Instructions to use capriciousmarauder/test-submodel-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use capriciousmarauder/test-submodel-3 with Transformers:

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

pipe = pipeline("image-text-to-text", model="capriciousmarauder/test-submodel-3")
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("capriciousmarauder/test-submodel-3")
model = AutoModelForMultimodalLM.from_pretrained("capriciousmarauder/test-submodel-3", 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 capriciousmarauder/test-submodel-3 with vLLM:

Install from pip and serve model

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

SGLang

How to use capriciousmarauder/test-submodel-3 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 "capriciousmarauder/test-submodel-3" \
    --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": "capriciousmarauder/test-submodel-3",
		"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 "capriciousmarauder/test-submodel-3" \
        --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": "capriciousmarauder/test-submodel-3",
		"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 capriciousmarauder/test-submodel-3 with Docker Model Runner:
```
docker model run hf.co/capriciousmarauder/test-submodel-3
```

capriciousmarauder commited on Jun 23

Commit

025468a

verified ·

1 Parent(s): 398f730

Update README.md with Gemma3n-E4B-it scores

Browse files

Files changed (1) hide show

README.md +14 -0

README.md CHANGED Viewed

@@ -13,6 +13,7 @@ tags:
 ---
 ```
 mtx@mtx-cv-m13-gpu-master-14:~/Desktop/personal/vlms/evals/VLMEvalKit$ cat outputs/Gemma3n-E2B-it-ts3/*/*.json
 {
     "en_text_recognition": 0.5459304480487074,
@@ -24,6 +25,19 @@ mtx@mtx-cv-m13-gpu-master-14:~/Desktop/personal/vlms/evals/VLMEvalKit$ cat outpu
     "en_knowledge_reasoning": 0.4669721878768469,
     "English Overall Score": 0.3146145912885819
 }
 ```
 > [!Note]

 ---
 ```
+# score for test-submodel-3, which is a slice of Gemma3n-E4B-it
 mtx@mtx-cv-m13-gpu-master-14:~/Desktop/personal/vlms/evals/VLMEvalKit$ cat outputs/Gemma3n-E2B-it-ts3/*/*.json
 {
     "en_text_recognition": 0.5459304480487074,
     "en_knowledge_reasoning": 0.4669721878768469,
     "English Overall Score": 0.3146145912885819
 }
+# score for Gemma3n-E2B-it, google's official published submodel of Gemma3n-E4B-it
+mtx@mtx-cv-m13-gpu-master-14:~/Desktop/personal/vlms/evals/VLMEvalKit$ cat outputs/Gemma3n-E2B-it/T202*/*.json
+{
+    "en_text_recognition": 0.6096878412118829,
+    "en_text_detection": 0.23172620479653033,
+    "en_text_spotting": 0.0,
+    "en_element_parsing": 0.04,
+    "en_mathematical_calculation": 0.3240026170865559,
+    "en_visual_text_understanding": 0.7103983997859018,
+    "en_knowledge_reasoning": 0.5074402603391522,
+    "English Overall Score": 0.34617933188857475
+}
 ```
 > [!Note]