Instructions to use tiny-random/gemma-4e with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiny-random/gemma-4e with Transformers:

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

pipe = pipeline("image-text-to-text", model="tiny-random/gemma-4e")
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("tiny-random/gemma-4e")
model = AutoModelForImageTextToText.from_pretrained("tiny-random/gemma-4e")
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 tiny-random/gemma-4e with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiny-random/gemma-4e"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiny-random/gemma-4e",
		"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/tiny-random/gemma-4e

SGLang

How to use tiny-random/gemma-4e 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 "tiny-random/gemma-4e" \
    --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": "tiny-random/gemma-4e",
		"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 "tiny-random/gemma-4e" \
        --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": "tiny-random/gemma-4e",
		"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 tiny-random/gemma-4e with Docker Model Runner:
```
docker model run hf.co/tiny-random/gemma-4e
```

yujiepan commited on 3 days ago

Commit

3a207ad

verified ·

1 Parent(s): 5a1b2b2

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

.meta.json +1 -1
README.md +5 -5
model.safetensors +1 -1

.meta.json CHANGED Viewed

@@ -1,4 +1,4 @@
 {
-  "torch": "2.12.0",
   "transformers": "5.9.0"
 }

 {
+  "torch": "2.10.0+cu130",
   "transformers": "5.9.0"
 }

README.md CHANGED Viewed

@@ -28,7 +28,7 @@ messages = [
         "content": [
             {
                 "type": "audio",
-                "audio": "https://raw.githubusercontent.com/google-gemma/cookbook/refs/heads/main/Demos/sample-data/journal1.wav",
             },
             {"type": "text", "text": "Transcribe the following speech segment."},
         ],
@@ -42,7 +42,7 @@ messages = [
         "content": [
             {
                 "type": "image",
-                "url": "https://raw.githubusercontent.com/google-gemma/cookbook/refs/heads/main/Demos/sample-data/GoldenGate.png",
             },
             {"type": "text", "text": "What is shown in this image?"},
         ],
@@ -345,12 +345,12 @@ Gemma4ForConditionalGeneration(
       (subsample_conv_projection): Gemma4AudioSubSampleConvProjection(
         (layer0): Gemma4AudioSubSampleConvProjectionLayer(
           (conv): Conv2d(1, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
-          (norm): LayerNorm((128,), eps=1e-06, elementwise_affine=True, bias=False)
           (act): ReLU()
         )
         (layer1): Gemma4AudioSubSampleConvProjectionLayer(
           (conv): Conv2d(128, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
-          (norm): LayerNorm((32,), eps=1e-06, elementwise_affine=True, bias=False)
           (act): ReLU()
         )
         (input_proj_linear): Linear(in_features=1024, out_features=64, bias=False)
@@ -431,5 +431,5 @@ Gemma4ForConditionalGeneration(
 ### Test environment:
-- torch: 2.12.0
 - transformers: 5.9.0

         "content": [
             {
                 "type": "audio",
+                "audio": "https://github.com/google-gemma/cookbook/raw/refs/heads/main/apps/sample-data/journal1.wav",
             },
             {"type": "text", "text": "Transcribe the following speech segment."},
         ],
         "content": [
             {
                 "type": "image",
+                "url": "https://raw.githubusercontent.com/google-gemma/cookbook/4a352192744f73fba5b80aeea3a8ba9b543edd29/apps/sample-data/surprise.png",
             },
             {"type": "text", "text": "What is shown in this image?"},
         ],
       (subsample_conv_projection): Gemma4AudioSubSampleConvProjection(
         (layer0): Gemma4AudioSubSampleConvProjectionLayer(
           (conv): Conv2d(1, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
+          (norm): LayerNorm((128,), eps=1e-06, elementwise_affine=True)
           (act): ReLU()
         )
         (layer1): Gemma4AudioSubSampleConvProjectionLayer(
           (conv): Conv2d(128, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
+          (norm): LayerNorm((32,), eps=1e-06, elementwise_affine=True)
           (act): ReLU()
         )
         (input_proj_linear): Linear(in_features=1024, out_features=64, bias=False)
 ### Test environment:
+- torch: 2.10.0+cu130
 - transformers: 5.9.0

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8582ee51fce3dac0a80d9a90008785011e2e24d9d26234822df7361d2092877b
 size 9470740

 version https://git-lfs.github.com/spec/v1
+oid sha256:032cdee368a3cf233b3ec293cff59bdbcf7d39a836d66b34f44337151da85fe0
 size 9470740