Instructions to use Lexuselizar/pegasus-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lexuselizar/pegasus-mini with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Lexuselizar/pegasus-mini",
	filename="pegasus-mini-q4.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Lexuselizar/pegasus-mini 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 Lexuselizar/pegasus-mini
# Run inference directly in the terminal:
llama cli -hf Lexuselizar/pegasus-mini

Install from WinGet (Windows)

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

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 Lexuselizar/pegasus-mini
# Run inference directly in the terminal:
./llama-cli -hf Lexuselizar/pegasus-mini

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 Lexuselizar/pegasus-mini
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Lexuselizar/pegasus-mini

Use Docker

docker model run hf.co/Lexuselizar/pegasus-mini

LM Studio
Jan

vLLM

How to use Lexuselizar/pegasus-mini with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Lexuselizar/pegasus-mini

Ollama
How to use Lexuselizar/pegasus-mini with Ollama:
```
ollama run hf.co/Lexuselizar/pegasus-mini
```

Unsloth Studio

How to use Lexuselizar/pegasus-mini 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 Lexuselizar/pegasus-mini 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 Lexuselizar/pegasus-mini to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Lexuselizar/pegasus-mini to start chatting

How to use Lexuselizar/pegasus-mini with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Lexuselizar/pegasus-mini

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": "Lexuselizar/pegasus-mini"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Lexuselizar/pegasus-mini with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Lexuselizar/pegasus-mini

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 Lexuselizar/pegasus-mini

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Lexuselizar/pegasus-mini with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Lexuselizar/pegasus-mini

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 "Lexuselizar/pegasus-mini" \
  --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"

Docker Model Runner
How to use Lexuselizar/pegasus-mini with Docker Model Runner:
```
docker model run hf.co/Lexuselizar/pegasus-mini
```

Lemonade

How to use Lexuselizar/pegasus-mini with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Lexuselizar/pegasus-mini

Run and chat with the model

lemonade run user.pegasus-mini-{{QUANT_TAG}}

List all available models

lemonade list

pegasus-mini / README.md

Lexuselizar

Upload README.md with huggingface_hub

92c7e8e verified 20 days ago

preview code

Raw

History Blame Contribute Delete

5.01 kB

metadata

license: apache-2.0
base_model: Qwen/Qwen2.5-1.5B-Instruct
language:
  - en
  - ru
pipeline_tag: text-generation
tags:
  - gguf
  - qwen2
  - distillation
  - on-device
  - edge
  - local-llm
  - llama-cpp

PegasusLink mini (1.5B, distilled, GGUF)

A small, on-device chat model distilled from Qwen2.5-1.5B-Instruct and shipped as a q4 GGUF so it runs offline in llama.cpp / Ollama / a phone shell / the browser (WebGPU). It is the offline brain of the hybrid PegasusLink app at https://reverseml.online (online → cloud model + web search; offline → this).

Independent / solo project, open beta. Feedback and issues welcome.

What is in this repo vs. what is in the app

Be clear about this, because they are different things:

In this repo: the GGUF weights only — a fine-tuned 1.5B language model. That's it.
In the app (NOT in the weights): the on-device cognitive stack — persistent Kalman attribute-memory, BM25+cosine hybrid RAG, device-to-device attribute merge, and an exact rational null-space chemistry balancer. Those live in the client (app-memory.js / app-chem.js) and wrap any local model; they are not baked into these weights. If you just load this GGUF in llama.cpp, you get the model, not the stack.

So: judge the GGUF here as a 1.5B chat model. The architecture writeup is on the site.

How to run

llama.cpp

./llama-cli -m pegasus-mini-q4.gguf -p "Balance: H2 + O2 -> H2O" -ngl 99

Ollama

printf 'FROM ./pegasus-mini-q4.gguf\nPARAMETER temperature 0\nPARAMETER stop "<|im_end|>"\n' > Modelfile
ollama create pegasus-mini -f Modelfile
ollama run pegasus-mini "What is the pH of a neutral solution at 25 C?"

Phone: load the GGUF in a shell like ChatterUI. Browser: the WebLLM/WebGPU build (q4f16_1) is served from the site — zero install.

Prompt format is Qwen2 ChatML (<|im_start|> / <|im_end|>).

Performance

Measured with Ollama, q4 GGUF, CPU-only (no GPU) on a 4-core AMD EPYC-Genoa VM:

metric	value
eval (generation) rate	~33 tokens/s
prompt eval rate	~64 tokens/s
cold load	~1.4 s

That's CPU-only; on a laptop GPU or via WebGPU in the browser it's faster. The point is it's comfortably interactive on commodity hardware with no accelerator.

Example (temperature 0)

Prompt: Explain what a Kalman filter does in two sentences.

A Kalman filter is an algorithm that uses a combination of measurements and predictions to estimate the state of a system, such as a robot or an aircraft, by updating its estimates based on new information. It does this by using a mathematical model of the system to predict its future state, then comparing those predictions to actual measurements to refine them — it is widely used in robotics, navigation, and signal processing for estimating unknown variables under uncertainty.

Training

Base: Qwen2.5-1.5B-Instruct (Apache-2.0).
Method: QLoRA, nightly, on a single A10G, merged → converted to GGUF (q4).
Data (no raw private conversation):
- seed instruction/QA pairs (incl. Wikipedia-derived factual QA);
- execution-verified coding pairs (each solution is run in a locked-down sandbox against ground-truth tests; only passing ones are kept);
- math solutions distilled from stronger peer models;
- device-bridge pairs that are sanitized (emails/IPs/keys/tokens/long-digit runs scrubbed) and dropped if anything sensitive survives.
Quality gate: before publishing, a fresh build must pass a coding/math/chemistry smoke gate; on failure it is not shipped. Nightly runs that see no new data skip training (no GPU spent).

Intended use

General offline assistant for low-resource / private / edge settings: quick Q&A, coding help, math, deterministic chemistry balancing (via the app), and as a base to distill on your own data.

Out of scope / limitations

It's 1.5B. Offline reasoning is modest — a capable local helper, not a frontier model. Verify anything important.
On some mobile GPUs the driver watchdog (e.g. Adreno on recent Samsung devices) can drop the GPU context on larger kernels; the browser build is tuned around a ~1B stable ceiling with f16 and a reload-from-cache recovery loop.
Autonomous/embedded use: the app has an experimental "device brain" for embedded/autonomous systems. It is an advisory, human-in-the-loop decision-support layer behind a safety license — NOT a certified autopilot. Do not wire a 1.5B model to actuate a real vehicle, drone, or machine as the sole controller. No warranty; you are responsible for legal compliance and any hardware you connect.

License & attribution

Released under Apache-2.0, inheriting from the Qwen2.5-1.5B-Instruct base. Please keep the Qwen attribution when redistributing. The weights are derived via distillation/ fine-tuning of that base.