Instructions to use wls04/gemma_web with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wls04/gemma_web with Transformers:

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

pipe = pipeline("image-text-to-text", model="wls04/gemma_web")
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("wls04/gemma_web")
model = AutoModelForMultimodalLM.from_pretrained("wls04/gemma_web")
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 wls04/gemma_web with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wls04/gemma_web"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wls04/gemma_web",
		"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/wls04/gemma_web

SGLang

How to use wls04/gemma_web 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 "wls04/gemma_web" \
    --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": "wls04/gemma_web",
		"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 "wls04/gemma_web" \
        --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": "wls04/gemma_web",
		"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 wls04/gemma_web with Docker Model Runner:
```
docker model run hf.co/wls04/gemma_web
```

gemma_web / trainer_log.jsonl

wls04

Upload model

20acb38 verified 12 months ago

Raw

History Blame Contribute Delete

1.28 kB

	{"current_steps": 10, "total_steps": 67, "loss": 1.7659, "lr": 9.972609476841368e-06, "epoch": 0.15023474178403756, "percentage": 14.93, "elapsed_time": "1:02:40", "remaining_time": "5:57:17"}
	{"current_steps": 20, "total_steps": 67, "loss": 0.5183, "lr": 9.045084971874738e-06, "epoch": 0.3004694835680751, "percentage": 29.85, "elapsed_time": "2:05:42", "remaining_time": "4:55:25"}
	{"current_steps": 30, "total_steps": 67, "loss": 0.278, "lr": 7.033683215379002e-06, "epoch": 0.4507042253521127, "percentage": 44.78, "elapsed_time": "3:07:59", "remaining_time": "3:51:50"}
	{"current_steps": 40, "total_steps": 67, "loss": 0.2194, "lr": 4.477357683661734e-06, "epoch": 0.6009389671361502, "percentage": 59.7, "elapsed_time": "4:10:01", "remaining_time": "2:48:45"}
	{"current_steps": 50, "total_steps": 67, "loss": 0.1969, "lr": 2.061073738537635e-06, "epoch": 0.7511737089201878, "percentage": 74.63, "elapsed_time": "5:13:51", "remaining_time": "1:46:42"}
	{"current_steps": 60, "total_steps": 67, "loss": 0.1813, "lr": 4.322727117869951e-07, "epoch": 0.9014084507042254, "percentage": 89.55, "elapsed_time": "6:18:20", "remaining_time": "0:44:08"}
	{"current_steps": 67, "total_steps": 67, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "7:00:25", "remaining_time": "0:00:00"}