Instructions to use yujiepan/gemma-3-tiny-random with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yujiepan/gemma-3-tiny-random with Transformers:

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

pipe = pipeline("image-text-to-text", model="yujiepan/gemma-3-tiny-random")
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("yujiepan/gemma-3-tiny-random")
model = AutoModelForMultimodalLM.from_pretrained("yujiepan/gemma-3-tiny-random", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yujiepan/gemma-3-tiny-random with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yujiepan/gemma-3-tiny-random"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yujiepan/gemma-3-tiny-random",
		"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/yujiepan/gemma-3-tiny-random

SGLang

How to use yujiepan/gemma-3-tiny-random 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 "yujiepan/gemma-3-tiny-random" \
    --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": "yujiepan/gemma-3-tiny-random",
		"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 "yujiepan/gemma-3-tiny-random" \
        --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": "yujiepan/gemma-3-tiny-random",
		"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 yujiepan/gemma-3-tiny-random with Docker Model Runner:
```
docker model run hf.co/yujiepan/gemma-3-tiny-random
```

yujiepan commited on Mar 15, 2025

Commit

f746b7c

verified ·

1 Parent(s): 242145c

Upload folder using huggingface_hub

Browse files

Files changed (2) hide show

README.md +3 -0
config.json +1 -1

README.md CHANGED Viewed

@@ -69,6 +69,7 @@ config.text_config.head_dim = 32
 config.text_config.num_attention_heads = 1
 config.text_config.num_key_value_heads = 1
 config.text_config.num_hidden_layers = 2
 config.vision_config.hidden_size = 32
 config.vision_config.num_hidden_layers = 2
 config.vision_config.num_attention_heads = 1
@@ -76,6 +77,8 @@ config.vision_config.intermediate_size = 128
 model = Gemma3ForConditionalGeneration(
     config,
 ).to(torch.bfloat16)
 model.generation_config = GenerationConfig.from_pretrained(
     source_model_id, trust_remote_code=True,
 )

 config.text_config.num_attention_heads = 1
 config.text_config.num_key_value_heads = 1
 config.text_config.num_hidden_layers = 2
+config.text_config.sliding_window_pattern = 2
 config.vision_config.hidden_size = 32
 config.vision_config.num_hidden_layers = 2
 config.vision_config.num_attention_heads = 1
 model = Gemma3ForConditionalGeneration(
     config,
 ).to(torch.bfloat16)
+for layer in model.language_model.model.layers:
+    print(layer.is_sliding)
 model.generation_config = GenerationConfig.from_pretrained(
     source_model_id, trust_remote_code=True,
 )

config.json CHANGED Viewed

@@ -37,7 +37,7 @@
     },
     "rope_theta": 1000000.0,
     "sliding_window": 1024,
-    "sliding_window_pattern": 6,
     "use_cache": true,
     "vocab_size": 262208
   },

     },
     "rope_theta": 1000000.0,
     "sliding_window": 1024,
+    "sliding_window_pattern": 2,
     "use_cache": true,
     "vocab_size": 262208
   },