Instructions to use Intel/llava-gemma-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Intel/llava-gemma-2b with Transformers:

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

pipe = pipeline("image-text-to-text", model="Intel/llava-gemma-2b", 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?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Intel/llava-gemma-2b")
model = AutoModelForMultimodalLM.from_pretrained("Intel/llava-gemma-2b", 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 Intel/llava-gemma-2b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Intel/llava-gemma-2b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Intel/llava-gemma-2b",
		"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/Intel/llava-gemma-2b

SGLang

How to use Intel/llava-gemma-2b 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 "Intel/llava-gemma-2b" \
    --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": "Intel/llava-gemma-2b",
		"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 "Intel/llava-gemma-2b" \
        --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": "Intel/llava-gemma-2b",
		"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 Intel/llava-gemma-2b with Docker Model Runner:
```
docker model run hf.co/Intel/llava-gemma-2b
```

matthewlyleolson commited on Jun 10, 2024

Commit

b5674bf

verified ·

1 Parent(s): d51c5d1

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -3

README.md CHANGED Viewed

@@ -51,7 +51,7 @@ pipeline_tag: image-text-to-text
 | Model Details | Description |
 | ----------- | ----------- |
-| Authors | Intel: [Musashi Hinck](https://huggingface.co/musashihinck), [Matthew Olson](https://huggingface.co/matthewlyleolson), [David Cobbley](https://huggingface.co/djcobble), [Shao-Yen Tseng](https://huggingface.co/shaoyent), [Vasudev Lal](https://huggingface.co/vasudevlal) |
 | Date | March 2024 |
 | Version | 1 |
 | Type | Large multimodal model (LMM) |
@@ -71,7 +71,7 @@ This model card was created by [Benjamin Consolvo](https://huggingface.co/bconso
 ### How to use
-Currently, using `llava-gemma` requires a [modified preprocessor](./processing_llavagemma.py). _We are currently working on modifying the `LlavaProcessor` class to streamline usage (see [PR #30030](https://github.com/huggingface/transformers/pull/30030)). Expect updates soon._
 For current usage, see [`usage.py`](./usage.py) or the following code block:
@@ -83,7 +83,8 @@ from transformers import (
   AutoTokenizer,
   CLIPImageProcessor
 )
-from processing_llavagemma import LlavaGemmaProcessor # This is in this repo
 checkpoint = "Intel/llava-gemma-2b"

 | Model Details | Description |
 | ----------- | ----------- |
+| Authors | Intel: [Musashi Hinck*](https://huggingface.co/musashihinck), [Matthew L. Olson*](https://huggingface.co/matthewlyleolson), [David Cobbley](https://huggingface.co/djcobble), [Shao-Yen Tseng](https://huggingface.co/shaoyent), [Vasudev Lal](https://huggingface.co/vasudevlal) |
 | Date | March 2024 |
 | Version | 1 |
 | Type | Large multimodal model (LMM) |
 ### How to use
+Using `llava-gemma` requires a [modified preprocessor](./processing_llavagemma.py) if your transformers version is < 4.41.1
 For current usage, see [`usage.py`](./usage.py) or the following code block:
   AutoTokenizer,
   CLIPImageProcessor
 )
+#In this repo, needed for version < 4.41.1
+#from processing_llavagemma import LlavaGemmaProcessor
 checkpoint = "Intel/llava-gemma-2b"