Instructions to use RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic with Transformers:

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

pipe = pipeline("image-text-to-text", model="RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic")
model = AutoModelForMultimodalLM.from_pretrained("RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic",
		"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/RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic

SGLang

How to use RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic 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 "RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic" \
    --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": "RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic",
		"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 "RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic" \
        --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": "RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic",
		"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 RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic with Docker Model Runner:
```
docker model run hf.co/RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic
```

robgreenberg3 commited on Aug 13

Commit

3b3dae4

verified ·

1 Parent(s): d3bca79

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -1

README.md CHANGED Viewed

@@ -20,7 +20,10 @@ validated_on:
   - vLLM 0.24.0
 ---
-# RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic
 This model is an FP8 quantized version of [google/diffusiongemma-26B-A4B-it](https://huggingface.co/google/diffusiongemma-26B-A4B-it). The model has both weights and activations quantized to FP8 using [vllm/llm-compressor](https://github.com/vllm-project/llm-compressor) and in the [compressed-tensors](https://github.com/vllm-project/compressed-tensors) format.
 It was evaluated on several tasks to assess its quality in comparison to the unquantized model using vLLM.

   - vLLM 0.24.0
 ---
+<h1 align: center; style="display: flex; align-items: center; gap: 10px; margin: 0;">
+  diffusiongemma-26B-A4B-it-FP8-dynamic
+  <img src="https://www.redhat.com/rhdc/managed-files/Catalog-Validated_model_0.png" alt="Model Icon" width="40" style="margin: 0; padding: 0;" />
+</h1>
 This model is an FP8 quantized version of [google/diffusiongemma-26B-A4B-it](https://huggingface.co/google/diffusiongemma-26B-A4B-it). The model has both weights and activations quantized to FP8 using [vllm/llm-compressor](https://github.com/vllm-project/llm-compressor) and in the [compressed-tensors](https://github.com/vllm-project/compressed-tensors) format.
 It was evaluated on several tasks to assess its quality in comparison to the unquantized model using vLLM.