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

Libraries

How to use z-lab/gemma-4-31B-it-PARO with Transformers:

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

pipe = pipeline("image-text-to-text", model="z-lab/gemma-4-31B-it-PARO")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("z-lab/gemma-4-31B-it-PARO")
model = AutoModelForMultimodalLM.from_pretrained("z-lab/gemma-4-31B-it-PARO", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

MLX

How to use z-lab/gemma-4-31B-it-PARO with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("z-lab/gemma-4-31B-it-PARO")
config = load_config("z-lab/gemma-4-31B-it-PARO")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

vLLM

How to use z-lab/gemma-4-31B-it-PARO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "z-lab/gemma-4-31B-it-PARO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "z-lab/gemma-4-31B-it-PARO",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/z-lab/gemma-4-31B-it-PARO

SGLang

How to use z-lab/gemma-4-31B-it-PARO 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 "z-lab/gemma-4-31B-it-PARO" \
    --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": "z-lab/gemma-4-31B-it-PARO",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "z-lab/gemma-4-31B-it-PARO" \
        --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": "z-lab/gemma-4-31B-it-PARO",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

How to use z-lab/gemma-4-31B-it-PARO with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "z-lab/gemma-4-31B-it-PARO"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "z-lab/gemma-4-31B-it-PARO"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use z-lab/gemma-4-31B-it-PARO with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "z-lab/gemma-4-31B-it-PARO"

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 "z-lab/gemma-4-31B-it-PARO" \
  --custom-provider-id mlx-lm \
  --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 z-lab/gemma-4-31B-it-PARO with Docker Model Runner:
```
docker model run hf.co/z-lab/gemma-4-31B-it-PARO
```

Hermes Agent

How to use z-lab/gemma-4-31B-it-PARO with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "z-lab/gemma-4-31B-it-PARO"

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 z-lab/gemma-4-31B-it-PARO

Run Hermes

hermes

gemma-4-31B-it-PARO / config.json

liang2kl

Upload folder using huggingface_hub

707ecc9 verified 4 months ago

Raw

History Blame

4.74 kB

	{
	"architectures": [
	"Gemma4ForConditionalGeneration"
	],
	"audio_config": null,
	"audio_token_id": 258881,
	"boa_token_id": 256000,
	"boi_token_id": 255999,
	"dtype": "bfloat16",
	"eoa_token_id": 258883,
	"eoa_token_index": 258883,
	"eoi_token_id": 258882,
	"eos_token_id": [
	1,
	106
	],
	"image_token_id": 258880,
	"initializer_range": 0.02,
	"model_type": "gemma4",
	"text_config": {
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attention_k_eq_v": true,
	"bos_token_id": 2,
	"dtype": "bfloat16",
	"enable_moe_block": false,
	"eos_token_id": 1,
	"expert_intermediate_size": null,
	"final_logit_softcapping": 30.0,
	"global_head_dim": 512,
	"head_dim": 256,
	"hidden_activation": "gelu_pytorch_tanh",
	"hidden_size": 5376,
	"hidden_size_per_layer_input": 0,
	"initializer_range": 0.02,
	"intermediate_size": 21504,
	"layer_types": [
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention"
	],
	"max_position_embeddings": 262144,
	"model_type": "gemma4_text",
	"num_attention_heads": 32,
	"num_experts": null,
	"num_global_key_value_heads": 4,
	"num_hidden_layers": 60,
	"num_key_value_heads": 16,
	"num_kv_shared_layers": 0,
	"pad_token_id": 0,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"full_attention": {
	"partial_rotary_factor": 0.25,
	"rope_theta": 1000000.0,
	"rope_type": "proportional"
	},
	"sliding_attention": {
	"rope_theta": 10000.0,
	"rope_type": "default"
	}
	},
	"sliding_window": 1024,
	"tie_word_embeddings": true,
	"top_k_experts": null,
	"use_bidirectional_attention": "vision",
	"use_cache": true,
	"use_double_wide_mlp": false,
	"vocab_size": 262144,
	"vocab_size_per_layer_input": 262144
	},
	"tie_word_embeddings": true,
	"transformers_version": "5.5.0.dev0",
	"video_token_id": 258884,
	"vision_config": {
	"_name_or_path": "",
	"architectures": null,
	"attention_bias": false,
	"attention_dropout": 0.0,
	"chunk_size_feed_forward": 0,
	"default_output_length": 280,
	"dtype": "bfloat16",
	"global_head_dim": 72,
	"head_dim": 72,
	"hidden_activation": "gelu_pytorch_tanh",
	"hidden_size": 1152,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"initializer_range": 0.02,
	"intermediate_size": 4304,
	"is_encoder_decoder": false,
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"max_position_embeddings": 131072,
	"model_type": "gemma4_vision",
	"num_attention_heads": 16,
	"num_hidden_layers": 27,
	"num_key_value_heads": 16,
	"output_attentions": false,
	"output_hidden_states": false,
	"patch_size": 16,
	"pooling_kernel_size": 3,
	"position_embedding_size": 10240,
	"problem_type": null,
	"return_dict": true,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"rope_theta": 100.0,
	"rope_type": "default"
	},
	"standardize": true,
	"use_clipped_linears": false
	},
	"vision_soft_tokens_per_image": 280,
	"quantization_config": {
	"quant_method": "paroquant",
	"bits": 4,
	"group_size": 128,
	"krot": 8
	}
	}