain specialization at single-expert inference latency with a sub-1GB RAM footprint.

A pre-quantized standalone GGUF (vigyan-1.5b-4x-moe.Q4_K_M.gguf) is available directly within this repository for instantaneous local execution on CPU or mobile.

🚀 1-Click Interactive Google Colab Demo

Test this model on Google Colab with an embedded Gradio chat interface:

📐 2. Architectural Blueprint

Base Foundation: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
Active Routing: Top-1 active expert per token + shared residual STEM anchor.
Assembled Experts:
- shreyansh12183/vigyan-1.5b-adapter-science
- shreyansh12183/vigyan-1.5b-adapter-technology
- shreyansh12183/vigyan-1.5b-adapter-engineering
- shreyansh12183/vigyan-1.5b-adapter-mathematics
Gating Mechanism: gate_mode: hidden with contrasting negative prompt calibration.

📊 3. Empirical Benchmark Observations

Entropy Score: Observed gating logit entropy $\approx 1.1152$, demonstrating router domain sensitivity.
Inference Velocity: Evaluated at $\approx 16-22\text{ tokens/second}$ on consumer AMD Ryzen 5 CPU.
Failure Modes Identified:
1. Delimiter Blindness: Without general conversational anchor replay during adapter training, the model degrades into token echo loops when receiving general chat greetings.
2. Attractor Collapse: Due to uncoordinated expert state representations, consecutive tokens routed across disparate experts trigger representation collapse.

🔮 4. Future Roadmap

Our primary production focus has transitioned to Allen AI's native OLMoE-1B-7B (64 natively pretrained experts with auxiliary load-balancing loss). This checkpoint serves as foundational reference data for the Post-Hoc Upcycling Fragility Theorem.

📜 License & Sovereign Attribution

Released under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license.

✅ Permitted Free Use:

Academic research, university coursework, student study, and personal experimentation.

🚫 Commercial Restrictions:

Any commercial deployment, paid SaaS API, commercial tutoring platform, or enterprise wrapper requires an explicit commercial license.
Founder & Chief Architect: Shreyansh Singh
Organization: Vigyan AI / ExperimentLab.in

📜 Academic Research Paper & Citation

This architecture is formally documented and validated in the Vigyan AI Technical Paper Series (Vol 01):

Paper Title: Sparse Mixture-of-Experts (MoE) Upcycling and Router Stabilization
Author: Shreyansh Singh (Founder & Lead Researcher, Vigyan AI / ExperimentLab.in)
Dataset & LaTeX Sources: 🤗 HuggingFace Paper Hub
Interactive Kaggle Dataset: 📦 Kaggle Paper
GitHub Repository: 🐙 vigyan-ai-journey-docs

@article{singh2026moe},
  title   = {Sparse Mixture-of-Experts (MoE) Upcycling and Router Stabilization},
  author  = {Singh, Shreyansh},
  journal = {Vigyan AI Technical Whitepaper Series},
  year    = {2026},
  publisher = {ExperimentLab.in},
  url     = {https://huggingface.co/datasets/shreyansh12183/vigyan-ai-research-papers}
}

Downloads last month: 1,201

Safetensors

Model size

6B params

Tensor type

BF16

Model tree for shreyansh12183/Vigyan-1.5B-4x-MoE

Base model

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

Quantized

(274)

this model

Quantizations

1 model

shreyansh12183
/

Vigyan-1.5B-4x-MoE