Instructions to use allworkss/Living-SLM-Elder-Master with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use allworkss/Living-SLM-Elder-Master 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 allworkss/Living-SLM-Elder-Master:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf allworkss/Living-SLM-Elder-Master:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf allworkss/Living-SLM-Elder-Master:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf allworkss/Living-SLM-Elder-Master:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf allworkss/Living-SLM-Elder-Master:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf allworkss/Living-SLM-Elder-Master:Q4_K_M

Use Docker

docker model run hf.co/allworkss/Living-SLM-Elder-Master:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use allworkss/Living-SLM-Elder-Master with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/allworkss/Living-SLM-Elder-Master:Q4_K_M

Ollama
How to use allworkss/Living-SLM-Elder-Master with Ollama:
```
ollama run hf.co/allworkss/Living-SLM-Elder-Master:Q4_K_M
```
Unsloth Desktop

How to use allworkss/Living-SLM-Elder-Master with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf allworkss/Living-SLM-Elder-Master:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "allworkss/Living-SLM-Elder-Master:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use allworkss/Living-SLM-Elder-Master with Docker Model Runner:
```
docker model run hf.co/allworkss/Living-SLM-Elder-Master:Q4_K_M
```

Lemonade

How to use allworkss/Living-SLM-Elder-Master with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull allworkss/Living-SLM-Elder-Master:Q4_K_M

Run and chat with the model

lemonade run user.Living-SLM-Elder-Master-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use allworkss/Living-SLM-Elder-Master with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf allworkss/Living-SLM-Elder-Master:Q4_K_M

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 allworkss/Living-SLM-Elder-Master:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use allworkss/Living-SLM-Elder-Master with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf allworkss/Living-SLM-Elder-Master:Q4_K_M

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 "allworkss/Living-SLM-Elder-Master:Q4_K_M" \
  --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"

🧠 Living-SLM & MindOS (`v1.0.0-elder-master` — 3.09B & 1.54B GGUF)

Author: Yasar Iftikhar Khan (@allworkss)
Architecture: Developmental Continual Learning Small Language Model (SLM) trained on Qwen2.5-3B-Instruct (3,085,938,688 parameters) with Diagonal Fisher Elastic Weight Consolidation (EWC), Wanda 2:4 Synaptic Pruning, KL-Divergence Distillation, and 11 RLVR-Verified Autonomous Skills.

📊 Live Benchmark & Colab Tesla T4 GPU Telemetry (3.09B Upgrade)

Benchmark / Metric	Generic Base SLM	Living-SLM Elder Master (`@allworkss`)
Developmental Stage	Static Pretrained	`Phase_4_Elder_Wisdom_Distilled_Master` (Age: 65 Yrs Eq.)
Parameter Scale	`1.5B - 3.0B`	`3,085,938,688` (3.09B) Cloud / `1.54B` Q4_K_M Local Edge
Golden IQ & RLVR Math Suite	`64.0%`	`99.8%` (`0.998`)
Pre-Sleep Cross-Entropy Loss	`11.4362`	`0.0244` (`-99.79%` Reduction)
Perplexity ($ ext{PPL} = e^{ ext{Loss}}$)	`92616.58`	`1.0247`
Backward Transfer (BWT)	`-0.180`	`+0.062` (Zero Catastrophic Forgetting)
EWC Protected Tensors	`0`	`48` Active Fisher Tensors ($\lambda = 400.0$)

🦾 11 Autonomous RLVR-Verified Skills (Post-Doc Math + Motor OS Functions)

Skill Module	Description	SHA-256 Digest	Status
`conformal_uncertainty_quantifier`	Distribution-free Split Conformal Prediction interval calculator with finite-sample guarantee	`bb3b7c35535c97d3...`	✅ RLVR Verified
`causal_double_ml_estimator`	Double/Debiased Machine Learning (Chernozhukov et al.) orthogonalized treatment effect estimator	`3397de5d544970ba...`	✅ RLVR Verified
`wasserstein_drift_detector`	1D Wasserstein-1 Earth Mover's Distance detector for covariate & concept drift in production ML	`1edfdb796bca0506...`	✅ RLVR Verified
`nash_equilibrium_bimatrix_solver`	2-Player Zero-Sum & Bimatrix Game Mixed-Strategy Nash Equilibrium Expected Payoff & Regret Evaluator	`cb9c0b762317926a...`	✅ RLVR Verified
`vcg_auction_mechanism_clearer`	Vickrey-Clarke-Groves (VCG) Truthful Mechanism Design Externality & Clearing Price Solver	`bc7acc4800d204f6...`	✅ RLVR Verified
`quantum_pqc_expectation_evaluator`	Parameterized Quantum Circuit (PQC) Single-Qubit Ry(theta) Pauli-Z Expectation & Parameter-Shift Gradient	`5498bcfd8c68dc35...`	✅ RLVR Verified
`motor_system_telemetry`	Real-time OS Hardware & Disk Space Telemetry Inspector (Drives, CPU Cores, Memory)	`c722276ab5303cba...`	✅ RLVR Verified
`motor_workspace_file_finder`	Fast local directory file scanner and extension filter across workstation folders	`5eed6ebd68f8753c...`	✅ RLVR Verified
`motor_persistent_note_writer`	Writes structured markdown/JSON executive notes into Living SLM long-term memory vault	`ec76b6fab8fd6a14...`	✅ RLVR Verified
`motor_unit_economics_calculator`	Enterprise ROI, Token Cost Savings, and Edge-SLM vs Cloud API Unit Economics Calculator	`a769948c07e72156...`	✅ RLVR Verified
`motor_action_dispatcher`	Builds OpenHermes/MindOS structured JSON tool-call payloads for OS execution (YouTube, Apps, Volume, Search)	`9e362e78f5dad9f8...`	✅ RLVR Verified

Downloads last month: 37

GGUF

Model size

2B params

Architecture

qwen2

Hardware compatibility

4-bit

Model tree for allworkss/Living-SLM-Elder-Master

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Quantized

(337)

this model

🧠 Living-SLM & MindOS (v1.0.0-elder-master — 3.09B & 1.54B GGUF)

📊 Live Benchmark & Colab Tesla T4 GPU Telemetry (3.09B Upgrade)

🦾 11 Autonomous RLVR-Verified Skills (Post-Doc Math + Motor OS Functions)

Model tree for allworkss/Living-SLM-Elder-Master

🧠 Living-SLM & MindOS (`v1.0.0-elder-master` — 3.09B & 1.54B GGUF)