Instructions to use reinforce20001/gemma4-26b-a4b-it-qat-w4a16-ct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use reinforce20001/gemma4-26b-a4b-it-qat-w4a16-ct with Transformers:

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

pipe = pipeline("image-text-to-text", model="reinforce20001/gemma4-26b-a4b-it-qat-w4a16-ct")
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("reinforce20001/gemma4-26b-a4b-it-qat-w4a16-ct")
model = AutoModelForMultimodalLM.from_pretrained("reinforce20001/gemma4-26b-a4b-it-qat-w4a16-ct")
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 reinforce20001/gemma4-26b-a4b-it-qat-w4a16-ct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "reinforce20001/gemma4-26b-a4b-it-qat-w4a16-ct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "reinforce20001/gemma4-26b-a4b-it-qat-w4a16-ct",
		"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/reinforce20001/gemma4-26b-a4b-it-qat-w4a16-ct

SGLang

How to use reinforce20001/gemma4-26b-a4b-it-qat-w4a16-ct 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 "reinforce20001/gemma4-26b-a4b-it-qat-w4a16-ct" \
    --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": "reinforce20001/gemma4-26b-a4b-it-qat-w4a16-ct",
		"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 "reinforce20001/gemma4-26b-a4b-it-qat-w4a16-ct" \
        --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": "reinforce20001/gemma4-26b-a4b-it-qat-w4a16-ct",
		"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 reinforce20001/gemma4-26b-a4b-it-qat-w4a16-ct with Docker Model Runner:
```
docker model run hf.co/reinforce20001/gemma4-26b-a4b-it-qat-w4a16-ct
```

Methodology?

by JDWarner - opened 8 days ago

Discussion

JDWarner

8 days ago

I noticed this wasn't part of the official release package, and considered making one with Intel Autoround. The Readme doesn't have any info about methods or reproducibility.

Would you consider adding that to the Readme and here? Specifically interested in the package and flags used, as well as calibration data.

reinforce20001

Owner 7 days ago

This was created by using the tokenizer and config from google/gemma-4-26B-A4B-it-qat-q4_0-unquantized, copying and processing the weights from google/gemma-4-26B-A4B-it-qat-q4_0-gguf, and adding some necessary padding for vLLM. Therefore, no calibration data or flags related.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment