Instructions to use kontextdev/agent-gemma with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kontextdev/agent-gemma with Transformers:

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

pipe = pipeline("image-text-to-text", model="kontextdev/agent-gemma")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("kontextdev/agent-gemma")
model = AutoModelForImageTextToText.from_pretrained("kontextdev/agent-gemma")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kontextdev/agent-gemma with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kontextdev/agent-gemma"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kontextdev/agent-gemma",
		"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/kontextdev/agent-gemma

SGLang

How to use kontextdev/agent-gemma 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 "kontextdev/agent-gemma" \
    --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": "kontextdev/agent-gemma",
		"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 "kontextdev/agent-gemma" \
        --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": "kontextdev/agent-gemma",
		"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"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use kontextdev/agent-gemma with Docker Model Runner:
```
docker model run hf.co/kontextdev/agent-gemma
```

agent-gemma / config.json

macmacmacmac

Upload folder using huggingface_hub

4174976 verified about 2 months ago

raw

history blame contribute delete

4.5 kB

	{
	"architectures": [
	"Gemma3nForConditionalGeneration"
	],
	"audio_config": {
	"conf_attention_chunk_size": 12,
	"conf_attention_context_left": 13,
	"conf_attention_context_right": 0,
	"conf_attention_logit_cap": 50.0,
	"conf_conv_kernel_size": 5,
	"conf_num_attention_heads": 8,
	"conf_num_hidden_layers": 12,
	"conf_reduction_factor": 4,
	"conf_residual_weight": 0.5,
	"dtype": "bfloat16",
	"gradient_clipping": 10000000000.0,
	"hidden_size": 1536,
	"input_feat_size": 128,
	"model_type": "gemma3n_audio",
	"rms_norm_eps": 1e-06,
	"sscp_conv_channel_size": [
	128,
	32
	],
	"sscp_conv_group_norm_eps": 0.001,
	"sscp_conv_kernel_size": [
	[
	3,
	3
	],
	[
	3,
	3
	]
	],
	"sscp_conv_stride_size": [
	[
	2,
	2
	],
	[
	2,
	2
	]
	],
	"vocab_offset": 262272,
	"vocab_size": 128
	},
	"audio_soft_tokens_per_image": 188,
	"audio_token_id": 262273,
	"boa_token_id": 256000,
	"boi_token_id": 255999,
	"dtype": "bfloat16",
	"eoa_token_id": 262272,
	"eoi_token_id": 262144,
	"eos_token_id": [
	1,
	106
	],
	"image_token_id": 262145,
	"initializer_range": 0.02,
	"model_type": "gemma3n",
	"text_config": {
	"activation_sparsity_pattern": [
	0.95,
	0.95,
	0.95,
	0.95,
	0.95,
	0.95,
	0.95,
	0.95,
	0.95,
	0.95,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0
	],
	"altup_active_idx": 0,
	"altup_coef_clip": 120.0,
	"altup_correct_scale": true,
	"altup_num_inputs": 4,
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 2,
	"dtype": "bfloat16",
	"eos_token_id": 1,
	"final_logit_softcapping": 30.0,
	"head_dim": 256,
	"hidden_activation": "gelu_pytorch_tanh",
	"hidden_size": 2048,
	"hidden_size_per_layer_input": 256,
	"initializer_range": 0.02,
	"intermediate_size": [
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192,
	8192
	],
	"laurel_rank": 64,
	"layer_types": [
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention"
	],
	"max_position_embeddings": 32768,
	"model_type": "gemma3n_text",
	"num_attention_heads": 8,
	"num_hidden_layers": 30,
	"num_key_value_heads": 2,
	"num_kv_shared_layers": 10,
	"pad_token_id": 0,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"full_attention": {
	"rope_theta": 1000000.0,
	"rope_type": "default"
	},
	"sliding_attention": {
	"rope_theta": 10000.0,
	"rope_type": "default"
	}
	},
	"sliding_window": 512,
	"tie_word_embeddings": true,
	"use_cache": true,
	"vocab_size": 262400,
	"vocab_size_per_layer_input": 262144
	},
	"tie_word_embeddings": true,
	"transformers_version": "5.3.0",
	"vision_config": {
	"architecture": "mobilenetv5_300m_enc",
	"do_pooling": false,
	"dtype": "bfloat16",
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"label_names": [
	"LABEL_0",
	"LABEL_1"
	],
	"model_args": null,
	"model_type": "gemma3n_vision",
	"num_classes": 2,
	"rms_norm_eps": 1e-06,
	"vocab_offset": 262144,
	"vocab_size": 128
	},
	"vision_soft_tokens_per_image": 256
	}