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

Libraries

How to use PrevonFounder/prevon-pulse with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PrevonFounder/prevon-pulse")
model = AutoModelForCausalLM.from_pretrained("PrevonFounder/prevon-pulse", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

LiteRT-LM

How to use PrevonFounder/prevon-pulse 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 \
  --prompt="Write me a poem"

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PrevonFounder/prevon-pulse with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/PrevonFounder/prevon-pulse

SGLang

How to use PrevonFounder/prevon-pulse 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 "PrevonFounder/prevon-pulse" \
    --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": "PrevonFounder/prevon-pulse",
		"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 "PrevonFounder/prevon-pulse" \
        --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": "PrevonFounder/prevon-pulse",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Prevon Pulse (first release)

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.

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

This model is a modified version of Google's FunctionGemma (google/functiongemma-270m-it). It was changed by a full fine-tune of all weights on Prevon's own training data (see Training). It is a Model Derivative under the Gemma Terms of Use, which apply in full; Prevon adds a short set of terms on top (see License).

Files

file	for
`prevon-pulse.litertlm`	LiteRT-LM: Android, iOS, Apple Silicon Mac, Windows (this is the file the Prevon app downloads)
`model.safetensors`, `config.json`, `generation_config.json`, `tokenizer.json`, `tokenizer_config.json`, `chat_template.jinja`	Hugging Face weights, tokenizer and config (source of the `.litertlm`)

Training

Full fine-tune of google/functiongemma-270m-it on Prevon's own training data.

Superseded

Newer, better-scored releases exist: Prevon Pulse MK4 and MK2. This first release is kept because existing app builds still list it.

Use and limits

Built for the Prevon app's own prompt format; it is not a general chat model. Outputs can be wrong; review any action before relying on it. 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).

License

Gemma Terms of Use (ai.google.dev/gemma/terms) and Prohibited Use Policy (ai.google.dev/gemma/prohibited_use_policy) apply in full. Prevon adds a short set of terms: see PREVON_MODEL_TERMS.md. Short version: free for people, schools, researchers and non-profits; companies and anything that makes money need Prevon's written permission; competitors are never covered; rename it if you change it.

Downloads last month: 650

Safetensors

Model size

0.3B params

Tensor type

BF16

Model tree for PrevonFounder/prevon-pulse

Base model

google/functiongemma-270m-it

Finetuned

(480)

this model