Instructions to use hilman2/gev-e4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hilman2/gev-e4b with Transformers:

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

pipe = pipeline("text-classification", model="hilman2/gev-e4b")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("hilman2/gev-e4b")
model = AutoModelForMultimodalLM.from_pretrained("hilman2/gev-e4b", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use hilman2/gev-e4b 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 hilman2/gev-e4b:Q4_0
# Run inference directly in the terminal:
llama cli -hf hilman2/gev-e4b:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf hilman2/gev-e4b:Q4_0
# Run inference directly in the terminal:
llama cli -hf hilman2/gev-e4b:Q4_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 hilman2/gev-e4b:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf hilman2/gev-e4b:Q4_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 hilman2/gev-e4b:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf hilman2/gev-e4b:Q4_0

Use Docker

docker model run hf.co/hilman2/gev-e4b:Q4_0

LM Studio
Jan
Ollama
How to use hilman2/gev-e4b with Ollama:
```
ollama run hf.co/hilman2/gev-e4b:Q4_0
```
Unsloth Desktop

How to use hilman2/gev-e4b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hilman2/gev-e4b:Q4_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": "hilman2/gev-e4b:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use hilman2/gev-e4b with Docker Model Runner:
```
docker model run hf.co/hilman2/gev-e4b:Q4_0
```

Lemonade

How to use hilman2/gev-e4b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull hilman2/gev-e4b:Q4_0

Run and chat with the model

lemonade run user.gev-e4b-Q4_0

List all available models

lemonade list

Hermes Agent

How to use hilman2/gev-e4b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hilman2/gev-e4b:Q4_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 hilman2/gev-e4b:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use hilman2/gev-e4b with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf hilman2/gev-e4b:Q4_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 "hilman2/gev-e4b:Q4_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"

Gev E4B

Google's Gemma 4 E4B, retrained to answer questions about a text with probabilities: which team should handle a ticket, how urgent it is, whether a rule allows a case. It is the default model of Gev, which serves it through an HTTP API compatible with Jev's /v1/systemone.

The model is meant to be run by Gev, which reads the probability of each answer at one position instead of generating text. It is not tested as a chat model.

Files

File	Use
`model.safetensors`, `config.json`, tokenizer files	the weights, bf16, for building a Mev engine on a Mac (`scripts/build-engine.sh gev-e4b`) or for your own tools
`gev-e4b-q8_0.gguf`	for llama.cpp, 8.0 GB; Gev's Docker image downloads it
`gev-e4b-q4_0.gguf`	for llama.cpp on smaller GPUs, 5.2 GB, laid out like Google's QAT Q4_0 GGUF

Retraining moved the weights off the grid Google's quantization-aware training had put them on, so Q4_0 costs this model more than it costs the original. On the 316 example requests of Gev's playground, the most probable answer through llama.cpp matched the one from the unquantized weights for 99.1 % of the questions with Q8_0 and 93.9 % with Q4_0 (Google's E4B at Q4_0: 96.2 %).

A ready-built engine for Apple's M4 is in hilman2/gev-e4b-mev.