Instructions to use PrevonFounder/prevon-pulse-mk2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PrevonFounder/prevon-pulse-mk2 with Transformers:

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("PrevonFounder/prevon-pulse-mk2", device_map="auto")

LiteRT-LM

How to use PrevonFounder/prevon-pulse-mk2 with LiteRT-LM:

# LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM)
# and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter).
# For platform-specific integration guides, please refer to the official developer website:
# https://ai.google.dev/edge/litert-lm

# To try LiteRT-LM, the easiest way is to use our CLI tool.
# 1. Install the LiteRT-LM CLI tool:
pip install -U litert-lm

# 2. Download and run this model locally:
# See: https://ai.google.dev/edge/litert-lm/cli
# A single .litertlm file in the repo is picked automatically; otherwise the CLI asks which one to run
# (or pass its name right after the repo id).
litert-lm run \
  --from-huggingface-repo=PrevonFounder/prevon-pulse-mk2 \
  --prompt="Write me a poem"

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use PrevonFounder/prevon-pulse-mk2 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 PrevonFounder/prevon-pulse-mk2:Q8_0
# Run inference directly in the terminal:
llama cli -hf PrevonFounder/prevon-pulse-mk2:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf PrevonFounder/prevon-pulse-mk2:Q8_0
# Run inference directly in the terminal:
llama cli -hf PrevonFounder/prevon-pulse-mk2: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 PrevonFounder/prevon-pulse-mk2:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf PrevonFounder/prevon-pulse-mk2: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 PrevonFounder/prevon-pulse-mk2:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf PrevonFounder/prevon-pulse-mk2:Q8_0

Use Docker

docker model run hf.co/PrevonFounder/prevon-pulse-mk2:Q8_0

LM Studio
Jan
Ollama
How to use PrevonFounder/prevon-pulse-mk2 with Ollama:
```
ollama run hf.co/PrevonFounder/prevon-pulse-mk2:Q8_0
```
Unsloth Desktop

How to use PrevonFounder/prevon-pulse-mk2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PrevonFounder/prevon-pulse-mk2:Q8_0

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": "PrevonFounder/prevon-pulse-mk2:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use PrevonFounder/prevon-pulse-mk2 with Docker Model Runner:
```
docker model run hf.co/PrevonFounder/prevon-pulse-mk2:Q8_0
```

Lemonade

How to use PrevonFounder/prevon-pulse-mk2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull PrevonFounder/prevon-pulse-mk2:Q8_0

Run and chat with the model

lemonade run user.prevon-pulse-mk2-Q8_0

List all available models

lemonade list

Hermes Agent

How to use PrevonFounder/prevon-pulse-mk2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PrevonFounder/prevon-pulse-mk2: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 PrevonFounder/prevon-pulse-mk2:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use PrevonFounder/prevon-pulse-mk2 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf PrevonFounder/prevon-pulse-mk2: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 "PrevonFounder/prevon-pulse-mk2: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"

Prevon Pulse MK2

Prevon Pulse is a 270M-parameter fine-tune of FunctionGemma that picks an app action and fills in its arguments for the Prevon notes app, entirely on device. It is trained to read the tool menu it is given (renamed, masked and shuffled tools), to answer NoMatchingAction when nothing fits, and to stop on its own after one call.

FunctionGemma is provided under and subject to the Gemma Terms of Use found at ai.google.dev/gemma/terms

Files

file	for
`prevon-pulse-mk2.litertlm`	LiteRT-LM: Android, iOS, Apple Silicon Mac, Windows
`prevon-pulse-mk2-Q8_0.gguf`	llama.cpp: Intel Mac
`safetensors/`	bf16 Hugging Face weights, tokenizer and config (source of the two files above)
`training/`	run settings, data hash and loss curve
`SHA256SUMS.txt`	checksums of every file

Training

Full fine-tune of google/functiongemma-270m-it, 1 epoch over 140,945 rows (49 tools, 10.8% refusals, both prompt formats), learning rate 1.5e-5, effective batch 64, loss on the answer tokens only, best checkpoint kept. Final eval loss 0.0499. See training/run_manifest.json.

Evaluation

See eval/ and the table below (filled in from the real3 held-out test after scoring).

Use and limits

Built for the Prevon app's own prompt format; it is not a general chat model. Use is subject to the Gemma Terms of Use and Prohibited Use Policy (https://ai.google.dev/gemma/terms, https://ai.google.dev/gemma/prohibited_use_policy).

Downloads last month: 27

GGUF

Model size

0.3B params

Architecture

gemma3

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for PrevonFounder/prevon-pulse-mk2

Base model

google/functiongemma-270m-it

Quantized

(61)

this model