Instructions to use macmacmacmac/gemma-4-31B-it-litert-lm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use macmacmacmac/gemma-4-31B-it-litert-lm with Transformers:

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

pipe = pipeline("text-generation", model="macmacmacmac/gemma-4-31B-it-litert-lm")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("macmacmacmac/gemma-4-31B-it-litert-lm", device_map="auto")

LiteRT-LM

How to use macmacmacmac/gemma-4-31B-it-litert-lm 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
litert-lm run \
  --from-huggingface-repo=macmacmacmac/gemma-4-31B-it-litert-lm \
  --prompt="Write me a poem"

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use macmacmacmac/gemma-4-31B-it-litert-lm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "macmacmacmac/gemma-4-31B-it-litert-lm"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "macmacmacmac/gemma-4-31B-it-litert-lm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/macmacmacmac/gemma-4-31B-it-litert-lm

SGLang

How to use macmacmacmac/gemma-4-31B-it-litert-lm 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 "macmacmacmac/gemma-4-31B-it-litert-lm" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "macmacmacmac/gemma-4-31B-it-litert-lm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "macmacmacmac/gemma-4-31B-it-litert-lm" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "macmacmacmac/gemma-4-31B-it-litert-lm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use macmacmacmac/gemma-4-31B-it-litert-lm with Docker Model Runner:
```
docker model run hf.co/macmacmacmac/gemma-4-31B-it-litert-lm
```

gemma-4-31B-it-litert-lm / README.md

macmacmacmac

Update README.md

72d6a81 verified 4 months ago

preview code

Raw

History Blame Contribute Delete

3.19 kB

	---
	language:
	- en
	license: gemma
	library_name: transformers
	pipeline_tag: text-generation
	base_model: google/gemma-4-31B-it
	widget:
	- text: "gemma"
	output:
	url: gemma.webp
	tags:
	- text-generation
	- security
	- red-team
	- telemetry
	- local-first
	- safetensors
	- litert-lm
	- dpm
	---

	<div align="center">
	<img src="gemma.webp" width="180px" style="border-radius: 10px; margin-bottom: 20px;">
	<h1>google/gemma-4-31B-it <br><sub>LiteRT-LM Optimized</sub></h1>
	<p><i>Deterministic Projection Memory (DPM) Artifact for Security Telemetry</i></p>
	</div>

	---

	### 🟢 Overview
	This repository contains a specialized LiteRT-LM conversion of `google/gemma-4-31B-it`. It is engineered for local-first DPM//BENCH experiments, specifically targeting long-horizon incident narratives and red-team traces.

	> Objective: Package the base instruction model into a runtime format for deterministic projection memory experiments, ensuring that append-only event logs map to a consistent structured memory surface.

	---

	### 🛠️ Conversion Architecture
	The conversion utilizes the latest LiteRT-LM stack, requiring specific flags to handle the Gemma 4 per-layer embedding structure.

	<details>
	<summary><b>View Conversion Script</b></summary>

	```bash
	python -m litert_torch.generative.export_hf \
	--model /path/to/google/gemma-4-31B-it \
	--output_dir /path/to/out/gemma-4-31B-it-litert-lm \
	--externalize_embedder True \
	--single_token_embedder True \
	--experimental_lightweight_conversion True \
	--bundle_litert_lm True \
	--task text_generation
	```
	</details>

	Critical Flags for Compatibility:
	* --externalize_embedder True: Essential for per-layer embedding paths.
	* --experimental_lightweight_conversion True: Prevents runtime artifact corruption.
	* --bundle_litert_lm True: Packages tokenizer and templates into the `.litertlm` artifact.

	---

	### 💻 Infrastructure Requirements

	\| Requirement \| Specification \| Context \|
	\| :--- \| :--- \| :--- \|
	\| RAM \| 128 GB+ \| Minimum for 31B conversion overhead \|
	\| Disk Space \| 500 GB \| Workspace for intermediate FlatBuffer assets \|
	\| Storage Type \| NVMe SSD \| Crucial for large model serialization \|
	\| Inference \| Apple Silicon / GPU \| 31B is unsuitable for fast CPU-only DPM \|

	---

	### 🔍 Validation Protocol
	For a successful DPM//BENCH run, the artifact must maintain byte-stability. Ensure the following conditions are met:

	1. Integrity: LiteRT-LM binary successfully parses the `.litertlm` bundle.
	2. Determinism: At `temp 0` and a fixed seed, repeated projection calls must yield identical memory-surface bytes.
	3. Format: JSON-only prompts must satisfy schema constraints under high-compression DPM tests.

	---

	### ⚠️ Implementation Boundaries
	* Intended Use: Security incident summarization, telemetry trace compression, and blue-team event reasoning.
	* Non-Intended Use: This is not a standalone decision-making system. It is a projection tool. All outputs require human review and replay-validation in high-stakes environments.

	---

	<div align="right">
	<p><i>Base Model: google/gemma-4-31B-it</i></p>
	</div>